APPARATUS AND METHOD FOR CORRECTING MACHINE LEARNING MODEL PREDICTIONS

FIELD OF THE INVENTION

The present invention generally relates to the field of signal processing. In particular, the present invention is directed to an apparatus and method for correcting machine learning model predictions.

BACKGROUND

Signal processing plays a crucial role in the healthcare industry. In general, to interpret critical information from signals such as cardiac signals, it is required that signal labeling be performed accurately. However, there are various challenges in signal labeling, such as signal interpretation subjectivity, human errors, high time consumption, and extensive training requirements. These challenges may cause negative impacts on the accuracy of diagnosis and clinical decision-making.

SUMMARY OF THE DISCLOSURE

In an aspect, an apparatus for correcting machine learning model predictions is described. Apparatus includes a processor and a memory communicatively connected to the processor, wherein the memory contains instructions configuring the processor to receive at least a cardiac signal having a plurality of segments, generate, for at least a segment of the plurality of segments, a label representing at least a signal feature, generate at least an automated annotation as a function of the label using an annotation machine learning model trained with annotation training data, generate, using a correction module, at least a correction upon detecting an absence of annotations, receive, using a user interface, at least an input from a user, create at least a user annotation within the at least a cardiac signal using the at least an input, wherein creating the at least a user annotation includes validating the at least an automated annotation and generating, for each incorrect automatic annotation identified based on the validation, the at least a user annotation, update the at least a cardiac signal and the annotation machine learning model as a function of the at least a correction and the at least a user annotation, and display, using the user interface, the updated at least a cardiac signal to the user.

In another aspect, a method for correcting machine learning model predictions is described. Method is performed by processor and includes receiving at least a cardiac signal having plurality of segments, generating, for at least a segment of the plurality of segments, label representing at least a signal feature, generating at least an automated annotation as a function of the label using annotation machine learning model trained with annotation training data, generating using correction module at least a correction upon detecting an absence of annotations, receiving, using user interface, at least an input from user, creating at least a user annotation within the at least a cardiac signal using the at least an input, wherein creating the at least a user annotation includes validating the at least an automated annotation and generating, for each incorrect automatic annotation identified based on the validation, the at least a user annotation, updating the at least a cardiac signal and the annotation machine learning model as a function of the at least a correction and the at least a user annotation, and displaying, by the processor using the user interface, the updated at least a cardiac signal to the user.

These and other aspects and features of nonlimiting embodiments of the present invention will become apparent to those skilled in the art upon review of the following description of specific nonlimiting embodiments of the invention in conjunction with the accompanying drawings.

BRIEF DESCRIPTION OF THE DRAWINGS

For the purpose of illustrating the invention, the drawings show aspects of one or more embodiments of the invention. However, it should be understood that the present invention is not limited to the precise arrangements and instrumentalities shown in the drawings, wherein:

FIG. 1 is an exemplary embodiment of an apparatus for correcting machine learning model predictions;

FIG. 2 is an exemplary embodiment of an electrocardiogram (ECG);

FIG. 3 is a block diagram of an exemplary embodiment of a machine learning process;

FIG. 4 is a block diagram of an exemplary embodiment of a neural network;

FIG. 5 is a block diagram of an exemplary embodiment of a node of a neural network;

FIG. 6 is an illustration of an exemplary embodiment of fuzzy set comparison;

FIG. 7 is an exemplary flow diagram illustrating a method for correcting machine learning model predictions;

FIG. 8 is an exemplary embodiment of a workflow of the apparatus;

FIG. 9A-D are exemplary embodiments of graphical user interfaces (GUIs); and

FIG. 10 is a block diagram of an exemplary embodiment of a computing system that can be used to implement any one or more of the methodologies disclosed herein and any one or more portions thereof.

The drawings are not necessarily to scale and may be illustrated by phantom lines, diagrammatic representations and fragmentary views. In certain instances, details that are not necessary for an understanding of the embodiments or that render other details difficult to perceive may have been omitted.

DETAILED DESCRIPTION

At a high level, aspects of the present disclosure are directed to apparatus and methods for correcting machine learning model predictions. Apparatus includes a processor and a memory communicatively connected to the processor, wherein the memory contains instructions configuring the processor to receive at least a cardiac signal having a plurality of segments, generate, for at least a segment of the plurality of segments, a label representing at least a signal feature, generate at least an automated annotation as a function of the label using an annotation machine learning model trained with annotation training data, generate, using a correction module, at least a correction upon detecting an absence of annotations, receive, using a user interface, at least an input from a user, create at least a user annotation within the at least a cardiac signal using the at least an input, wherein creating the at least a user annotation includes validating the at least an automated annotation and generating, for each incorrect automatic annotation identified based on the validation, the at least a user annotation, update the at least a cardiac signal and the annotation machine learning model as a function of the at least a correction and the at least a user annotation, and display, using the user interface, the updated at least a cardiac signal to the user.

Aspects of the present disclosure may be used to streamline signal processing and signal labeling procedures. Aspects of the present disclosure may be used to provide efficient clinical decision support. Exemplary embodiments illustrating aspects of the present disclosure are described below in the context of several specific examples.

Referring now to FIG. 1, an apparatus 100 for correcting machine learning model predictions is illustrated. Apparatus 100 includes a processor 104. In one or more embodiments, processor 104 may include a computing device. Computing device could include any analog or digital control circuit, including an operational amplifier circuit, a combinational logic circuit, a sequential logic circuit, an application-specific integrated circuit (ASIC), a field programmable gate arrays (FPGA), or the like. Computing device may include a processor communicatively connected to a memory, as described above. Computing device may include any computing device as described in this disclosure, including without limitation a microcontroller, microprocessor, digital signal processor, and/or system on a chip as described in this disclosure. Computing device may include, be included in, and/or communicate with a mobile device such as a mobile telephone, smartphone, or tablet. Computing device may include a single computing device operating independently, or may include two or more computing device operating in concert, in parallel, sequentially, or the like; two or more computing devices may be included together in a single computing device or in two or more computing devices. Computing device may interface or communicate with one or more additional devices as described below in further detail via a network interface device. Network interface device may be utilized for connecting computing device to one or more of a variety of networks, and one or more devices. Examples of a network interface device include, but are not limited to, a network interface card (e.g., a mobile network interface card, a LAN card), a modem, and any combination thereof. Examples of a network include, but are not limited to, a wide area network (e.g., the Internet, an enterprise network), a local area network (e.g., a network associated with an office, a building, a campus, or other relatively small geographic space), a telephone network, a data network associated with a telephone/voice provider (e.g., a mobile communications provider data and/or voice network), a direct connection between two computing devices, and any combinations thereof. A network may employ a wired and/or a wireless mode of communication. In general, any network topology may be used. Information (e.g., data, software etc.) may be communicated to and/or from a computer and/or a computing device. Computing device may include but is not limited to, for example, a first computing device or cluster of computing devices in a first location and a second computing device or cluster of computing devices in a second location. Computing device may include one or more computing devices dedicated to data storage, security, distribution of traffic for load balancing, and the like. Computing device may distribute one or more computing tasks as described below across a plurality of computing devices of computing device, which may operate in parallel, in series, redundantly, or in any other manner used for distribution of tasks or memory between computing devices. Computing device may be implemented, as a nonlimiting example, using a “shared nothing” architecture.

With continued reference to FIG. 1, computing device may be designed and/or configured to perform any method, method step, or sequence of method steps in any embodiment described in this disclosure, in any order and with any degree of repetition. For instance, computing device may be configured to perform a single step or sequence repeatedly until a desired or commanded outcome is achieved; repetition of a step or a sequence of steps may be performed iteratively and/or recursively using outputs of previous repetitions as inputs to subsequent repetitions, aggregating inputs and/or outputs of repetitions to produce an aggregate result, reduction or decrement of one or more variables such as global variables, and/or division of a larger processing task into a set of iteratively addressed smaller processing tasks. Computing device may perform any step or sequence of steps as described in this disclosure in parallel, such as simultaneously and/or substantially simultaneously performing a step two or more times using two or more parallel threads, processor cores, or the like; division of tasks between parallel threads and/or processes may be performed according to any protocol suitable for division of tasks between iterations. A person of ordinary skill in the art, upon reviewing the entirety of this disclosure, will be aware of various ways in which steps, sequences of steps, processing tasks, and/or data may be subdivided, shared, or otherwise dealt with using iteration, recursion, and/or parallel processing. More details regarding computing devices will be described below.

With continued reference to FIG. 1, apparatus 100 includes a memory 108 communicatively connected to processor 104, wherein the memory 108 contains instructions configuring the processor 104 to perform any processing steps described herein. For the purposes of this disclosure, “communicatively connected” means connected by way of a connection, attachment, or linkage between two or more relata which allows for reception and/or transmittance of information therebetween. For example, and without limitation, this connection may be wired or wireless, direct, or indirect, and between two or more components, circuits, devices, systems, and the like, which allows for reception and/or transmittance of data and/or signal(s) therebetween. Data and/or signals therebetween may include, without limitation, electrical, electromagnetic, magnetic, video, audio, radio, and microwave data and/or signals, combinations thereof, and the like, among others. A communicative connection may be achieved, for example and without limitation, through wired or wireless electronic, digital, or analog, communication, either directly or by way of one or more intervening devices or components. Further, communicative connection may include electrically coupling or connecting at least an output of one device, component, or circuit to at least an input of another device, component, or circuit. For example, and without limitation, using a bus or other facility for intercommunication between elements of a computing device. Communicative connecting may also include indirect connections via, for example and without limitation, wireless connection, radio communication, low-power wide-area network, optical communication, magnetic, capacitive, or optical coupling, and the like. In some instances, the terminology “communicatively coupled” may be used in place of communicatively connected in this disclosure.

With continued reference to FIG. 1, computing device may perform determinations, classification, and/or analysis steps, methods, processes, or the like as described in this disclosure using machine learning processes. For the purposes of this disclosure, a “machine learning process” is a process that automatedly uses a body of data known as “training data” and/or a “training set” to generate an algorithm that will be performed by a processor module to produce outputs given data provided as inputs. This is in contrast to a nonmachine learning software program where the commands to be executed are determined in advance by a user and written in a programming language. A machine learning process may utilize supervised, unsupervised, lazy-learning processes and/or neural networks. More details regarding computing devices and machine learning processes will be provided below.

With continued reference to FIG. 1, in one or more embodiments, apparatus 100 may include or be communicatively connected to a database. For the purposes of this disclosure, a “database” is an organized collection of data, or a type of data store based on the use of a database management system (DBMS), the software that interacts with end users, applications, and the database itself to capture and analyze the data. Database may be implemented, without limitation, as a relational database, a key-value retrieval database such as a NoSQL database, or any other format or structure for use as database that a person of ordinary skill in the art would recognize as suitable upon review of the entirety of this disclosure. Database may alternatively or additionally be implemented using a distributed data storage protocol and/or data structure, such as a distributed hash table or the like. Database may include a plurality of data entries and/or records as described in this disclosure. Data entries in database may be flagged with or linked to one or more additional elements of information, which may be reflected in data entry cells and/or in linked tables such as tables related by one or more indices in database or another relational database. A person of ordinary skill in the art, upon reviewing the entirety of this disclosure, will be aware of various ways in which data entries in database may store, retrieve, organize, and/or reflect data and/or records as used herein, as well as categories and/or populations of data consistently with this disclosure.

With continued reference to FIG. 1, apparatus 100 may include or be communicatively connected to one or more electronic health records (EHRs) of one or more patients. For the purposes of this disclosure, an electronic health record (EHR) is a comprehensive collection of records relating to the health history, diagnosis, or condition of patient, relating to treatment provided or proposed to be provided to the patient, or relating to additional factors that may impact the health of the patient. Elements within an EHR, once combined, provide a detailed picture of a patient's overall health. In one or more embodiments, data may be deposited to and retrieved from one or more EHRs in order to in order to perform one or more functions of apparatus 100. In one or more embodiments, EHR may include demographic data of patient; for example, and without limitation, EHR may include basic information about patient such as name, age, gender, ethnicity, socioeconomic status, and/or the like. In one or more embodiments, each EHR may also include patient's medical history; for example, and without limitation, EHR may include a detailed record of patient's past health conditions, medical procedures, hospitalizations, and illnesses such as surgeries, treatments, medications, allergies, and/or the like. In one or more embodiments, each EHR may include lifestyle information of patient; for example, and without limitation, EHR may include details about the patient's diet, exercise habits, smoking and alcohol consumption, and other behaviors that could impact patient's health. In one or more embodiments, EHR may include patient's family history; for example, and without limitation, EHR may include a record of hereditary diseases. In one or more embodiments, EHR may include one or more digital files or documents that contain one or more elements described above. In one or more embodiments, a database may include a plurality of EHRs. In one or more embodiments, EHRs may be deposited to and/or retrieved from a database or a repository of similar nature as a database.

With continued reference to FIG. 1, for the purposes of this disclosure, a “patient” is a human or any individual organism, on whom or on which a procedure, study, or otherwise experiment, is conducted. As nonlimiting examples, patient may include a human subject with symptoms of atrial fibrillation or pulmonary hypertension, an individual undergoing cardiac screening, a participant in a clinical trial, an individual with congenital heart disease, a heart transplant candidate, an individual receiving follow-up care after cardiac surgery, a healthy volunteer, an individual with heart failure, or the like. Additionally, or alternatively, patient may include a pet or an animal model (i.e., an animal used to model certain medical conditions such as a laboratory rat).

With continued reference to FIG. 1, apparatus 100 may include or be communicatively connected to a data repository 112. For the purposes of this disclosure, a “data repository” is a structured collection of data from which one or more data elements are retrieved, or to which another set of data is compared in order to obtain one or more results and/or initiate one or more steps. Data repository 112 may include at least a cardiac signal 116 pertaining to a patient, as described below. In one or more embodiments, data repository 112 may include a plurality of EHRs, consistent with details described above. Additionally, and/or alternatively, data repository 112 may include, for example and without limitation, clinical data, research findings, case studies, diagnostic criteria, treatment outcomes, patient records, and/or the like. Additionally, and/or alternatively, data repository 112 may include or be linked to a centralized or distributed source of medical data such as a hospital information system (HIS), regional health information organization (RHIO), health information exchange (HIE), cloud-based EHR platform, research database and biobank, public health database, clinical registry, among others. In one or more embodiments, data repository 112 may include one or more databases or the like and may be implemented in any manner suitable for implementation of databases.

With continued reference to FIG. 1, for the purposes of this disclosure, a “cardiac signal” is a signal pertaining to the structural and/or functional features of a patient's heart. Nonlimiting examples of cardiac signal 116 include echocardiogram (ECG) signal, intracardiac electrogram (IEGM) signal 120, ultrasound imaging signal including intracardiac echocardiogram (ICE), transthoracic echocardiogram, and/or transesophageal echocardiogram (TEE) signal, and/or the like. For the purposes of this disclosure, an “electrocardiogram (ECG)” is a recording of electrical activity of patient's heart over a period of time; “ECG” and “ECG data” may be used interchangeably throughout this disclosure. In one or more embodiments, ECG data may include one or more recordings captured by a plurality (e.g., 12) of electrodes placed on patient's skin. In one or more embodiments, ECG data may include information regarding a P wave, T wave, QRS complex, PR interval, ST segment, and/or the like, as described in detail below in this disclosure. In one or more embodiments, ECG data may be used to identify specific cardiac events or phases of a cardiac cycle, e.g., isovolumic relaxation, ventricular filling, isovolumic contraction, and rapid ventricular ejection. For the purposes of this disclosure, “intracardiac electrogram (IEGM)” is a diagnostic recording obtained directly from within a patient's heart, capturing the electrical activity of the cardiac tissue therein. IEGM is generated using electrodes positioned inside the heart chambers or on the heart's surface. IEGM provides detailed insights into a cardiac conduction system and is crucial for diagnosing and treating various cardiac arrhythmias and other heart conditions. An IEGM signal reflects the electrical impulses that dictate heart muscle contraction, offering a high-resolution view of cardiac electrical functions compared to surface electrocardiograms (ECGs) described above. In some cases, IEGM may be considered essential in electrophysiology studies, catheter ablation procedures, and monitoring of implanted cardiac devices such as pacemakers and defibrillators, among others.

With continued reference to FIG. 1, for the purposes of this disclosure, an “intracardiac echocardiogram (ICE)” is a two-dimensional (2D) ultrasound image collected by inserting, using a catheter, an ultrasound transducer inside a heart; it represents the anatomy (i.e., walls, chambers, blood vessels, etc.) of at least part of a heart. In some cases, ICE may be collected by crossing the interatrial septum with a transseptal puncture to permit catheter access from the right atrium to the left atrium; alternatively, catheter may access the left heart by retrograding through the aorta and passing the aortic valve into the left ventricle. For the purposes of this disclosure, a “transthoracic echocardiogram (TTE) frame” is a 2D ultrasound image collected by placing a probe or ultrasound transducer on patient's chest or abdomen to collect various views of heart. For the purposes of this disclosure, a “transesophageal echocardiogram (TEE) frame” is a 2D ultrasound image collected by passing a specialized probe containing an ultrasound transducer at its tip into patient's esophagus; it is an alternative way of performing echocardiography. For the purposes of this disclosure, “echocardiography” is an imaging technique that uses ultrasound to examine a heart, the resulting visual image of which is an echocardiogram.

With continued reference to FIG. 1, for the purposes of this disclosure, a “signal” is any intelligible representation of data, for example from one device to another. A signal may include an optical signal, a hydraulic signal, a pneumatic signal, a mechanical signal, an electric signal, a digital signal, an analog signal, and the like. In some cases, a signal may be used to communicate with a computing device, for example by way of one or more ports. In some cases, a signal may be transmitted and/or received by a computing device for example by way of an input/output port. An analog signal may be digitized, for example by way of an analog to digital converter. In some cases, an analog signal may be processed, for example by way of any analog signal processing steps described in this disclosure, prior to digitization. In some cases, a digital signal may be used to communicate between two or more devices, including without limitation computing devices. In some cases, a digital signal may be communicated by way of one or more communication protocols, including without limitation internet protocol (IP), controller area network (CAN) protocols, serial communication protocols (e.g., universal asynchronous receiver-transmitter [UART]), parallel communication protocols (e.g., IEEE 128 [printer port]), and the like.

With continued reference to FIG. 1, in one or more embodiments, cardiac signal 116 may include time series data 124 of a patient. For the purposes of this disclosure, “time series data” are data measured as a function of time and/or recorded over consistent intervals of time. In one or more embodiments, time series data 124 may include information related to patient's cardiac health and recorded over weeks, months, years, or decades. As a nonlimiting example, time series data 124 may include parameters such as filling pressure and/or ejection volume/fraction of one or more chambers of a heart. As another nonlimiting example, time series data 124 may include cases of pulmonary hypertension, diastolic/systolic dysfunctions, atrial/ventricular fibrillation, heart failure, as well as grades or levels of severity related thereto, among others. In one or more embodiments, time series data 124 may include one or more signals or parameters, such as voltage, measured using one or more medical facilities over a short time span. In some cases, time series data 124 may include waveform time series data 124. In some cases, time series data 124 may include at least an IEGM signal 120. In some cases, times series data may include at least an ECG signal. In some cases, time series data 124 may be created in a protocol buffer format. For the purposes of this disclosure, “Protocol Buffer Format”, commonly known as protobuf, is a language-neutral, platform-neutral, extensible mechanism for serializing structured data. It encodes structured data in a compact binary format and allows for efficient serialization and deserialization of complex data structures, providing a language-agnostic way to define, serialize, and deserialize data. Developed by Google, it is widely used for data storage, communication protocols, among others. Protocol Buffer Format uses “.proto” files to define data structures, which are compiled into source code for various programming languages. Protocol Buffer Format is suitable for inter-service communication, data storage, configuration files, and remote procedure calls, and supports extensibility, ensuring compatibility across different versions of software systems.

With continued reference to FIG. 1, in one or more embodiments, cardiac signal 116 may be accompanied by metadata. for the purposes of this disclosure, “metadata” are secondary data providing background information about one or more aspects of certain primary data that potentially make it easier to track and/or work with the primary data. In one or more embodiments, metadata may include details regarding how a medical procedure was performed. As a nonlimiting example, for an ablation procedure, metadata may include parameters such as pulse duration, frequency, pulse width, amplitude, power of ablation, total energy delivered, total treatment time, energy delivered to a particular location, treatment time at a particular location, current, average power, peak power, and biphasic vs monophasic pulse delivery, among others.

With continued reference to FIG. 1, processor 104 is configured to receive at least a cardiac signal 116 having a plurality of segments. In one or more embodiments, processor 104 may be configured to retrieve cardiac signal 116 from data repository 112 and/or from a signal capturing device such as a sensor. In one or more embodiments, at least a cardiac signal 116 includes time series data 124, consistent with details described above. In some cases, plurality of segments may include a plurality of time series segments. In some cases, time series data 124 may include plurality of time series segments. For the purposes of this disclosure, a “time series segment” is portion of time series data 124 that spans across a fraction of a temporal window associated with the time series data 124. For the purposes of this disclosure, a “segment” is a portion of a set of data selected based on one or more variables. In some cases, time series segments may be divided as a function of evenly spaced temporal cutoffs, such as at an end of every interval of 1 s, 2 s, 3 s, or the like. In some cases, time series segments may be divided based on one or more features of time series data, such as one or more peaks, troughs, rises, decays, plateaus, 1^st/2^ndderivative features, among others. As a nonlimiting example, when time series data 124 includes one or more ECG signals, time series segment may include one or more elements of P wave, T wave, QRS complex, PR interval, ST segment, and/or the like, as described in detail below in this disclosure.

With continued reference to FIG. 1, processor 104 is configured to generate, for at least a segment of plurality of segments, a label 128 representing at least a signal feature 132. For the purposes of this disclosure, “labeling” is a process of identifying raw data and adding one or more labels to provide a context for one or more following steps. For the purposes of this disclosure, a “label” is an indication describing one or more characteristics of a subject matter as well as how the subject matter is categorized into one or more categories with respect to a population or sub-population containing the subject. As nonlimiting examples, subject matter described herein may include one or more signal features 132 of cardiac signal 116. In one or more embodiments, label 128 may include a binary diagnostic label, e.g., “yes” vs. “no” or “positive” vs. “negative”. In one or more embodiments, label 128 may be further specified, such as “highly likely”, “highly unlikely”, “abnormally high”, or “abnormally low”. In one or more embodiments, label 128 may be associated with a percentile ranking, e.g., “top 10% of the population”. In one or more embodiments, label 128 may be applied with respect to at least a specific cohort upon application of one or more inclusion/exclusion criteria, such as “top 25% of the female population”. In some cases, generating label 128 may include analyzing the statistical distribution of signal features 132 across a collection of cardiac signals 116, as described below.

With continued reference to FIG. 1, in one or more embodiments, a collection of cardiac signals 116 with one or more similar signal features 132 may be combined into a cohort, wherein one or more statistical parameters within the cohort may be combined and tallied to form a statistical model. For the purposes of this disclosure, a “statistical parameter” is a characteristic or metric that describes how one data element or group of data elements compares to another data element or group of data elements. In some cases, a match between a first set of statistical parameters associated with a first patient and a second set of statistical parameters associated with a second patient may be determined as a function of one or more pre-determined criteria selected by one or more medical professionals. As a nonlimiting example, first set of statistical parameters and second set of statistical parameters may be considered a match when the two sets of statistical parameters are within one standard deviation from each other. As a nonlimiting example, matching first set of statistical parameters with second set of statistical parameters may involve a fuzzy set comparison, as described below.

With continued reference to FIG. 1, statistical model may be described by one or more numerical indicators such as without limitation an average or mean, a median, a standard deviation, a variance, a range, or the like. In one or more embodiments, statistical model may be updated when its associated cohort or cohorts are filtered into one or more sub-cohorts as a function of one or more newly applied inclusion/exclusion criteria. As a nonlimiting example, one or more statistical parameters associated with signal features 132 may be compared to and/or located within statistical model to help a medical professional decide whether one or more signal features 132 should be labeled as abnormal. For the purposes of this disclosure, an “abnormal” signal feature 132 is a feature possessed by or associated with a minority of population or collection of cardiac signals 116 and/or described by a numerical value that is different from a statistical average of the population collection of cardiac signals 116, according to one or more cutoffs and/or pre-determined criteria. As a nonlimiting example, an abnormal signal feature 132 may be specified as a signal feature 132 possessed by or associated with less than 50% of the population and/or described by a numerical value that is at least two standard deviations away from statistical average.

With continued reference to FIG. 1, for the purposes of this disclosure, a “signal feature” is a feature pertaining to the intensity, duration, and shape of a signal. As nonlimiting examples, signal feature 132 may include one or more peaks, troughs, rises, decays, plateaus, 1^st/2^ndderivative features, among others. As another nonlimiting example, signal feature 132 may include one or more features such as multiplicity, frequency, amplitude, wavelength, asymmetry, area under the curve, among others.

With continued reference to FIG. 1, in one or more embodiments, one or more machine learning models 136 may be used to perform certain function or functions of apparatus 100, such as generating one or more labels 128, annotations, and/or corrections, as described in detail below. Processor 104 may use a machine learning module to implement one or more algorithms as described herein or generate one or more machine learning models, such as labeling or correction machine learning model, as described below. However, machine learning module is exemplary and may not be necessary to generate one or more machine learning models and perform any machine learning described herein. In one or more embodiments, one or more machine learning models may be generated using training data. Training data may include inputs and corresponding predetermined outputs so that machine learning model may use correlations between the provided exemplary inputs and outputs to develop an algorithm and/or relationship that then allows the machine learning model to determine its own outputs for inputs. Training data may contain correlations that a machine learning process may use to model relationships between two or more categories of data elements. Exemplary inputs and outputs may be retrieved from a database, data repository 112, or a data store of similar nature, selected from one or more electronic health records (EHRs), or be provided by a user. In one or more embodiments, machine learning module may obtain training data by querying a communicatively connected database that includes past inputs and outputs. Training data may include inputs from various types of databases, resources, and/or user inputs and outputs correlated to each of those inputs, so that machine learning model may determine an output. Correlations may indicate causative and/or predictive links between data, which may be modeled as relationships, such as mathematical relationships, by machine learning models, as described in further detail below. In one or more embodiments, training data may be formatted and/or organized by categories of data elements by, for example, associating data elements with one or more descriptors corresponding to categories of data elements. As a nonlimiting example, training data may include data entered in standardized forms by persons or processes, such that entry of a given data element in a given field in a form may be mapped to one or more descriptors of categories. Elements in training data may be linked to descriptors of categories by tags, tokens, or other data elements. In one or more embodiments, training data may include previous outputs such that one or more machine learning models may iteratively produce outputs.

With continued reference to FIG. 1, in one or more embodiments, generating label 128 may involve implementing a labeling machine learning model 136. Specifically, generating label 128 may include receiving a plurality of training data 140 including a plurality of exemplary cardiac signals as inputs correlated with a plurality of exemplary labels as outputs, training labeling machine learning model 136 as a function of the plurality of training data 140, and generating the label 128 using the labeling machine learning model 136. Implementation of labeling machine learning model 136 may be consistent with any type of machine learning model or algorithm described in this disclosure. In one or more embodiments, training data 140 May include data specifically synthesized for training purposes using one or more generative models. As a nonlimiting example, training data 140 may be generated or synthesized using deidentified patient data from EHRs. Deidentified patient data may be generated, as a nonlimiting example, using a generative machine learning model trained and configured to obfuscate data containing sensitive information, such as names, age, contact information, or the like, while preserving its utility for training purposes. Such deidentification procedure may be used to comply with privacy regulations and ethical standards. As another nonlimiting example, training data 140 may be extracted from medical literature. In one or more embodiments, one or more historic sessions may be incorporated into training data 140 upon validation. In one or more embodiments, training data 140 may be retrieved from one or more databases, EHRs, and/or other repositories of similar nature, or be supplied as one or more user inputs. In one or more embodiments, at least a portion of training data 140 may be added, deleted, replaced, or otherwise updated as a function of one or more inputs from one or more users. In one or more embodiments, labeling machine learning model 136 may include a classifier, as described in detail below in this disclosure. Details pertaining to labeling machine learning model 136 may be consistent with any detail disclosed in U.S. Pat. App. Ser. No. 63/614,864 (attorney docket number 1518-093USP1), filed on Dec. 26, 2023, entitled “METHOD AND SYSTEM FOR LABELING OF INTRACARDIAC SIGNALS”, the entirety of which is incorporated herein by reference.

With continued reference to FIG. 1, in one or more embodiments, apparatus 100 may include a display device 144 communicatively connected to processor 104. For the purposes of this disclosure, a “display device” is a device configured to show visual information. In some cases, display device 144 may include a liquid crystal display (LCD), a cathode ray tube (CRT), a plasma display, a light emitting diode (LED) display, and any combinations thereof. Display device 144 may include, but is not limited to, a smartphone, tablet, laptop, monitor, tablet, and the like. Display device 144 may include a separate device that includes a transparent screen configured to display computer-generated images and/or information. In one or more embodiments, display device 144 may be configured to visually present data through a user interface 148 or a graphical user interface (GUI) to at least a user, wherein the user may interact with the data through the user interface or GUI, as described below. In one or more embodiments, a user may view GUI through display device 144. In one or more embodiments, display device 144 may be located on remote device, as described below. Additional details will be provided below in this disclosure through nonlimiting examples.

With continued reference to FIG. 1, in some cases, display device 144 may include a remote device. For the purposes of this disclosure, a “remote device” is a computer device separate and distinct from apparatus 100. For example, and without limitation, remote device may include a smartphone, a tablet, a laptop, a desktop computer, or the like. In one or more embodiments, remote device may be communicatively connected to apparatus 100 such as, for example, through network communication, through Bluetooth communication, and/or the like. In one or more embodiments, processor 104 may receive one or more inputs from a user and/or initiate one or more of subsequent steps through remote device. In one or more embodiments, one or more inputs from one or more users may be submitted through a user interface 148, such as a GUI, displayed through remote device, as described below.

With continued reference to FIG. 1, in one or more embodiments, apparatus 100 includes a user interface 148, as described above. For the purposes of this disclosure, a “user interface” is a means by which a user and a computer system interact using input devices, software, and/or the like. User interface 148 may include a graphical user interface (GUI), command line interface (CLI), menu-driven user interface, touch user interface, voice user interface (VUI), form-based user interface, any combination thereof, or the like. In one or more embodiments, a user may interact with user interface 148 using computing device distinct from and communicatively connected to processor 104, such as a smartphone, tablet, or the like operated by the user. User interface 148 may include one or more graphical locator and/or cursor facilities allowing user to interact with graphical models and/or combinations thereof, for instance using a touchscreen, touchpad, mouse, keyboard, and/or other manual data entry device. For the purposes of this disclosure, a “graphical user interface (GUI)” is a type of user interface that allows end users to interact with electronic devices through visual representations. In one or more embodiments, GUI may include icons, menus, other visual indicators or representations (graphics), audio indicators such as primary notation, display information, and related user controls. Menu may contain a list of choices and may allow users to select one from them. A menu bar may be displayed horizontally across the screen as a pull-down menu. Menu may include a context menu that appears only when user performs a specific action. Files, programs, web pages, and the like may be represented using a small picture within GUI. In one or more embodiments, GUI may include a graphical visualization of a user profile and/or the like. In one or more embodiments, processor 104 may be configured to modify and/or update GUI as a function of at least an input or the like by populating a user interface data structure and visually presenting data through modification of the GUI.

With continued reference to FIG. 1, in one or more embodiments, GUI may contain one or more interactive elements. For the purposes of this disclosure, an “interactive element” is an element within GUI that allows for communication with processor 104 by one or more users. For example, and without limitation, interactive elements may include a plurality of tabs wherein selection of a particular tab, such as for example, by using a fingertip, may indicate to a system to perform a particular function and display the result through GUI. In one or more embodiments, interactive element may include tabs within GUI, wherein the selection of a particular tab may result in a particular function. In one or more embodiments, interactive elements may include words, phrases, illustrations, and the like to indicate a particular process that one or more users would like system to perform. A person of ordinary skill in the art, upon reviewing the entirety of this disclosure, will be aware of various ways in which user interfaces 148, GUIs, and/or elements thereof may be implemented and/or used as described in this disclosure.

With continued reference to FIG. 1, in one or more embodiments, display device 144 and/or remote device may be configured to display at least an event handler graphic corresponding to at least an event handler. For the purposes of this disclosure, an “event handler graphic” is a graphical element with which user interacts using display device 144 and/or remote device to enter data. In some cases, a user may submit one or more inputs by interacting with event handler graphic, as described below. Event handler graphic may include, without limitation, a button, a link, a checkbox, a text entry box and/or window, a drop-down list, a slider, or any other event handler graphic deemed suitable by a person of ordinary skill in the art upon reviewing the entirety of this disclosure. For the purposes of this disclosure, an “event handler” is a module, data structure, function, and/or routine that performs an action on display device 144 and/or remote device in response to one or more user inputs. For instance, and without limitation, event handler may record data corresponding to user selections of previously populated fields such as drop-down lists and/or text auto-complete and/or default entries, data corresponding to user selections of checkboxes, radio buttons, or the like, potentially along with automatically entered data triggered by such selections, user entry of textual data using a keyboard, touchscreen, speech-to-text program, or the like. Event handler may generate prompts for further information, may compare data to validation rules such as requirements that the data in question be entered within certain numerical ranges, and/or may modify data and/or generate warnings to user in response to such requirements. Event handler may convert data into expected and/or desired formats, for instance such as date formats, currency entry formats, name formats, or the like. Event handler may transmit data from a remote device to computing device.

With continued reference to FIG. 1, in one or more embodiments, event handler may include a cross-session state variable. For the purposes of this disclosure, a “cross-session state variable” is a variable recording data entered on remote device during a previous session. Such data may include, for instance, previously entered text, previous selections of one or more elements as described above, or the like. For instance, cross-session state variable data may represent a search that user entered in a past session. Cross-session state variable may be saved using any suitable combination of client-side data storage on remote device and server-side data storage on computing device; for instance, data may be saved wholly or in part as a “cookie” which may include data or an identification of remote device to prompt provision of cross-session state variable by the computing device, which may store the data on the computing device. Alternatively, or additionally, computing device may use login credentials, device identifier, and/or device fingerprint data to retrieve cross-session state variable, which the computing device may transmit to remote device. Cross-session state variable may include at least a prior session datum. A prior session datum may include any element of data that may be stored in cross-session state variable. Event handler graphic may be further configured to display at least a prior session datum, for instance and without limitation, by auto-populating user query data from previous sessions.

With continued reference to FIG. 1, in one or more embodiments, processor 104 and/or computing device may configure display device 144 and/or remote device to generate a graphical view. For the purposes of this disclosure, a “graphical view” is a data structure that results in display of one or more graphical elements on a screen. Graphical view may include at least a display element. For the purposes of this disclosure, a “display element” is an image that a program and/or data structure cause to be displayed. Display elements may include, without limitation, windows, pop-up boxes, web browser pages, display layers, and/or any other display element deemed relevant by a person of ordinary skill in the art upon reviewing the entirety of this disclosure. Graphical view may include at least a selectable event graphic corresponding to one or more selectable event handlers. For the purposes of this disclosure, a “selectable event graphic” is a graphical element that, upon selection, will trigger an action to be performed. Selection may be performed using a cursor or other locator as manipulated using a locator device such as a mouse, touchscreen, track pad, joystick, or the like. As a nonlimiting example, a selectable event graphic may include a redirection link, defined as a hyperlink, button, image, portion of an image, and/or other graphic containing or referring to a uniform resource locator (URL) and/or other resource locator to another graphical view including without limitation buttons, and/or to a process that performs navigation to such URL and/or other resource locator upon selection of selectable event graphic. Redirection may be performed using any event handler, including without limitation event handlers detecting the click of a mouse or other locator, access of redirection link using a touchscreen, the selection of any key, mouseover events, or the like.

With continued reference to FIG. 1, in one or more embodiments, generating label 128 may include displaying at least a cardiac signal 116 with a first visual indicator 152, displaying at least a labeled segment in at least a second visual indicator 156, wherein the at least a second visual indicator 156 is different from the first visual indicator 152. Accordingly, processor 104 may be configured to overlay at least a labeled segment within at least a cardiac signal 116. For the purposes of this disclosure, a “visual indicator” is a symbol that helps a user visually isolate one or more visual components from a plurality of visual components. In some cases, visual indicators may be implemented via means such as highlighting, dimming, blinking, shading, and/or the like. In some cases, visual indicators may be color-coded. As a nonlimiting example, first visual indicator 152 may include a first color, and second visual indicator 156 may include a second color that is different from the first color.

With continued reference to FIG. 1, processor 104 is configured to generate at least an automated annotation 160 as a function of label 128. For the purposes of this disclosure, an “automated annotation” is an annotation created by a computing system without human intervention. For the purposes of this disclosure, an “annotation” is a note pertaining to a specific label 128 that further describes the meaning and/or implications of the label 128. Nonlimiting examples of annotation may include textual notes, symbolic markings based on one or more index tables, graphical markings based on certain codes or protocols, or the like. In some cases, automated annotation 160 may be generated using an annotation machine learning model 136, consistent with details described above. Specifically, generating automated annotation 160 may include receiving a plurality of training data 140 comprising a plurality of exemplary cardiac signals as inputs correlated with a plurality of exemplary annotations as outputs, training automation machine learning model 136 as a function of the plurality of training data 140, and generating the automated annotation 160 using the annotation machine learning model 136. Implementation of annotation machine learning model 136 may be consistent with any type of machine learning model described in this disclosure without limitation. In one or more embodiments, training data 140 may include data specifically synthesized for training purposes using one or more generative models. As a nonlimiting example, training data 140 may be generated or synthesized using deidentified patient data from EHRs. Deidentified patient data may be generated, as a nonlimiting example, using a generative machine learning model trained and configured to obfuscate data containing sensitive information, such as names, age, contact information, or the like, while preserving its utility for training purposes. Such deidentification procedure may be used to comply with privacy regulations and ethical standards. As another nonlimiting example, training data 140 may be extracted from medical literature. In one or more embodiments, one or more historic queries may be incorporated into training data 140 upon validation. In one or more embodiments, training data 140 may be retrieved from one or more databases, EHRs, and/or other repositories of similar nature, or be supplied as one or more user inputs. In one or more embodiments, at least a portion of training data 140 may be added, deleted, replaced, or otherwise updated as a function of one or more inputs from one or more users. In some cases, automated annotation 160 may be generated as a function of one or more system parameters of apparatus 100 that define one or more thresholds of annotation; accordingly, automated annotation 160 may be configured to be either more comprehensive or more concise by adjusting such thresholds. In some cases, a first portion of cardiac signal 116 may be annotated with one or more automated annotations 160, whereas a second portion of the cardiac signal may be annotation-free.

With continued reference to FIG. 1, processor 104 is further configured to generate at least a correction 164 upon detecting an absence of annotations. For the purposes of this disclosure, a “correction” is a procedure used by a computing device to remove one or more errors in a data set. In one or more embodiments, generating correction 164 may involve using a correction module 168, such as a correction machine learning model 136. Specifically, generating correction 164 may include receiving a plurality of training data 140 comprising a plurality of exemplary cardiac signals as inputs correlated with a plurality of exemplary corrections as outputs, training correction machine learning model 136 as a function of the plurality of training data 140, and generating the correction 164 using the correction machine learning model 136. Implementation of correction machine learning model 136 may be consistent with any type of machine learning model described in this disclosure without limitation. In one or more embodiments, training data 140 may include data specifically synthesized for training purposes using one or more generative models. As a nonlimiting example, training data 140 may be generated or synthesized using deidentified patient data from EHRs. Deidentified patient data may be generated, as a nonlimiting example, using a generative machine learning model trained and configured to obfuscate data containing sensitive information, such as names, age, contact information, or the like, while preserving its utility for training purposes. Such deidentification procedure may be used to comply with privacy regulations and ethical standards. As another nonlimiting example, training data 140 may be extracted from medical literature. In one or more embodiments, one or more historic queries may be incorporated into training data 140 upon validation. In one or more embodiments, training data 140 may be retrieved from one or more databases, EHRs, and/or other repositories of similar nature, or be supplied as one or more user inputs. In one or more embodiments, at least a portion of training data 140 may be added, deleted, replaced, or otherwise updated as a function of one or more inputs from one or more users. Nonlimiting examples of correction 164 may include removal of one or more signal artifacts, noises, jittering, skewed baselines, among others. In some cases, generating correction 164 may include processing at least a portion of cardiac signal 116 using a filter, as described below.

With continued reference to FIG. 1, correction 164 may include automatically processing cardiac signal 116. For instance, apparatus 100 may analyze, modify, and/or synthesize a signal representative of cardiac signal 116 in order to improve the cardiac signal 116, for instance by improving transmission, storage efficiency, or signal-to-noise ratio. Exemplary methods of signal processing may include analog, continuous time, discrete, digital, nonlinear, and statistical. Analog signal processing may be performed on non-digitized or analog signals. Exemplary analog processes may include passive filters, active filters, additive mixers, integrators, delay lines, compandors, multipliers, voltage-controlled filters, voltage-controlled oscillators, and phase-locked loops. Continuous-time signal processing may be used, in some cases, to process signals which vary continuously within a domain, for instance time. Exemplary non-limiting continuous time processes may include time domain processing, frequency domain processing (Fourier transform), and complex frequency domain processing. Discrete time signal processing may be used when a signal is sampled non-continuously or at discrete time intervals (i.e., quantized in time). Analog discrete-time signal processing may process a signal using the following exemplary circuits sample and hold circuits, analog time-division multiplexers, analog delay lines and analog feedback shift registers. Digital signal processing may be used to process digitized discrete-time sampled signals. Commonly, digital signal processing may be performed by a computing device or other specialized digital circuits, such as without limitation an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a specialized digital signal processor (DSP). Digital signal processing may be used to perform any combination of typical arithmetical operations, including fixed-point and floating-point, real-valued and complex-valued, multiplication and addition. Digital signal processing may additionally operate circular buffers and lookup tables. Further nonlimiting examples of algorithms that may be performed according to digital signal processing techniques include fast Fourier transform (FFT), finite impulse response (FIR) filter, infinite impulse response (IIR) filter, and adaptive filters such as the Wiener and Kalman filters. Statistical signal processing may be used to process a signal as a random function (i.e., a stochastic process), utilizing statistical properties. For instance, in some embodiments, a signal may be modeled with a probability distribution indicating noise, which then may be used to reduce noise in a processed signal.

With continued reference to FIG. 1, processor 104 is configured to receive, using user interface 148, at least an input 172 from a user, consistent with details described above in this disclosure. In one or more embodiments, user interface 148 may include at least an annotation window. For the purposes of this disclosure, an “annotation window” is a portion of user interface 148 within which annotation may be performed. Additional details will be described below in this disclosure. Accordingly, processor 104 is configured to create at least a user annotation 176 within at least a cardiac signal 116 using at least an input 172. For the purposes of this disclosure, a “user annotation” is an annotation performed manually by a user in order to capture one or more aspects of cardiac signal 116 that automated annotation 160 is not able to address or correct one or more errors in automated annotation 160. In some cases, creating at least a user annotation 176 may include validating at least an automated annotation 160, and generating, for each incorrect automatic annotation 160 identified based on the validation, the at least a user annotation 176. In some cases, certain signal features 132 of cardiac signal 116 may be omitted by automated annotation 160 due to its limitations but deemed important or relevant by a medical professional; in such cases, user annotation 176 may be added to these features. In some cases, certain signal features 132 of cardiac signal 116 may be marked by an incorrect automated annotation 160, which may be either altered or removed by user annotation 176. In some cases, user annotation 176 may include at least a prediction regarding a future trajectory of cardiac signal 116, which may not be readily captured by automated annotation 160. In some cases, creating at least a user annotation 176 may include modifying at least a cardiac signal 116. Nonlimiting examples of such modification may include a manual correction of baseline, a manual removal of artifacts, among others. In some cases, creating at least a user annotation 176 may include modifying label 128. In some cases, creating at least a user annotation 176 may include creating at least an annotation segment within at least an annotation window. For the purposes of this disclosure, an “annotation segment” is a portion of annotation window that include at least a user annotation 176. As a nonlimiting example, annotation segment may include a temporal span that ranges from tens of milliseconds to tens of seconds. In some cases, first visual indicator 152, second visual indicator 156, and third visual indicator 180 may be color coded. In some cases, creating at least an annotation segment may include displaying the at least an annotation segment in at least a third visual indicator 180, wherein the at least a third visual indicator 180 is different from first visual indicator 152 and at least a second visual indicator 156. As a nonlimiting example, first visual indicator 152 may include a first color, second visual indicator 156 may include a second color that is different from the first color, and third visual indicator 180 may include a third color that is different from both the first color and the second color. Accordingly, processor 104 may be configured to overlay at least an annotation segment within at least a cardiac signal 116.

With continued reference to FIG. 1, in one or more embodiments, processor 104 may be further configured to adjust a length of at least an annotation window as a function of input 172. As a nonlimiting example, processor may be configured to switch from a first annotation window to a second annotation window, either upon a completion of user annotation 176 in the first annotation window or upon a quest of user. As another nonlimiting example, annotation window may be toggled between a 50-millisecond temporal span and a 100-millisecond temporal span.

With continued reference to FIG. 1, processor 104 is configured to update at least a cardiac signal 116 and annotation machine learning model 136 as a function of at least a correction 164 and at least a user annotation 176. In one or more embodiments, updating at least a cardiac signal 116 may include replacing one or more portions of the cardiac signal 116 as a function of correction 164. In one or more embodiments, updating cardiac signal 116 may include incorporating one or more user annotations 176 within the cardiac signal 116. In one or more embodiments, updating annotation machine learning model 136 may include adjusting one or more parameters within the annotation machine learning model 136 to achieve a higher accuracy of annotation. As a nonlimiting example, updating annotation machine learning model 136 may include adding, deleting, and/or replacing one or more portions of training data 140, such as incorporating an active session into data repository 112, upon proper validation, to be used as part of the training data 140. In one or more embodiments, updating at least a cardiac signal 116 and annotation machine learning model 136 may include transmitting the updated at least a cardiac signal 116 and annotation machine learning model 136 to data repository 112 for storage and/or maintenance. Similarly, in some cases, processor 104 may be further configured to update labeling/correction machine learning model 136. Further, updating annotation machine learning model 136, labeling machine learning model 136, and/or correction machine learning model may include validating its performance from a domain point of view.

With continued reference to FIG. 1, processor 104 is further configured to display, using user interface 148, updated at least a cardiac signal 116 to user. In some cases, updated cardiac signal may include at least a label 128, at least an automated annotation 160, and/or at least a user annotation 176, consistent with details described above. In some cases, when cardiac signal 116 includes time series data 124, displaying at least a cardiac signal 116 may include displaying at least a time series segment of plurality of time series segments, consistent with details described above. In some cases, user interface 148 may include one or more interactive elements that allow a user to toggle between a first times series segment and a second times series segment. As a nonlimiting example, such function may be implemented in user interface 148 using a “forward” or “backward” tab. In some cases, displaying at least a cardiac signal 116 may include displaying at least a modified cardiac signal 116, consistent with details described above. In some cases, a modified cardiac signal 116 may be superimposed with its corresponding original cardiac signal 116 to show a user what modifications have been made.

With continued reference to FIG. 1, it should be noted that apparatus 100 and methods described herein are not limited to medical or cardiac applications only. For example, and without limitation, annotation capabilities disclosed herein may be effectively adapted for use within other organs, such as brains, where there is a similar need to label/annotate data such as electroencephalograms. A person of ordinary skill in the art, upon reviewing the entirety of this disclosure, will recognize one or more embodiments described herein (although principally focused on the heart) and their underlaying principles may be readily transferrable to a broader spectrum of medical imaging and intervention applications as well as nonmedical signal processing applications that are not currently disclosed.

With continued reference to FIG. 1, in one or more embodiments, processor 104 may use one or more parameters from metadata associated to cardiac signal 116 in order to perform one or more of its functions such as generation of labels 128 and automated annotation 160, among others. Accordingly, processor 104 may use optical character recognition (OCR) to read digital files and extract information therein. In one or more embodiments, OCR may include automatic conversion of images (e.g., typed, handwritten, or printed text) into machine-encoded text. In one or more embodiments, recognition of at least a keyword from an image component may include one or more processes, including without limitation OCR, optical word recognition, intelligent character recognition, intelligent word recognition, and the like. In one or more embodiments, OCR may recognize written text one glyph or character at a time, for example, for languages that use a space as a word divider. In one or more embodiments, intelligent character recognition (ICR) may recognize written text one glyph or character at a time, for instance by employing machine learning processes. In one or more embodiments, intelligent word recognition (IWR) may recognize written text, one word at a time, for instance by employing machine learning processes.

With continued reference to FIG. 1, in one or more embodiments, OCR may employ preprocessing of image components. Preprocessing process may include without limitation de-skew, de-speckle, binarization, line removal, layout analysis or “zoning”, line and word detection, script recognition, character isolation or “segmentation”, and normalization. In one or more embodiments, a de-skew process may include applying a transform (e.g., homography or affine transform) to an image component to align text. In one or more embodiments, a de-speckle process may include removing positive and negative spots and/or smoothing edges. In one or more embodiments, a binarization process may include converting an image from color or greyscale to black-and-white (i.e., a binary image). Binarization may be performed as a simple way of separating text (or any other desired image component) from the background of image component. In one or more embodiments, binarization may be required for example if an employed OCR algorithm only works on binary images. In one or more embodiments, line removal process may include removal of non-glyph or non-character imagery (e.g., boxes and lines). In one or more embodiments, a layout analysis or “zoning” process may identify columns, paragraphs, captions, and the like as distinct blocks. In one or more embodiments, a line and word detection process may establish a baseline for word and character shapes and separate words, if necessary. In one or more embodiments, a script recognition process may, for example in multilingual documents, identify a script, allowing an appropriate OCR algorithm to be selected. In one or more embodiments, a character isolation or “segmentation” process may separate signal characters, for example, character-based OCR algorithms. In one or more embodiments, a normalization process may normalize the aspect ratio and/or scale of image component.

With continued reference to FIG. 1, in one or more embodiments, an OCR process may include an OCR algorithm. Exemplary OCR algorithms include matrix-matching processes and/or feature extraction processes. Matrix matching may involve comparing an image to a stored glyph on a pixel-by-pixel basis. In one or more embodiments, matrix matching may also be known as “pattern matching”, “pattern recognition”, and/or “image correlation”. Matrix matching may rely on an input glyph being correctly isolated from the rest of image component. Matrix matching may also rely on a stored glyph being in a similar font and at the same scale as input glyph.

With continued reference to FIG. 1, in one or more embodiments, an OCR process may include a feature extraction process. In one or more embodiments, feature extraction may decompose a glyph into features. Exemplary nonlimiting features may include corners, edges, lines, closed loops, line direction, line intersections, and the like. In one or more embodiments, feature extraction may reduce the dimensionality of representation and may make the recognition process computationally more efficient. In one or more embodiments, extracted features can be compared with an abstract vector-like representation of a character, which might be reduced to one or more glyph prototypes. General techniques of feature detection in computer vision are applicable to this type of OCR. In one or more embodiments, machine learning process like nearest neighbor classifiers (e.g., k-nearest neighbors algorithm) can be used to compare image features with stored glyph features and choose a nearest match. OCR may employ any machine learning process described in this disclosure. Exemplary nonlimiting OCR software includes Cuneiform and Tesseract. Cuneiform is a multi-language, open-source OCR system originally developed by Cognitive Technologies of Moscow, Russia. Tesseract is a free OCR software originally developed by Hewlett-Packard of Palo Alto, California, United States.

With continued reference to FIG. 1, in one or more embodiments, OCR may employ a two-pass approach to character recognition. Second pass may include adaptive recognition and use letter shapes recognized with high confidence on a first pass to better recognize remaining letters on a second pass. In one or more embodiments, two-pass approach may be advantageous for unusual fonts or low-quality image components where visual verbal content may be distorted. Another exemplary OCR software tool includes OCRopus. The development of OCRopus is led by the German Research Center for Artificial Intelligence in Kaiserslautern, Germany. In one or more embodiments, OCR software may employ neural networks, for example, deep neural networks, as described in this disclosure below.

With continued reference to FIG. 1, in one or more embodiments, OCR may include post-processing. For example, OCR accuracy can be increased, in some cases, if output is constrained by a lexicon. A lexicon may include a list or set of words that are allowed to occur in a document. In one or more embodiments, a lexicon may include, for instance, all the words in the English language, or a more technical lexicon for a specific field. In some cases, an output stream may be a plain text stream or file of characters. In one or more embodiments, an OCR may preserve an original layout of visual verbal content. In one or more embodiments, near-neighbor analysis can make use of co-occurrence frequencies to correct errors by noting that certain words are often seen together. For example, “Washington, D.C.” is generally far more common in English than “Washington DOC”. In one or more embodiments, an OCR process may make use of a priori knowledge of grammar for a language being recognized. For example, OCR process may apply grammatical rules to help determine if a word is likely to be a verb or a noun. Distance conceptualization may be employed for recognition and classification. For example, a Levenshtein distance algorithm may be used in OCR post-processing to further optimize results. A person of ordinary skill in the art will recognize how to apply the aforementioned technologies to extract information from a digital file upon reviewing the entirety of this disclosure.

With continued reference to FIG. 1, in one or more embodiments, a computer vision module configured to perform one or more computer vision tasks such as, without limitation, object recognition, feature detection, edge/corner detection thresholding, or machine learning process may be used to recognize specific features or attributes. For the purposes of this disclosure, a “computer vision module” is a computational component designed to perform one or more computer vision, image processing, and/or modeling tasks. In one or more embodiments, computer vision module may receive one or more digital files containing metadata from data repository 112 and generate one or more labels 128 as a function of the metadata. In one or more embodiments, to generate label 128, computer vision module may be configured to compare one or more signal features 132 against the statistical data of the one or more signal features 132 and attach one or more labels 128 as a function of the comparison, as described below.

With continued reference to FIG. 1, in one or more embodiments, computer vision module may include an image processing module, wherein images may be pre-processed using the image processing module. For the purposes of this disclosure, an “image processing module” is a component designed to process digital images such as images described herein. For example, and without limitation, image processing module may be configured to compile a plurality of images of a multi-layer scan to create an integrated image. In one or more embodiments, image processing module may include a plurality of software algorithms that can analyze, manipulate, or otherwise enhance an image, such as, without limitation, a plurality of image processing techniques as described below. In one or more embodiments, computer vision module may also include hardware components such as, without limitation, one or more graphics processing units (GPUs) that can accelerate the processing of a large number of images. In one or more embodiments, computer vision module may be implemented with one or more image processing libraries such as, without limitation, OpenCV, PIL/Pillow, ImageMagick, and the like. In a nonlimiting example, in order to generate one or more labels and/or recognize one or more reference attributes, one or more image processing tasks, such as noise reduction, contrast enhancement, intensity normalization, image segmentation, and/or the like, may be performed by computer vision module on a plurality of images to isolate certain features or components from the rest. In one or more embodiments, one or more machine learning models may be used to perform segmentations, for example, and without limitation, a U-net (i.e., a convolution neural network containing a contracting path as an encoder and an expansive path as a decoder, wherein the encoder and the decoder forms a U-shaped structure). A person of ordinary skill in the art, upon reviewing the entirety of this disclosure, will be aware of various image processing, computer vision, and modeling tasks that may be performed by processor 104.

With continued reference to FIG. 1, in one or more embodiments, one or more functions of apparatus 100 may involve a use of image classifiers to classify images within any data described in this disclosure. For the purposes of this disclosure, an “image classifier” is a machine learning model that sort inputs of image information into categories or bins of data, outputting the categories or bins of data and/or labels associated therewith. Image classifier may include a mathematical model, a neural net, or a program generated by a machine learning algorithm known as a “classification algorithm”, as described in further detail below. Image classifier may be configured to output at least a datum that labels or otherwise identifies a set of images that are clustered together, found to be close under a distance metric as described below, or the like. Computing device and/or another device may generate image classifier using a classification algorithm. For the purposes of this disclosure, a classification algorithm is a process whereby computing device derives a classifier from training data. Classification may be performed using, without limitation, linear classifiers such as without limitation logistic regression and/or naive Bayes classifiers, nearest neighbor classifiers such as k-nearest neighbors classifiers, support vector machines, least squares support vector machines, Fisher's linear discriminant, quadratic classifiers, decision trees, boosted trees, random forest classifiers, learning vector quantization, and/or neural network-based classifiers. In one or more embodiments, processor 104 may use image classifier to identify a key image in any data described in this disclosure. For the purposes of this disclosure, a “key image” is an element of visual data used to identify and/or match elements to each other. In one or more embodiments, key image may include part of a medical image such as an ECG, an IEGM, or the like, with features that unambiguously identify the type of the medical image. Image classifier may be trained with binarized visual data that have already been classified to determine key images in any other data described in this disclosure. For the purposes of this disclosure, “binarized visual data” are visual data that are described in a binary format. For example, binarized visual data of a photo may comprise ones and zeroes, wherein the specific sequence of ones and zeros may be used to represent the photo. Binarized visual data may be used for image recognition wherein a specific sequence of ones and zeroes may indicate a product present in the image. An image classifier may be consistent with any classifier as discussed herein. An image classifier may receive input data (e.g., cardiac signal 116) described in this disclosure and output a key image with the data. In one or more embodiments, image classifier may be used to compare visual data in one data set, such as cardiac signal 116, with visual data in another data set, such as one or more exemplary cardiac signals within data repository 112, as described below.

With continued reference to FIG. 1, processor 104 may be configured to perform feature extraction on one or more images, as described below. For the purposes of this disclosure, “feature extraction” is a process of transforming an initial data set into informative measures and values. For example, feature extraction may include a process of determining one or more geometric features of an anatomic structure. In one or more embodiments, feature extraction may be used to determine one or more spatial relationships within a drawing that may be used to uniquely identify one or more features. In one or more embodiments, processor 104 may be configured to extract one or more regions of interest, wherein the regions of interest may be used to extract one or more features using one or more feature extraction techniques.

With continued reference to FIG. 1, processor 104 may be configured to perform one or more of its functions, such as extraction of signal features 132, as described below, using a feature learning algorithm. For the purposes of this disclosure, a “feature learning algorithm” is a machine learning algorithm that identifies associations between elements of data in a data set where particular outputs and/or inputs are not specified. Data set may include without limitation a training data set. For instance, and without limitation, a feature learning algorithm may detect co-occurrences of elements of data, as defined above, with each other. Computing device may perform feature learning algorithm by dividing elements or sets of data into various sub-combinations of such data to create new elements of data and evaluate which elements of data tend to co-occur with which other elements. In one or more embodiments, feature learning algorithm may perform clustering of data.

With continued reference to FIG. 1, feature learning and/or clustering algorithm may be implemented, as a nonlimiting example, using a k-means clustering algorithm. For the purposes of this disclosure, a “k-means clustering algorithm” is a type of cluster analysis that partitions n observations or unclassified cluster data entries into k clusters in which each observation or unclassified cluster data entry belongs to the cluster with the nearest mean. For the purposes of this disclosure, “cluster analysis” is a process that includes grouping a set of observations or data entries in way that observations or data entries in the same group or cluster are more similar to each other than to those in other groups or clusters. Cluster analysis may be performed by various cluster models that include connectivity models such as hierarchical clustering, centroid models such as k-means, distribution models such as multivariate normal distribution, density models such as density-based spatial clustering of applications with nose (DBSCAN) and ordering points to identify the clustering structure (OPTICS), subspace models such as biclustering, group models, graph-based models such as a clique, signed graph models, neural models, and the like. Cluster analysis may include hard clustering, whereby each observation or unclassified cluster data entry belongs to a cluster or not. Cluster analysis may include soft clustering or fuzzy clustering, whereby each observation or unclassified cluster data entry belongs to each cluster to a certain degree such as for example a likelihood of belonging to a cluster; for instance, and without limitation, a fuzzy clustering algorithm may be used to identify clustering of elements of a first type or category with elements of a second type or category, and vice versa, as described below. Cluster analysis may include strict partitioning clustering, whereby each observation or unclassified cluster data entry belongs to exactly one cluster. Cluster analysis may include strict partitioning clustering with outliers, whereby observations or unclassified cluster data entries may belong to no cluster and may be considered outliers. Cluster analysis may include overlapping clustering whereby observations or unclassified cluster data entries may belong to more than one cluster. Cluster analysis may include hierarchical clustering, whereby observations or unclassified cluster data entries that belong to a child cluster also belong to a parent cluster.

With continued reference to FIG. 1, computing device may generate a k-means clustering algorithm by receiving unclassified data and outputting a definite number of classified data entry clusters, wherein the data entry clusters each contain cluster data entries. K-means algorithm may select a specific number of groups or clusters to output, identified by a variable “k”. Generating k-means clustering algorithm includes assigning inputs containing unclassified data to a “k-group” or “k-cluster” based on feature similarity. Centroids of k-groups or k-clusters may be utilized to generate classified data entry cluster. K-means clustering algorithm may select and/or be provided “k” variable by calculating k-means clustering algorithm for a range of k values and comparing results. K-means clustering algorithm may compare results across different values of k as the mean distance between cluster data entries and cluster centroid. K-means clustering algorithm may calculate mean distance to a centroid as a function of k value, and the location of where the rate of decrease starts to sharply shift, which may be utilized to select a k value. Centroids of k-groups or k-cluster include a collection of feature values which are utilized to classify data entry clusters containing cluster data entries. K-means clustering algorithm may act to identify clusters of closely related data, which may be provided with user cohort labels; this may, for instance, generate an initial set of user cohort labels from an initial set of data, and may also, upon subsequent iterations, identify new clusters to be provided new labels, to which additional data may be classified, or to which previously used data may be reclassified.

With continued reference to FIG. 1, generating a k-means clustering algorithm may include generating initial estimates for k centroids which may be randomly generated or randomly selected from unclassified data input. K centroids may be utilized to define one or more clusters. K-means clustering algorithm may assign unclassified data to one or more k-centroids based on the squared Euclidean distance by first performing a data assigned step of unclassified data. K-means clustering algorithm may assign unclassified data to its nearest centroid based on the collection of centroids ci of centroids in set C. Unclassified data may be assigned to a cluster based on argminc_i∈Cdist(ci, x)², where argmin includes argument of the minimum, ci includes a collection of centroids in a set C, and dist includes standard Euclidean distance. K-means clustering module may then recompute centroids by taking a mean of all cluster data entries assigned to a centroid's cluster. This may be calculated based on ci=1/|Si|Σxi∈Si^xi. K-means clustering algorithm may continue to repeat these calculations until a stopping criterion has been satisfied such as when cluster data entries do not change clusters, the sum of the distances have been minimized, and/or some maximum number of iterations has been reached.

With continued reference to FIG. 1, k-means clustering algorithm may be configured to calculate a degree of similarity index value. For the purposes of this disclosure, a “degree of similarity index value” is a distance measured between each data entry cluster generated by k-means clustering algorithm and a selected element. Degree of similarity index value may indicate how close a particular combination of elements is to being classified by k-means algorithm to a particular cluster. K-means clustering algorithm may evaluate the distances of the combination of elements to the k-number of clusters output by k-means clustering algorithm. Short distances between an element of data and a cluster may indicate a higher degree of similarity between the element of data and a particular cluster. Longer distances between an element and a cluster may indicate a lower degree of similarity between the element to be compared and/or clustered and a particular cluster.

With continued reference to FIG. 1, k-means clustering algorithm selects a classified data entry cluster as a function of the degree of similarity index value. In one or more embodiments, k-means clustering algorithm may select a classified data entry cluster with the smallest degree of similarity index value indicating a high degree of similarity between an element and the data entry cluster. Alternatively or additionally, k-means clustering algorithm may select a plurality of clusters having low degree of similarity index values to elements to be compared and/or clustered thereto, indicative of greater degrees of similarity. Degree of similarity index values may be compared to a threshold number indicating a minimal degree of relatedness suitable for inclusion of a set of element data in a cluster, where degree of similarity indices a-n falling under the threshold number may be included as indicative of high degrees of relatedness. The above-described illustration of feature learning using k-means clustering is included for illustrative purposes only and should not be construed as limiting potential implementation of feature learning algorithms; a person of ordinary skills in the art, upon reviewing the entirety of this disclosure, will be aware of various additional or alternative feature learning approaches, such as particle swarm optimization (PSO) and generative adversarial network (GAN) that may be used consistently with this disclosure.

With continued reference to FIG. 1, in one or more embodiments, processor 104 may use an image recognition algorithm to determine patterns within an image. In one or more embodiments, image recognition algorithm may include an edge-detection algorithm, which may detect one or more shapes defined by edges. For the purposes of this disclosure, an “edge detection algorithm” is or includes a mathematical method that identifies points in a digital image at which the image brightness changes sharply and/or has discontinuities. In one or more embodiments, such points may be organized into straight and/or curved line segments, which may be referred to as “edges”. Edge detection may be performed using any suitable edge detection algorithm, including without limitation Canny edge detection, Sobel operator edge detection, Prewitt operator edge detection, Laplacian operator edge detection, and/or differential edge detection. Edge detection may include phase congruency-based edge detection, which finds all locations of an image where all sinusoids in the frequency domain, for instance when generated using a Fourier decomposition, may have matching phases which may indicate a location of an edge.

Referring now to FIG. 2, an exemplary embodiment 200 of ECG signal is illustrated. ECG may include a plurality of features such as P-wave, Q-wave, R-wave, S-wave, QRS complex, and T wave, as well as a plurality of parameters such a PR interval 204, QT interval 208, ST interval 212, TP interval 216, RR interval 220, and the like. P-wave may reflect atrial depolarization (activation). For the purposes of this disclosure, a “PR interval” is the distance between the onset of P-wave to the onset of QRS complex. PR interval 204 may be assessed to determine whether impulse conduction from the atria to the ventricles is normal. PR interval 204 may be measured in seconds. For the purposes of this disclosure, a “QT interval” is a reflection of the total duration of ventricular depolarization and repolarization and is measured from the onset of QRS complex to the end of T-wave. The QT duration may be inversely related to heart rate; i.e., QT interval 208 may increase at slower heart rates and decrease at higher heart rates. Therefore, to determine whether QT interval 208 is within normal limits, it may be necessary to adjust for the heart rate. A heart rate-adjusted QT interval 208 is referred to as a corrected QT interval 208 (QTc interval). A long QTc interval may indicate an increased risk of ventricular arrhythmias. The QTc interval may be in the range of 0.36 to 0.44 seconds. For the purposes of this disclosure, an “RR interval” is the time between two consecutive R waves. For the purposes of this disclosure, a “QRS complex” is a representation of the depolarization (activation) of ventricles depicted between Q-, R- and S-waves, although it may not always display all three waves. Since the electrical vector generated by the left ventricle is usually many times larger than the vector generated by the right ventricle, QRS complex is a reflection of left ventricular depolarization.

With continued reference to FIG. 2, for the purposes of this disclosure, an “ST interval” is the segment of ECG that starts at the end of QRS complex and extends to the beginning of T wave; it represents the early part of ventricular repolarization. ST segment may be relatively isoelectric, meaning it is at the baseline, with minimal elevation or depression. The normal duration of ST interval 212 is usually around 0.12 seconds. For the purposes of this disclosure, a “TP interval” is the segment of ECG that extends from the end of T wave to the beginning of the next P wave; it represents the time when the ventricles are fully repolarized and are in a resting state. The duration of TP interval 216 may vary but is typically short, as it may represent the brief pause between cardiac cycles. Significant deviations may be associated with certain conditions affecting repolarization. For the purposes of this disclosure, an “RR interval” is the time between two consecutive R waves of ECG; it may represent the duration of one cardiac cycle, encompassing both atrial and ventricular depolarization and repolarization. RR interval 220 may be measured in seconds and can be used to calculate heart rate (beats per minute) using

$heart rate = \frac{6 0}{RR Interval}$

(in seconds). The intervals described above may be used to determine a ventricular rate, i.e., the number of ventricular contractions (heartbeats) that occur in one minute, which may be closely related to RR interval 220 of ECG, as the RR interval 220 represents the time between two consecutive ventricular contractions.

Referring now to FIG. 3, an exemplary embodiment of a machine learning module 300 that may perform one or more machine learning processes as described above is illustrated. Machine learning module may perform determinations, classification, and/or analysis steps, methods, processes, or the like as described in this disclosure using machine learning processes. For the purposes of this disclosure, a “machine learning process” is an automated process that uses training data 304 to generate an algorithm instantiated in hardware or software logic, data structures, and/or functions that will be performed by a computing device/module to produce outputs 308 given data provided as inputs 312. This is in contrast to a non-machine learning software program where the commands to be executed are pre-determined by user and written in a programming language.

With continued reference to FIG. 3, “training data”, for the purposes of this disclosure, are data containing correlations that a machine learning process uses to model relationships between two or more categories of data elements. For instance, and without limitation, training data 304 may include a plurality of data entries, also known as “training examples”, each entry representing a set of data elements that were recorded, received, and/or generated together. Data elements may be correlated by shared existence in a given data entry, by proximity in a given data entry, or the like. Multiple data entries in training data 304 may evince one or more trends in correlations between categories of data elements; for instance, and without limitation, a higher value of a first data element belonging to a first category of data element may tend to correlate to a higher value of a second data element belonging to a second category of data element, indicating a possible proportional or other mathematical relationship linking values belonging to the two categories. Multiple categories of data elements may be related in training data 304 according to various correlations; correlations may indicate causative and/or predictive links between categories of data elements, which may be modeled as relationships such as mathematical relationships by machine learning processes as described in further detail below. Training data 304 may be formatted and/or organized by categories of data elements, for instance by associating data elements with one or more descriptors corresponding to categories of data elements. As a nonlimiting example, training data 304 may include data entered in standardized forms by persons or processes, such that entry of a given data element within a given field in a given form may be mapped to one or more descriptors of categories. Elements in training data 304 may be linked to descriptors of categories by tags, tokens, or other data elements. For instance, and without limitation, training data 304 may be provided in fixed-length formats, formats linking positions of data to categories such as comma-separated value (CSV) formats and/or self-describing formats such as extensible markup language (XML), JavaScript Object Notation (JSON), or the like, enabling processes or devices to detect categories of data.

With continued reference to FIG. 3, alternatively or additionally, training data 304 may include one or more elements that are uncategorized; that is, training data 304 may not be formatted or contain descriptors for some elements of data. Machine learning algorithms and/or other processes may sort training data 304 according to one or more categorizations using, for instance, natural language processing algorithms, tokenization, detection of correlated values in raw data, and the like; categories may be generated using correlation and/or other processing algorithms. As a nonlimiting example, in a corpus of text, phrases making up a number “n” of compound words, such as nouns modified by other nouns, may be identified according to a statistically significant prevalence of n-grams containing such words in a particular order; such an n-gram may be categorized as an element of language such as a “word” to be tracked similarly to single words, generating a new category as a result of statistical analysis. Similarly, in a data entry including some textual data, a person's name may be identified by reference to a list, dictionary, or other compendium of terms, permitting ad-hoc categorization by machine learning algorithms, and/or automated association of data in the data entry with descriptors or into a given format. The ability to categorize data entries automatedly may enable the same training data 304 to be made applicable for two or more distinct machine learning algorithms as described in further detail below. Training data 304 used by machine learning module 300 may correlate any input data as described in this disclosure to any output data as described in this disclosure. As a nonlimiting illustrative example, inputs may include plurality of images containing biomedical data 112, whereas outputs may include plurality of biomedical features 124.

With continued reference to FIG. 3, training data 304 may be filtered, sorted, and/or selected using one or more supervised and/or unsupervised machine learning processes and/or models as described in further detail below; such processes and/or models may include without limitation a training data classifier 316. For the purposes of this disclosure, a “classifier” is a machine learning model that sorts inputs into categories or bins of data, outputting the categories or bins of data and/or labels associated therewith. Machine learning model may include without limitation a data structure representing and/or using a mathematical model, neural net, or a program generated by a machine learning algorithm, known as a “classification algorithm”. A classifier may be configured to output at least a datum that labels or otherwise identifies a set of data that are clustered together, found to be close under a distance metric as described below, or the like. A distance metric may include any norm, such as, without limitation, a Pythagorean norm. Machine learning module 300 may generate a classifier using a classification algorithm. For the purposes of this disclosure, a “classification algorithm” is a process wherein a computing device and/or any module and/or component operating therein derives a classifier from training data 304. Classification may be performed using, without limitation, linear classifiers such as without limitation logistic regression and/or naive Bayes classifiers, nearest neighbor classifiers such as k-nearest neighbors classifiers, support vector machines, least squares support vector machines, Fisher's linear discriminant, quadratic classifiers, decision trees, boosted trees, random forest classifiers, learning vector quantization, and/or neural network-based classifiers. In one or more embodiments, training data classifier 316 may classify elements of training data to a plurality of cohorts as a function of certain anatomic and/or demographic traits.

With continued reference to FIG. 3, machine learning module 300 may be configured to generate a classifier using a naive Bayes classification algorithm. Naive Bayes classification algorithm generates classifiers by assigning class labels to problem instances, represented as vectors of element values. Class labels are drawn from a finite set. Naive Bayes classification algorithm may include generating a family of algorithms that assume that the value of a particular element is independent of the value of any other element, given a class variable. Naive Bayes classification algorithm may be based on Bayes Theorem expressed as P(A/B)=P(B/A)×P(A)÷P(B), where P(A/B) is the probability of hypothesis A given data B, also known as posterior probability; P(B/A) is the probability of data B given that the hypothesis A was true; P(A) is the probability of hypothesis A being true regardless of data, also known as prior probability of A; and P(B) is the probability of the data regardless of the hypothesis. A naive Bayes algorithm may be generated by first transforming training data into a frequency table. Machine learning module 300 may then calculate a likelihood table by calculating probabilities of different data entries and classification labels. Machine learning module 300 may utilize a naive Bayes equation to calculate a posterior probability for each class. A class containing the highest posterior probability is the outcome of prediction. Naive Bayes classification algorithm may include a gaussian model that follows a normal distribution. Naive Bayes classification algorithm may include a multinomial model that is used for discrete counts. Naive Bayes classification algorithm may include a Bernoulli model that may be utilized when vectors are binary.

With continued reference to FIG. 3, machine learning module 300 may be configured to generate a classifier using a k-nearest neighbors (KNN) algorithm. For the purposes of this disclosure, a “k-nearest neighbors algorithm” is or at least includes a classification method that utilizes feature similarity to analyze how closely out-of-sample features resemble training data 304 and to classify input data to one or more clusters and/or categories of features as represented in training data 304. This may be performed by representing both training data 304 and input data in vector forms and using one or more measures of vector similarity to identify classifications within training data 304 and determine a classification of input data. K-nearest neighbors algorithm may include specifying a k-value, or a number directing the classifier to select the k most similar entries of training data 304 to a given sample, determining the most common classifier of the entries in the database, and classifying the known sample; this may be performed recursively and/or iteratively to generate a classifier that may be used to classify input data as further samples. For instance, an initial set of samples may be performed to cover an initial heuristic and/or “first guess” at an output and/or relationship, which may be seeded, without limitation, using expert input received according to any process as described herein. As a nonlimiting example, an initial heuristic may include a ranking of associations between inputs 312 and elements of training data 304. Heuristic may include selecting some number of highest-ranking associations and/or training data elements.

With continued reference to FIG. 3, generating k-nearest neighbors algorithm may generate a first vector output containing a data entry cluster, generating a second vector output containing input data, and calculate the distance between the first vector output and the second vector output using any suitable norm such as cosine similarity, Euclidean distance measurement, or the like. Each vector output may be represented, without limitation, as an n-tuple of values, where n is at least 2. Each value of n-tuple of values may represent a measurement or other quantitative value associated with a given category of data or attribute, examples of which are provided in further detail below. A vector may be represented, without limitation, in n-dimensional space using an axis per category of value represented in n-tuple of values, such that a vector has a geometric direction characterizing the relative quantities of attributes in the n-tuple as compared to each other. Two vectors may be considered equivalent when their directions and/or relative quantities of values are the same; thus, as a nonlimiting example, a vector represented as [5, 10, 15] may be treated as equivalent, for the purposes of this disclosure, as a vector represented as [1, 2, 3]. Vectors may be more similar where their directions are more similar, and more different where their directions are more divergent. However, vector similarity may alternatively or additionally be determined using averages of similarities between like attributes, or any other measure of similarity suitable for any n-tuple of values, or aggregation of numerical similarity measures for the purposes of loss functions as described in further detail below. Any vectors as described herein may be scaled, such that each vector represents each attribute along an equivalent scale of values. Each vector may be “normalized”, or divided by a “length” attribute, such as a length attribute l as derived using a Pythagorean norm: l=√{square root over (Σ_i=0ⁿα_i²)}, where at is attribute number of vector i. Scaling and/or normalization may function to make vector comparison independent of absolute quantities of attributes, while preserving any dependency on similarity of attributes. This may, for instance, be advantageous where cases represented in training data 304 are represented by different quantities of samples, which may result in proportionally equivalent vectors with divergent values.

With continued reference to FIG. 3, training examples for use as training data may be selected from a population of potential examples according to cohorts relevant to an analytical problem to be solved, a classification task, or the like. Alternatively or additionally, training data 304 may be selected to span a set of likely circumstances or inputs for a machine learning model and/or process to encounter when deployed. For instance, and without limitation, for each category of input data to a machine learning model and/or process that may exist in a range of values in a population of phenomena such as images, user data, process data, physical data, or the like, a computing device, processor 104, and/or machine learning module 300 may select training examples representing each possible value on such a range and/or a representative sample of values on such a range. Selection of a representative sample may include selection of training examples in proportions matching a statistically determined and/or predicted distribution of such values according to relative frequency, such that, for instance, values encountered more frequently in a population of data so analyzed are represented by more training examples than values that are encountered less frequently. Alternatively or additionally, a set of training examples may be compared to a collection of representative values in a database and/or presented to user, so that a process can detect, automatically or via user input, one or more values that are not included in the set of training examples. Computing device, processor 104, and/or machine learning module 300 may automatically generate a missing training example. This may be done by receiving and/or retrieving a missing input and/or output value and correlating the missing input and/or output value with a corresponding output and/or input value collocated in a data record with the retrieved value, provided by user, another device, or the like.

With continued reference to FIG. 3, computing device, processor 104, and/or machine learning module 300 may be configured to preprocess training data 304. For the purposes of this disclosure, “preprocessing” training data is a process that transforms training data from a raw form to a format that can be used for training a machine learning model. Preprocessing may include sanitizing, feature selection, feature scaling, data augmentation and the like.

With continued reference to FIG. 3, computing device, processor 104, and/or machine learning module 300 may be configured to sanitize training data. For the purposes of this disclosure, “sanitizing” training data is a process whereby training examples that interfere with convergence of a machine learning model and/or process are removed to yield a useful result. For instance, and without limitation, a training example may include an input and/or output value that is an outlier from typically encountered values, such that a machine learning algorithm using the training example will be skewed to an unlikely range of input 312 and/or output 308; a value that is more than a threshold number of standard deviations away from an average, mean, or expected value, for instance, may be eliminated. Alternatively or additionally, one or more training examples may be identified as having poor-quality data, where “poor-quality” means having a signal-to-noise ratio below a threshold value. In one or more embodiments, sanitizing training data may include steps such as removing duplicative or otherwise redundant data, interpolating missing data, correcting data errors, standardizing data, identifying outliers, and/or the like. In one or more embodiments, sanitizing training data may include algorithms that identify duplicate entries or spell-check algorithms.

With continued reference to FIG. 3, in one or more embodiments, images used to train an image classifier or other machine learning model and/or process that takes images as inputs 312 or generates images as outputs 308 may be rejected if image quality is below a threshold value. For instance, and without limitation, computing device, processor 104, and/or machine learning module 300 may perform blur detection. Elimination of one or more blurs may be performed, as a nonlimiting example, by taking Fourier transform or a Fast Fourier Transform (FFT) of image and analyzing a distribution of low and high frequencies in the resulting frequency-domain depiction of the image. Numbers of high-frequency values below a threshold level may indicate blurriness. As a further nonlimiting example, detection of blurriness may be performed by convolving an image, a channel of an image, or the like with a Laplacian kernel; this may generate a numerical score reflecting a number of rapid changes in intensity shown in the image, such that a high score indicates clarity and a low score indicates blurriness. Blurriness detection may be performed using a gradient-based operator, which measures operators based on the gradient or first derivative of image, based on the hypothesis that rapid changes indicate sharp edges in the image, and thus are indicative of a lower degree of blurriness. Blur detection may be performed using a wavelet-based operator, which uses coefficients of a discrete wavelet transform to describe the frequency and spatial content of images. Blur detection may be performed using statistics-based operators that take advantage of several image statistics as texture descriptors in order to compute a focus level. Blur detection may be performed by using discrete cosine transform (DCT) coefficients in order to compute a focus level of an image from its frequency content.

With continued reference to FIG. 3, computing device, processor 104, and/or machine learning module 300 may be configured to precondition one or more training examples. For instance, and without limitation, where a machine learning model and/or process has one or more inputs 312 and/or outputs 308 requiring, transmitting, or receiving a certain number of bits, samples, or other units of data, one or more elements of training examples to be used as or compared to inputs 312 and/or outputs 308 may be modified to have such a number of units of data. In one or more embodiments, computing device, processor 104, and/or machine learning module 300 may convert a smaller number of units, such as in a low pixel count image, into a desired number of units by upsampling and interpolating. As a nonlimiting example, a low pixel count image may have 100 pixels, whereas a desired number of pixels may be 128. Processor 104 may interpolate the low pixel count image to convert 100 pixels into 128 pixels. It should also be noted that one of ordinary skill in the art, upon reading the entirety of this disclosure, would recognize the various methods to interpolate a smaller number of data units such as samples, pixels, bits, or the like to a desired number of such units. In one or more embodiments, a set of interpolation rules may be trained by sets of highly detailed inputs 312 and/or outputs 308 and corresponding inputs 312 and/or outputs 308 downsampled to smaller numbers of units, and a neural network or another machine learning model that is trained to predict interpolated pixel values using the training data 304. As a nonlimiting example, a sample input 312 and/or output 308, such as a sample picture, with sample-expanded data units (e.g., pixels added between the original pixels) may be input to a neural network or machine learning model and output a pseudo replica sample picture with dummy values assigned to pixels between the original pixels based on a set of interpolation rules. As a nonlimiting example, in the context of an image classifier, a machine learning model may have a set of interpolation rules trained by sets of highly detailed images and images that have been downsampled to smaller numbers of pixels, and a neural network or other machine learning model that is trained using those examples to predict interpolated pixel values in a facial picture context. As a result, an input with sample-expanded data units (the ones added between the original data units, with dummy values) may be run through a trained neural network and/or model, which may fill in values to replace the dummy values. Alternatively or additionally, computing device, processor 104, and/or machine learning module 300 may utilize sample expander methods, a low-pass filter, or both. For the purposes of this disclosure, a “low-pass filter” is a filter that passes signals with a frequency lower than a selected cutoff frequency and attenuates signals with frequencies higher than the cutoff frequency. The exact frequency response of the filter depends on the filter design. Computing device, processor 104, and/or machine learning module 300 may use averaging, such as luma or chroma averaging in images, to fill in data units in between original data units.

With continued reference to FIG. 3, in one or more embodiments, computing device, processor 104, and/or machine learning module 300 may downsample elements of a training example to a desired lower number of data elements. As a nonlimiting example, a high pixel count image may contain 256 pixels, however a desired number of pixels may be 128. Processor 104 may downsample the high pixel count image to convert 256 pixels into 128 pixels. In one or more embodiments, processor 104 may be configured to perform downsampling on data. Downsampling, also known as decimation, may include removing every N^thentry in a sequence of samples, all but every N^thentry, or the like, which is a process known as “compression” and may be performed, for instance by an N-sample compressor implemented using hardware or software. Anti-aliasing and/or anti-imaging filters, and/or low-pass filters, may be used to eliminate side effects of compression.

With continued reference to FIG. 3, feature selection may include narrowing and/or filtering training data 304 to exclude features and/or elements, or training data including such elements that are not relevant to a purpose for which a trained machine learning model and/or algorithm is being trained, and/or collection of features, elements, or training data including such elements based on relevance to or utility for an intended task or purpose for which a machine learning model and/or algorithm is being trained. Feature selection may be implemented, without limitation, using any process described in this disclosure, including without limitation using training data classifiers, exclusion of outliers, or the like.

With continued reference to FIG. 3, feature scaling may include, without limitation, normalization of data entries, which may be accomplished by dividing numerical fields by norms thereof, for instance as performed for vector normalization. Feature scaling may include absolute maximum scaling, wherein each quantitative datum is divided by the maximum absolute value of all quantitative data of a set or subset of quantitative data. Feature scaling may include min-max scaling, wherein a difference between each value, X, and a minimum value, X_min, in a set or subset of values is divided by a range of values, X_max−X_min, in the set or subset:

$X_{n e w} = \frac{X - X_{\min}}{X_{\max} - X_{\min}} .$

Feature scaling may include mean normalization, wherein a difference between each value, X, and a mean value of a set and/or subset of values, X_mean, is divided by a range of values, X_max−X_min, in the set or subset:

$X_{n e w} = \frac{X - X_{m e a n}}{X_{\max} - X_{\min}} .$

Feature scaling may include standardization, wherein a difference between X and X_meanis divided by a standard deviation, σ, of a set or subset of values:

$X_{n e w} = \frac{X - X_{m e a n}}{σ} .$

Feature scaling may be performed using a median value of a set or subset, X_median, and/or interquartile range (IQR), which represents the difference between the 25^thpercentile value and the 50^thpercentile value (or closest values thereto by a rounding protocol), such as:

$X_{n e w} = \frac{X - X_{m e d i a n}}{σ} .$

A Person of ordinary skill in the art, upon reviewing the entirety of this disclosure, will be aware of various alternative or additional approaches that may be used for feature scaling.

With continued reference to FIG. 3, computing device, processor 104, and/or machine learning module 300 may be configured to perform one or more processes of data augmentation. For the purposes of this disclosure, “data augmentation” is a process that adds data to a training data 304 using elements and/or entries already in the dataset. Data augmentation may be accomplished, without limitation, using interpolation, generation of modified copies of existing entries and/or examples, and/or one or more generative artificial intelligence (AI) processes, for instance using deep neural networks and/or generative adversarial networks. Generative processes may be referred to alternatively in this context as “data synthesis” and as creating “synthetic data”. Augmentation may include performing one or more transformations on data, such as geometric, color space, affine, brightness, cropping, and/or contrast transformations of images.

With continued reference to FIG. 3, machine learning module 300 may be configured to perform a lazy learning process and/or protocol 320. For the purposes of this disclosure, a “lazy learning” process and/or protocol is a process whereby machine learning is conducted upon receipt of input 312 to be converted to output 308 by combining the input 312 and training data 304 to derive the algorithm to be used to produce the output 308 on demand. A lazy learning process may alternatively be referred to as a “lazy loading” or “call-when-needed” process and/or protocol. For instance, an initial set of simulations may be performed to cover an initial heuristic and/or “first guess” at an output 308 and/or relationship. As a nonlimiting example, an initial heuristic may include a ranking of associations between inputs 312 and elements of training data 304. Heuristic may include selecting some number of highest-ranking associations and/or training data 304 elements. Lazy learning may implement any suitable lazy learning algorithm, including without limitation a k-nearest neighbors algorithm, a lazy naive Bayes algorithm, or the like. A person of ordinary skill in the art, upon reviewing the entirety of this disclosure, will be aware of various lazy learning algorithms that may be applied to generate outputs as described in this disclosure, including without limitation lazy learning applications of machine learning algorithms as described in further detail below.

With continued reference to FIG. 3, alternatively or additionally, machine learning processes as described in this disclosure may be used to generate machine learning models 324. A “machine learning model”, for the purposes of this disclosure, is a data structure representing and/or instantiating a mathematical and/or algorithmic representation of a relationship between inputs 312 and outputs 308, generated using any machine learning process including without limitation any process described above, and stored in memory. An input 312 is submitted to a machine learning model 324 once created, which generates an output 308 based on the relationship that was derived. For instance, and without limitation, a linear regression model, generated using a linear regression algorithm, may compute a linear combination of input data using coefficients derived during machine learning processes to calculate an output datum. As a further nonlimiting example, a machine learning model 324 may be generated by creating an artificial neural network, such as a convolutional neural network comprising an input layer of nodes, one or more intermediate layers, and an output layer of nodes. Connections between nodes may be created by “training” the network, in which elements from a training data 304 are applied to the input nodes, and a suitable training algorithm (such as Levenberg-Marquardt, conjugate gradient, simulated annealing, or other algorithms) is then used to adjust the connections and weights between nodes in adjacent layers of the neural network to produce the desired values at the output nodes. This process is sometimes referred to as deep learning, as described in detail below.

With continued reference to FIG. 3, machine learning module 300 may perform at least a supervised machine learning process 328. For the purposes of this disclosure, a “supervised” machine learning process is a process with algorithms that receive training data 304 relating one or more inputs 312 to one or more outputs 308, and seek to generate one or more data structures representing and/or instantiating one or more mathematical relations relating input 312 to output 308, where each of the one or more mathematical relations is optimal according to some criterion specified to the algorithm using some scoring function. For instance, a supervised learning algorithm may include inputs 312 described above as inputs, and outputs 308 described above as outputs, and a scoring function representing a desired form of relationship to be detected between inputs 312 and outputs 308. Scoring function may, for instance, seek to maximize the probability that a given input 312 and/or combination thereof is associated with a given output 308 to minimize the probability that a given input 312 is not associated with a given output 308. Scoring function may be expressed as a risk function representing an “expected loss” of an algorithm relating inputs 312 to outputs 308, where loss is computed as an error function representing a degree to which a prediction generated by the relation is incorrect when compared to a given input-output pair provided in training data 304. Supervised machine learning processes may include classification algorithms as defined above. A person of ordinary skill in the art, upon reviewing the entirety of this disclosure, will be aware of various possible variations of at least a supervised machine learning process 328 that may be used to determine a relation between inputs and outputs.

With continued reference to FIG. 3, training a supervised machine learning process may include, without limitation, iteratively updating coefficients, biases, and weights based on an error function, expected loss, and/or risk function. For instance, an output 308 generated by a supervised machine learning model 328 using an input example in a training example may be compared to an output example from the training example; an error function may be generated based on the comparison, which may include any error function suitable for use with any machine learning algorithm described in this disclosure, including a square of a difference between one or more sets of compared values or the like. Such an error function may be used in turn to update one or more weights, biases, coefficients, or other parameters of a machine learning model through any suitable process including without limitation gradient descent processes, least-squares processes, and/or other processes described in this disclosure. This may be done iteratively and/or recursively to gradually tune such weights, biases, coefficients, or other parameters. Updates may be performed in neural networks using one or more back-propagation algorithms. Iterative and/or recursive updates to weights, biases, coefficients, or other parameters as described above may be performed until currently available training data 304 are exhausted and/or until a convergence test is passed. For the purposes of this disclosure, a “convergence test” is a test for a condition selected to indicate that a model and/or weights, biases, coefficients, or other parameters thereof has reached a degree of accuracy. A convergence test may, for instance, compare a difference between two or more successive errors or error function values, where differences below a threshold amount may be taken to indicate convergence. Alternatively or additionally, one or more errors and/or error function values evaluated in training iterations may be compared to a threshold.

With continued reference to FIG. 3, a computing device, processor 104, and/or machine learning module 300 may be configured to perform method, method step, sequence of method steps, and/or algorithm described in reference to this figure, in any order and with any degree of repetition. For instance, computing device, processor 104, and/or machine learning module 300 may be configured to perform a single step, sequence, and/or algorithm repeatedly until a desired or commanded outcome is achieved; repetition of a step or a sequence of steps may be performed iteratively and/or recursively using outputs 308 of previous repetitions as inputs 312 to subsequent repetitions, aggregating inputs 312 and/or outputs 308 of repetitions to produce an aggregate result, reduction or decrement of one or more variables such as global variables, and/or division of a larger processing task into a set of iteratively addressed smaller processing tasks. A computing device, processor 104, apparatus 100, or machine learning module 300 may perform any step, sequence of steps, or algorithm in parallel, such as simultaneously and/or substantially simultaneously performing a step two or more times using two or more parallel threads, processor cores, or the like; division of tasks between parallel threads and/or processes may be performed according to any protocol suitable for division of tasks between iterations. A person of ordinary skill in the art, upon reviewing the entirety of this disclosure, will be aware of various ways in which steps, sequences of steps, processing tasks, and/or data may be subdivided, shared, or otherwise dealt with using iteration, recursion, and/or parallel processing.

With continued reference to FIG. 3, machine learning process may include at least an unsupervised machine learning process 332. For the purposes of this disclosure, an unsupervised machine learning process is a process that derives inferences in datasets without regard to labels. As a result, an unsupervised machine learning process 332 may be free to discover any structure, relationship, and/or correlation provided in the data. Unsupervised processes 332 may not require a response variable, may be used to find interesting patterns and/or inferences between variables, to determine a degree of correlation between two or more variables, or the like.

With continued reference to FIG. 3, machine learning module 300 may be designed and configured to create machine learning model 324 using techniques for development of linear regression models. Linear regression models may include ordinary least squares regression, which aims to minimize the square of the difference between predicted outcomes and actual outcomes according to an appropriate norm for measuring such a difference (e.g. a vector-space distance norm); coefficients of the resulting linear equation may be modified to improve minimization. Linear regression models may include ridge regression methods, where the function to be minimized includes the least-squares function plus term multiplying the square of each coefficient by a scalar amount to penalize large coefficients. Linear regression models may include least absolute shrinkage and selection operator (LASSO) models, in which ridge regression is combined with multiplying the least-squares term by a factor of 1 divided by double the number of samples. Linear regression models may include a multi-task lasso model wherein the norm applied in the least-squares term of the lasso model is the Frobenius norm amounting to the square root of the sum of squares of all terms. Linear regression models may include an clastic net model, a multi-task elastic net model, a least angle regression model, a LARS lasso model, an orthogonal matching pursuit model, a Bayesian regression model, a logistic regression model, a stochastic gradient descent model, a perceptron model, a passive aggressive algorithm, a robustness regression model, a Huber regression model, or any other suitable model that may occur to a person of ordinary skill in the art upon reviewing the entirety of this disclosure. Linear regression models may be generalized in an embodiment to polynomial regression models, whereby a polynomial equation (e.g. a quadratic, cubic or higher-order equation) providing a best predicted output/actual output fit is sought. Similar methods to those described above may be applied to minimize error functions, as will be apparent to a person of ordinary skill in the art upon reviewing the entirety of this disclosure.

With continued reference to FIG. 3, machine learning algorithms may include, without limitation, linear discriminant analysis. Machine learning algorithm may include quadratic discriminant analysis. Machine learning algorithms may include kernel ridge regression. Machine learning algorithms may include support vector machines, including without limitation support vector classification-based regression processes. Machine learning algorithms may include stochastic gradient descent algorithms, including classification and regression algorithms based on stochastic gradient descent. Machine learning algorithms may include nearest neighbors algorithms. Machine learning algorithms may include various forms of latent space regularization such as variational regularization. Machine learning algorithms may include Gaussian processes such as Gaussian Process Regression. Machine learning algorithms may include cross-decomposition algorithms, including partial least squares and/or canonical correlation analysis. Machine learning algorithms may include naive Bayes methods. Machine learning algorithms may include algorithms based on decision trees, such as decision tree classification or regression algorithms. Machine learning algorithms may include ensemble methods such as bagging meta-nstimator, forest of randomized trees, AdaBoost, gradient tree boosting, and/or voting classifier methods. Machine learning algorithms may include neural net algorithms, including convolutional neural net processes.

With continued reference to FIG. 3, a machine learning model and/or process may be deployed or instantiated by incorporation into a program, apparatus, system, and/or module. For instance, and without limitation, a machine learning model, neural network, and/or some or all parameters thereof may be stored and/or deployed in any memory or circuitry. Parameters such as coefficients, weights, and/or biases may be stored as circuit-based constants, such as arrays of wires and/or binary inputs and/or outputs set at logic “1” and “0” voltage levels in a logic circuit, to represent a number according to any suitable encoding system including twos complement or the like, or may be stored in any volatile and/or non-volatile memory. Similarly, mathematical operations and input 312 and/or output 308 of data to or from models, neural network layers, or the like may be instantiated in hardware circuitry and/or in the form of instructions in firmware, machine-code such as binary operation code instructions, assembly language, or any higher-order programming language. Any technology for hardware and/or software instantiation of memory, instructions, data structures, and/or algorithms may be used to instantiate a machine learning process and/or model, including without limitation any combination of production and/or configuration of non-reconfigurable hardware elements, circuits, and/or modules such as without limitation application-specific integrated circuits (ASICs), production and/or configuration of reconfigurable hardware elements, circuits, and/or modules such as without limitation field programmable gate arrays (FPGAs), production and/or configuration of non-reconfigurable and/or non-rewritable memory elements, circuits, and/or modules such as without limitation non-rewritable read-only memory (ROM), other memory technology described in this disclosure, and/or production and/or configuration of any computing device and/or component thereof as described in this disclosure. Such deployed and/or instantiated machine learning model and/or algorithm may receive inputs 312 from any other process, module, and/or component described in this disclosure, and produce outputs 308 to any other process, module, and/or component described in this disclosure.

With continued reference to FIG. 3, any process of training, retraining, deployment, and/or instantiation of any machine learning model and/or algorithm may be performed and/or repeated after an initial deployment and/or instantiation to correct, refine, and/or improve the machine learning model and/or algorithm. Such retraining, deployment, and/or instantiation may be performed as a periodic or regular process, such as retraining, deployment, and/or instantiation at regular elapsed time periods, after some measure of volume such as a number of bytes or other measures of data processed, a number of uses or performances of processes described in this disclosure, or the like, and/or according to a software, firmware, or other update schedule. Alternatively or additionally, retraining, deployment, and/or instantiation may be event-based, and may be triggered, without limitation, by user inputs indicating sub-optimal or otherwise problematic performance and/or by automated field testing and/or auditing processes, which may compare outputs 308 of machine learning models and/or algorithms, and/or errors and/or error functions thereof, to any thresholds, convergence tests, or the like, and/or may compare outputs 308 of processes described herein to similar thresholds, convergence tests or the like. Event-based retraining, deployment, and/or instantiation may alternatively or additionally be triggered by receipt and/or generation of one or more new training examples; a number of new training examples may be compared to a preconfigured threshold, where exceeding the preconfigured threshold may trigger retraining, deployment, and/or instantiation.

With continued reference to FIG. 3, retraining and/or additional training may be performed using any process for training described above, using any currently or previously deployed version of a machine learning model and/or algorithm as a starting point. Training data for retraining may be collected, preconditioned, sorted, classified, sanitized, or otherwise processed according to any process described in this disclosure. Training data 304 may include, without limitation, training examples including inputs 312 and correlated outputs 308 used, received, and/or generated from any version of any system, module, machine learning model or algorithm, apparatus, and/or method described in this disclosure. Such examples may be modified and/or labeled according to user feedback or other processes to indicate desired results, and/or may have actual or measured results from a process being modeled and/or predicted by system, module, machine learning model or algorithm, apparatus, and/or method as “desired” results to be compared to outputs 308 for training processes as described above. Redeployment may be performed using any reconfiguring and/or rewriting of reconfigurable and/or rewritable circuit and/or memory elements; alternatively, redeployment may be performed by production of new hardware and/or software components, circuits, instructions, or the like, which may be added to and/or may replace existing hardware and/or software components, circuits, instructions, or the like.

With continued reference to FIG. 3, one or more processes or algorithms described above may be performed by at least a dedicated hardware unit 336. For the purposes of this disclosure, a “dedicated hardware unit” is a hardware component, circuit, or the like, aside from a principal control circuit and/or processor 104 performing method steps as described in this disclosure, that is specifically designated or selected to perform one or more specific tasks and/or processes described in reference to this figure. Such specific tasks and/or processes may include without limitation preprocessing and/or sanitization of training data and/or training a machine learning algorithm and/or model. Dedicated hardware unit 336 may include, without limitation, a hardware unit that can perform iterative or massed calculations, such as matrix-based calculations to update or tune parameters, weights, coefficients, and/or biases of machine learning models and/or neural networks, efficiently using pipelining, parallel processing, or the like; such a hardware unit may be optimized for such processes by, for instance, including dedicated circuitry for matrix and/or signal processing operations that includes, e.g., multiple arithmetic and/or logical circuit units such as multipliers and/or adders that can act simultaneously, in parallel, and/or the like. Such dedicated hardware units 336 may include, without limitation, graphical processing units (GPUs), dedicated signal processing modules, field programmable gate arrays (FPGA), other reconfigurable hardware that has been configured to instantiate parallel processing units for one or more specific tasks, or the like. Computing device, processor 104, apparatus 100, or machine learning module 300 may be configured to instruct one or more dedicated hardware units 336 to perform one or more operations described herein, such as evaluation of model and/or algorithm outputs, one-time or iterative updates to parameters, coefficients, weights, and/or biases, vector and/or matrix operations, and/or any other operations described in this disclosure.

Referring now to FIG. 4, an exemplary embodiment of neural network 400 is illustrated. For the purposes of this disclosure, a neural network or artificial neural network is a network of “nodes” or data structures having one or more inputs, one or more outputs, and a function determining outputs based on inputs. Such nodes may be organized in a network, such as without limitation a convolutional neural network, including an input layer of nodes 404, at least an intermediate layer of nodes 408, and an output layer of nodes 412. Connections between nodes may be created via the process of “training” neural network 400, in which elements from a training dataset are applied to the input nodes, and a suitable training algorithm (such as Levenberg-Marquardt, conjugate gradient, simulated annealing, or other algorithms) is then used to adjust the connections and weights between nodes in adjacent layers of the neural network 400 to produce the desired values at the output nodes. This process is sometimes referred to as deep learning. Connections may run solely from input nodes toward output nodes in a “feed-forward” network or may feed outputs of one layer back to inputs of the same or a different layer in a “recurrent network”. As a further nonlimiting example, neural network 400 may include a convolutional neural network comprising an input layer of nodes 404, one or more intermediate layers of nodes 408, and an output layer of nodes 412. For the purposes of this disclosure, a “convolutional neural network” is a type of neural network 400 in which at least one hidden layer is a convolutional layer that convolves inputs to that layer with a subset of inputs known as a “kernel”, along with one or more additional layers such as pooling layers, fully connected layers, and the like.

Referring now to FIG. 5, an exemplary embodiment of a node 500 of neural network 400 is illustrated. Node 500 may include, without limitation, a plurality of inputs, x_i, that may receive numerical values from inputs to neural network 400 containing the node 500 and/or from other nodes 500. Node 500 may perform one or more activation functions to produce its output given one or more inputs, such as without limitation computing a binary step function comparing an input to a threshold value and outputting either a logic 1 or logic 0 output or its equivalent, a linear activation function whereby an output is directly proportional to input, and/or a nonlinear activation function wherein the output is not proportional to the input. Nonlinear activation functions may include, without limitation, a sigmoid function of the form

$f (x) = \frac{1}{1 - e^{- x}}$

given input x, a tanh (hyperbolic tangent) function of the form

$\frac{e^{x} - e^{- x}}{e^{x} + e^{- x}},$

a tanh derivative function such as f(x)=tanh²(x), a rectified linear unit function such as f(x)=max (0, x), a “leaky” and/or “parametric” rectified linear unit function such as f(x)=max(ax, x) for some value of α, an exponential linear units function such as

$f (x) = {\begin{matrix} x for x \geq 0 \\ α (e^{x} - 1) for x < 0 \end{matrix}$

for some value of α (this function may be replaced and/or weighted by its own derivative in some embodiments), a softmax function such as

$f (x_{i}) = \frac{e^{x}}{Σ_{i} x_{i}}$

where the inputs to an instant layer are x_i, a swish function such as f(x)=x*sigmoid(x), a Gaussian error linear unit function such as f(x)=α(1+tanh(√{square root over (2/π)}(x+bx^r))) for some values of α, b, and r, and/or a scaled exponential linear unit function such as

$f (x) = λ {\begin{matrix} α (e^{x} - 1) for x < 0 \\ x for x \geq 0 \end{matrix} .$

Fundamentally, there is no limit to the nature of functions of inputs x_i, that may be used as activation functions. As a nonlimiting and illustrative example, node 500 may perform a weighted sum of inputs using weights, w_i, that are multiplied by respective inputs, x_i. Additionally or alternatively, a bias b may be added to the weighted sum of the inputs such that an offset is added to each unit in a neural network layer that is independent of the input to the layer. The weighted sum may then be input into a function, φ, which may generate one or more outputs, y. Weight, w_i, applied to an input, x_i, may indicate whether the input is “excitatory”, indicating that it has strong influence on the one or more outputs, y, for instance by the corresponding weight having a large numerical value, or “inhibitory”, indicating it has a weak influence on the one more outputs, y, for instance by the corresponding weight having a small numerical value. The values of weights, w_i, may be determined by training neural network 400 using training data, which may be performed using any suitable process as described above.

Referring now to FIG. 6, an exemplary embodiment of fuzzy set comparison 600 is illustrated. A first fuzzy set 604 may be represented, without limitation, according to a first membership function 608 representing a probability that an input falling on a first range of values 612 is a member of the first fuzzy set 604, where the first membership function 608 has values on a range of probabilities such as without limitation the interval [0,1], and an area beneath the first membership function 608 may represent a set of values within the first fuzzy set 604. Although first range of values 612 is illustrated for clarity in this exemplary depiction as a range on a single number line or axis, first range of values 612 may be defined on two or more dimensions, representing, for instance, a Cartesian product between a plurality of ranges, curves, axes, spaces, dimensions, or the like. First membership function 608 may include any suitable function mapping first range 612 to a probability interval, including without limitation a triangular function defined by two linear elements such as line segments or planes that intersect at or below the top of the probability interval. As a non-limiting example, triangular membership function may be defined as:

$y (x, a, b, c) = {\begin{matrix} 0, for x > c and x < a \\ \frac{x - a}{b - a}, for a \leq x < b \\ \frac{c - x}{c - b}, if b < x \leq c \end{matrix}$

a trapezoidal membership function may be defined as:

$y (x, a, b, c, d) = \max (\min (\frac{x - a}{b - a}, L \frac{d - x}{d - c}), 0)$

a sigmoidal function may be defined as:

$y (x, a, c) = \frac{1}{1 - e^{- a (x - c)}}$

a Gaussian membership function may be defined as:

$y (x, c, σ) = e^{- \frac{1}{2} {(\frac{x - c}{σ})}^{2}}$

and a bell membership function may be defined as:

$y (x, a, b, c,) = {[1 + {❘ \frac{x - c}{a} ❘}^{2 b}]}^{- 1}$

A person of ordinary skill in the art, upon reviewing the entirety of this disclosure, will be aware of various alternative or additional membership functions that may be used consistently with this disclosure.

With continued reference to FIG. 6, in one or more embodiments, first fuzzy set 604 may represent any value or combination of values as described above, including output from one or more machine learning models. A second fuzzy set 616, which may represent any value which may be represented by first fuzzy set 604, may be defined by a second membership function 620 on a second range 624; second range 624 may be identical and/or overlap with first range 612 and/or may be combined with first range via Cartesian product or the like to generate a mapping permitting evaluation overlap of first fuzzy set 604 and second fuzzy set 616. Where first fuzzy set 604 and second fuzzy set 616 have a region 628 that overlaps, first membership function 608 and second membership function 620 may intersect at a point 632 representing a probability, as defined on probability interval, of a match between first fuzzy set 604 and second fuzzy set 616. Alternatively, or additionally, a single value of first and/or second fuzzy set may be located at a locus 636 on first range 612 and/or second range 624, where a probability of membership may be taken by evaluation of first membership function 608 and/or second membership function 620 at that range point. A probability at 628 and/or 632 may be compared to a threshold 640 to determine whether a positive match is indicated. Threshold 640 may, in a nonlimiting example, represent a degree of match between first fuzzy set 604 and second fuzzy set 616, and/or single values therein with each other or with either set, which is sufficient for purposes of the matching process; for instance, threshold 640 may indicate a sufficient degree of overlap between an output from one or more machine learning models. Alternatively or additionally, each threshold 640 may be tuned by a machine learning and/or statistical process, for instance and without limitation as described in further detail in this disclosure.

With continued reference to FIG. 6, in one or more embodiments, a degree of match between fuzzy sets may be used to classify plurality of signal features 132 as described above in this disclosure. As a nonlimiting example, if one or more signal features 132 are associated with a fuzzy set that matches a fuzzy set of a cohort by having a degree of overlap exceeding a threshold, computing device may classify the one or more signal features 132 as belonging to that cohort. Where multiple fuzzy matches are performed, degrees of match for each respective fuzzy set may be computed and aggregated through, for instance, addition, averaging, or the like, to determine an overall degree of match.

With continued reference to FIG. 6, in one or more embodiments, to generate labels 128, one or more signal features 132 may be compared to multiple fuzzy sets of multiple cohorts. As a nonlimiting example, one or more signal features 132 or similar parameters within one or more cardiac signal 116 may be represented by a fuzzy set that is compared to each of the multiple fuzzy sets of multiple cohorts, and a degree of overlap exceeding a threshold between the fuzzy set representing the one or more signal features 132 and any of the multiple fuzzy sets representing multiple cohorts may cause computing device to classify the one or more signal features 132 as belonging to that cohort. As a nonlimiting example, there may be two fuzzy sets representing two cohorts, cohort A and cohort B. Cohort A may have a cohort A fuzzy set, cohort B may have a cohort B fuzzy set, and signal feature 132 may have a signal feature fuzzy set. Computing device may compare signal feature fuzzy set with each of cohort A fuzzy set and cohort B fuzzy set, as described above, and classify one or more signal features 132 to either, both, or neither of cohort A fuzzy set and cohort B fuzzy set. Machine learning methods as described throughout this disclosure may, in a nonlimiting example, generate coefficients used in fuzzy set equations as described above, such as without limitation x, c, and σ of a Gaussian set as described above, as outputs of machine learning methods. Likewise, one or more signal features 132 may be used indirectly to determine a fuzzy set, as signal feature fuzzy set may be derived from outputs of one or more machine learning models that take one or more signal features 132 directly or indirectly as inputs.

With continued reference to FIG. 6, in one or more embodiments, fuzzy set comparison 600 may include a fuzzy inference model. For the purposes of this disclosure, a “fuzzy inference model” is a model that uses fuzzy logic to reach a decision and derive a meaningful outcome. As a nonlimiting example, a fuzzy inference system may be associated with various degrees of a medical condition, such as “Normal”, “Grade 1”, “Grade 2”, “Grade 3”, and “Indeterminate”, as described above. In one or more embodiments, an inferencing rule may be applied to determine a fuzzy set membership of a combined output based on the fuzzy set membership of linguistic variables. As a nonlimiting example, membership of a combined output in a “Grade 3” fuzzy set may be determined based on a percentage membership of a second linguistic variable with a first mode in an “Grade 3” fuzzy set and a percentage membership of a second linguistic variable associated with a second mode in a “Grade 2” fuzzy set. In one or more embodiments, parameters of one or more signal features 132 may then be determined by comparison to a threshold or output using another defuzzification process. Each stage of such a process may be implemented using any type of machine learning model, such as any type of neural network, as described herein. In one or more embodiments, parameters of one or more fuzzy sets may be tuned using machine learning.

With continued reference to FIG. 6, fuzzy set comparison 600 may be generated as a function of determining a data compatibility threshold. Data compatibility threshold may be determined by a computing device. In some embodiments, computing device may use a logic comparison program, such as, but not limited to, a fuzzy logic model to determine the compatibility threshold and/or version authenticator. Each such compatibility threshold may be represented as a value for a posting variable representing the compatibility threshold, or in other words a fuzzy set as described above that corresponds to a degree of compatibility and/or allowability as calculated using any statistical, machine learning, or other method that may occur to a person of ordinary skill in the art upon reviewing the entirety of this disclosure. In some embodiments, determining compatibility threshold may include using a linear regression model. A linear regression model may include a machine learning model. In some embodiments, determining compatibility threshold may include using a classification model. A classification model may be configured to input collected data and cluster data to a centroid based on, but not limited to, frequency of appearance, linguistic indicators of compatibility and/or allowability, and the like. Centroids may include scores assigned to them such that the compatibility threshold may each be assigned a score. In some embodiments, a classification model may include a K-means clustering model. In some embodiments, a classification model may include a particle swarm optimization model. In some embodiments, determining a compatibility threshold may include using a fuzzy inference engine. A fuzzy inference engine may be configured to map one or more compatibility thresholds using fuzzy logic. In some embodiments, a plurality of computing devices may be arranged by a logic comparison program into compatibility arrangements. Membership function coefficients and/or constants as described above may be tuned according to classification and/or clustering algorithms. As a nonlimiting example, a clustering algorithm may determine a Gaussian or other distribution about a centroid corresponding to a given compatibility threshold, and an iterative or other method may be used to find a membership function, for any membership function type as described above, that minimizes an average error from the statistically determined distribution, such that, for instance, a triangular or Gaussian membership function about a centroid representing a center of the distribution that most closely matches the distribution. Error functions to be minimized, and/or methods of minimization, may be performed without limitation according to any error function and/or error function minimization process and/or method as described in this disclosure.

With continued reference to FIG. 6, an inference engine may combine rules, such as any semantic language the like thereof. The degree to which a given input function membership matches a given rule may be determined by a triangular norm or “T-norm” of the rule or output function with the input function, such as min (a, b), product of a and b, drastic product of a and b, Hamacher product of a and b, or the like, satisfying the rules of commutativity (T(a, b)=T(b, a)), monotonicity: (T(a, b)≤T(c, d) if a≤c and b≤d), (associativity: T(a, T(b, c))=T(T(a, b), c)), and the requirement that the number 1 acts as an identity element. Combinations of rules (“and” or “or” combination of rule membership determinations) may be performed using any T-conorm, as represented by an inverted T symbol or “⊥,” such as max (a, b), probabilistic sum of a and b (a+b−a×b), bounded sum, and/or drastic T-conorm; any T-conorm may be used that satisfies the properties of commutativity: ⊥(a, b)=⊥(b, a), monotonicity: ⊥(a, b)≤⊥(c, d) if a≤c and b≤d, associativity: ⊥(a, ⊥(b, c))=⊥(⊥(a, b), c), and identity element of 0. Alternatively or additionally, T-conorm may be approximated by sum, as in a “product-sum” inference engine in which T-norm is product and T-conorm is sum. A final output score or other fuzzy inference output may be determined from an output membership function as described above using any suitable defuzzification process, including without limitation Mean of Max defuzzification, Centroid of Area/Center of Gravity defuzzification, Center Average defuzzification, Bisector of Area defuzzification, or the like. Alternatively or additionally, output rules may be replaced with functions according to the Takagi-Sugeno-King (TSK) fuzzy model.

Referring now to FIG. 7, an exemplary embodiment of a method 700 for correcting machine learning model predictions is described. At step 705, method 700 includes receiving, by processor 104, at least a cardiac signal 116 having a plurality of segments. This step may be implemented with reference to details described above in this disclosure and without limitation.

With continued reference to FIG. 7, at step 710, method 700 includes generating, for at least a segment of plurality of segments, label 128 representing at least a signal feature 132. This step may be implemented with reference to details described above in this disclosure and without limitation.

With continued reference to FIG. 7, at step 715, method 700 includes generating, by processor 104, at least an automated annotation 160 as a function of label 128. This step may be implemented with reference to details described above in this disclosure and without limitation.

With continued reference to FIG. 7, at step 720, method 700 includes generating, by processor 104 using correction module 168, at least a correction 164 upon detecting an absence of annotations. This step may be implemented with reference to details described above in this disclosure and without limitation.

With continued reference to FIG. 7, at step 725, method 700 includes receiving, by processor 104 using user interface 148, at least an input 172 from user. This step may be implemented with reference to details described above in this disclosure and without limitation.

With continued reference to FIG. 7, at step 730, method 700 includes creating, by processor 104, at least a user annotation 176 within at least a cardiac signal 116 using at least an input 172, wherein creating the at least a user annotation 176 includes validating at least an automated annotation 160 and generating, for each incorrect automatic annotation 160 identified based on the validation, the at least a user annotation 176. This step may be implemented with reference to details described above in this disclosure and without limitation.

With continued reference to FIG. 7, at step 735, method 700 includes updating, by processor 104, at least a cardiac signal 116 and annotation machine learning model 136 as a function of at least a correction 164 and at least a user annotation 176. This step may be implemented with reference to details described above in this disclosure and without limitation.

With continued reference to FIG. 7, at step 740, method 700 includes displaying, by processor 104 using user interface 148, updated at least a cardiac signal 116. This step may be implemented with reference to details described above in this disclosure and without limitation.

Referring now to FIG. 8, an exemplary embodiment of a workflow of apparatus 100 is illustrated. At 802, one or more case files, such as Prucka files, may be downloaded. For the purposes of this disclosure, a “Prucka file” is a specialized file format utilized by the Prucka CardioLab system, an electrophysiology recording and mapping system developed by GE Healthcare. This file format is designed to store and analyze data from cardiac electrophysiology studies, including IEGM and ECG signals, and various other clinical measurements. A Prucka file facilitates a detailed recording of electrical activity within a heart, thereby aiding electrophysiologists in diagnosing and treating cardiac arrhythmias. It encompasses annotations, measurements, and other pertinent clinical data. The CardioLab system creates and manages these files, providing critical information to guide procedures such as catheter ablation.

With continued reference to FIG. 8, at 804, apparatus 100 may be loaded, for example, by loading an executable instruction for labeling one or more cardiac signals 116. Apparatus 100 may include a plurality of modules, such as an input module, a pre-processing module, a training module, an output module, and/or the like. Apparatus 100 may store data that may be generated by these modules while performing corresponding operation. Additionally, and/or alternatively, such data may be retrieved from a data store, such as data repository 112, associated with apparatus 100. Input module may be configured to receive one or more cardiac signals 116, for example without limitation, intracardiac signal, ECG signals, IEGM signals, and/or the like. Input module may receive one or more cardiac signals 116 from one or more sensors. Input module may receive one or more cardiac signals 116 from a data store, such as data repository 112. Further, such one or more signals may correspond to an electrical activity of a patient's heart.

With continued reference to FIG. 8, input module may receive input data based on a set of protocols. A user may view a Prucka procedure log and refer to its comments section to identify each mapped structure (as recorded by an operator during a procedure), use the time stamp feature to extract data only at the time corresponding to the comment (e.g., start extraction at comment “LSPV” at 2:31 PM, end extraction at comment “LIPV” at 2:32 PM), and label each structure-specific extract using the comment entered by the operator during the procedure. The set of protocols may enable not only labeling of individual structures, but also the context in which the structure was mapped (e.g., baseline, post-isolation). Pre-processing module may be configured to perform pre-processing on one or more cardiac signals 116. Pre-processing module may utilize one or more pre-processing techniques, such as without limitation, data conversion techniques, data cleaning techniques, data validation techniques, and data labeling techniques. Data conversion techniques may employ one or more data conversion algorithms to perform data conversion on one or more cardiac signals 116. Data conversion may allow integration and utilization of converted data across one or more computing systems. Further, converted data may ensure an accurate representation of one or more cardiac signals 116, including one or more signal features. Additionally, data cleaning techniques may incorporate resampling algorithms to adjust a sampling rate and a time interval of converted data corresponding to one or more data formats. Further, data cleaning techniques may employ one or more data cleaning algorithms to perform data cleaning on converted signals. Data cleaning algorithms may remove noise, artifacts, and inference.

With continued reference to FIG. 8, at 806, a user login interface may be loaded. User login interface may be configured to receive login credentials, for example, a username, a password, and the like. At 808, a database may be configured to store the login credentials, consistent with details described in this disclosure. Further, at 810, a determination may be made regarding whether received credentials are valid or not. If login credentials are not valid, then at 812, instructions for loading user login interface may be re-loaded. Further, if login credentials are valid, at 814, a case user interface for selecting one or more case portions is displayed. Additionally, at 816, Prucka files may be received by apparatus 100 for labeling of one or more cardiac signals 116. At 818, each portion of one or more case portions may receive a user input to display the one or more cardiac signals 116 associated with one or more case portions. At 820, waveform cardiac signals 116 and labels 128 may be loaded. At 822, a determination is made regarding whether waveform cardiac signals 116 are annotated or not. If waveform cardiac signals 116 are not annotated, then at 824, correction 164 may be performed, and updated correction data may be sent to a Sigid correction database. If waveform cardiac signals 116 are annotated, then at 826, it may be then determined whether new annotation is required or not. If new annotation is not required, then at 828, an annotation window length may be changed, and an updated window length may be sent to Sigid correction database. However, if new annotation is required, then, at 830, the new annotation may be added to waveform cardiac signals 116, and new annotation data may be added to Sigid correction database.

Referring now to FIG. 9A-D, exemplary GUIs 900a-x are included to collectively illustrate a nonlimiting example of apparatus 100 for correcting machine learning model predictions.

Referring now to FIG. 9A, an exemplary GUI 900a for user authentication is illustrated. GUI 900a includes a username option 902a, a password option 902b, a login option 902c, and a logo 904. Username option 902a may be configured to receive a user input indicative of a username. Further, password option 902b may be configured to receive a user input indicative of a password. Further, based on the username and the password, login option 902c may be configured to perform user authentication. Further, user interface 800b may be configured to display logo 904.

Referring now to FIG. 9B, an exemplary GUI 900b for displaying a case directory is illustrated. GUI 900b may include a proto files directory option 906. For the purposes of this disclosure, a “proto files directory” is a designated folder within a project that contains Protocol Buffers (protobuf) definition files with a .proto extension, consistent with details described above in this disclosure. These files define the structure and schema of data for serialization and deserialization, ensuring efficient and consistent data exchange between systems. The directory is organized to facilitate management, version control, and reference during development, and the proto files within are compiled using tools like protoc to generate source code for various programming languages. Proto files directory option 906 may be configured to receive a user input indicative of a selection of one or more folders 908, for example, the folder 908 may include case waveform files. Further, the one or more folders 908 may be configured to display case waveform files corresponding to a selected case. Further, the case waveform files may be configured to display waveforms associated with one or more cardiac signals 116.

Referring now to FIG. 9C, an exemplary GUI 900c is illustrated for selecting one or more case portions. One or more case portions may include case portions 910a-n. Case portions 910a-n may be configured to display a case symbol, a case id, and a case analysis percentage. Further, the one or more case portions, for example, case portion 910a may be configured to display a case summary portion. Case summary portion may display at least one of: a case type data, an image URL data, a sig_thresh data, an ablation catheter data, ablation type rf cryo data, age data, anatomy data, caseid data, checked for anonymization data, comments data, dataid data, date data, display data, electrogram type data, EP_recording_system data, ethnicity data, gender data, map catheter data, operator institution data, paroxysmal v persistent AF data, phase of procedure data, redo data, rhythm data, s3 data location data, s3 original data location data, and veins involved annotated data. Further, the user id option 912 may be configured to display a userid. Further, the refresh option 914 may be configured to display the case user interface iteratively.

Referring now to FIG. 9D, an exemplary GUI 900d is illustrated for displaying one or more labeled cardiac signals 116. GUI 900d may include a plurality of options such as a select all option 916, a unselect all option 918, an ACH 1-2 option 920, an ACH 2-3 option 922, an ACH 3-4 option 924, an ACH 4-5 option 926, an ACH 5-6 option 928, an ACH 6-7 option 930, an ACH 7-8 option 932, an VI option 934, an annotation window option 936, a scale length window option 938, a previous annotation window option 940, and a next annotation window option 942, a waveform representation 944, at least a labeled segment 946a-n, and an annotation 948. Further, waveform representation 944 may include one or more cardiac signals 116 such as an intracardiac signal.

With continued reference to FIG. 9D, cardiac signal 116 may further include labeled segments 946a-n. In some embodiments, user interface 148 may be configured to display the at least one labeled segment 946a-n of one or more labeled cardiac signals 116 with second visual indicator 156 different from first visual indicator 152 of one or more labeled cardiac signals 116. As a nonlimiting example, at least one labeled segment 946a-n of one or more labeled cardiac signals 116 may be marked with a second color different from a first color of the one or more labeled cardiac signals 116. Second color may be specified based on label 128. As a nonlimiting example, second color may be specified as purple based on a “yes” label 128. As another nonlimiting example, second color may be specified as red based on a “no” label 128. As another nonlimiting example, second color may be specified as blue based on a “maybe” label 128. As another nonlimiting example, first color may be specified as green in order to be differentiated from second color. Details described herein may be consistent with details disclosed in U.S. Pat. App. Ser. No. 63/614,864.

With continued reference to FIG. 9D, apparatus 100 may be configured to display or hide one or more labeled cardiac signals 116 based on the plurality of options described above. Specifically, a respective option of the plurality of options may be configured to display or hide a respective cardiac signal 116 agnostic to other cardiac signals 116 of one or more labeled cardiac signals 116. As a nonlimiting example, the select all option 916 may be configured to display each cardiac signal 116 of one or more labeled cardiac signals 116 associated with the waveform representations 944. The unselect all option 918 may be configured to hide each cardiac signal 116 of one or more labeled cardiac signals 116 associated with waveform representation 944. ACH 1-2 option 920, the ACH 2-3 option 922, ACH 3-4 option 924, ACH 4-5 option 926, ACH 5-6 option 928, ACH 6-7 option 930, and/or ACH 7-8 option 932 may be configured to display or hide corresponding one or more labeled cardiac signals 116. As a nonlimiting example, ACH 1-2 option 920 may be configured to display or hide a cardiac signal 116. As another nonlimiting example, VI option 932 may be configured to display or hide a cardiac signal 116.

With continued reference to FIG. 9D, the annotation window option 940 may be configured to enable annotation window 948. A size of the annotation window 948 may indicate a size of at least one segment of one or more cardiac signals 116 correlated with label 128. Further, annotation window 948 may include annotation segments 948a-n. User interface 148 may be configured to display at least one segment of one or more annotated cardiac signals 116 in third visual indicator 180 different from first visual indicator 152 and second visual indicator 156. As a nonlimiting example, at least one annotation segment 948a-n of one or more annotated cardiac signals 116 may be annotated with a third color different from a first color of the one or more annotated cardiac signals 116. Third color may be specified based on label 128. As a nonlimiting example, third color may be specified as a brown color based on a “yes” label 128, and a white color based on a “no” label 128. As another nonlimiting example, first color may be specified as yellow in order to be differentiated from third color.

With continued reference to FIG. 9D, a color of a respective annotation segment 948a-n of one or more annotated cardiac signals 116 may indicate at least a characteristic of one or more signal features 132 or at least an input 172 indicative of a corrective factor corresponding to the respective annotation segment 948a-n of the one or more annotated cardiac signals 116. As a nonlimiting example, a white color of annotation segment 948a-n of one or more annotated cardiac signals 116 may indicate an absence of any “yes” label 128. As another nonlimiting example, a white color may indicate a presence of at least a “no” label 128. As another nonlimiting example, a brown color may indicate a presence of at least a “yes” label 128.

With continued reference to FIG. 9D, a yellow color of a respective annotation segment 948a-n of one or more annotated cardiac signals 116 may indicate a corrective factor corresponding to at least one respective annotation segment 948a-n of the one or more annotated cardiac signals 116. As a nonlimiting example, a yellow color may indicate a label change associated with a user validation; a “yes” label 128 may be changed to a “no” label 128 based on the user validation. A light brown color of a respective annotation segment 948a-n of one or more annotated cardiac signals 116 may indicate a corrective factor corresponding to at least one respective annotation segment 948a-n of the one or more annotated cardiac signals 116. As a nonlimiting example, a yellow color may indicate an addition of label 128 associated with a user validation; a “yes” label 128 may be added to at least one respective annotation segment 948a-n of one or more annotated cardiac signals 116 based on the user validation. As another nonlimiting example, a size of annotation window 948 may be changed based on user validation. As another nonlimiting example, annotation segment 948a-n may be displayed with a brown color to indicate that the annotation segment 948a-n of waveform representation 944 may be annotated by a machine learning model.

With continued reference to FIG. 9D, the scale window length option 938 may be configured to change the size of the annotation window 948. The scale length window option 938 may include a plurality of scale length window options, for example, a scale length window option of 50 ms (938a), and a scale length window option of 100 ms (938b).

With continued reference to FIG. 9D, a scale length window option 938a of 50 ms may be configured to specify a size of the annotation window 948 as 50 ms. Scale length window option 938b of 100 ms may be configured to specify a size of the annotation window as 100 ms. Scale length window option 938 may further include 150 ms, 200 ms, and the like.

With continued reference to FIG. 9D, previous annotation window option 940 may be configured to change a current location of annotation window 948 to a previous location of the annotation window 948. Next annotation window 942 may be configured to change a current location of annotation window 948 to a next location of the annotation window 948.

With continued reference to FIG. 9D, annotation window option 938 may be enabled to validate one or more labeled cardiac signals 116; accordingly, user interface 148 may be used to validate the one or more labeled cardiac signals 116.

With continued reference to FIG. 9D, a clinician or technician may provide input 172 to create user annotations 176, for example, user annotations 176 for predictions that a machine learning model fails to predict or a command to modify one or more automated annotations 160. As a nonlimiting example, annotation segment 948a may be displayed with a light brown color to indicate that the annotation segment 948a is user annotation 176 annotated by a technician. As another nonlimiting example, annotation segments 948b-d may be displayed with a dark brown color to indicate that a segment of the waveform representation 944 is annotated by a machine learning model. As another nonlimiting example, annotation segment 948e may be displayed with a yellow color to indicate that the annotation segments 948b-d of the waveform representation 944 are annotated by a machine learning model, but later corrected by a technician. Specifically, a yellow color may indicate an addition of label 128 associated with a user validation; a “yes” label 128 may be added to at least one annotation segment 948a-n of one or more labeled cardiac signals 116 based on the user validation.

With continued reference to FIG. 9D, a technician may change automated annotation 160 using previous annotation window option 940 and the next annotation window option 942. As a nonlimiting example, to correct automated annotation 160, a technician may position annotation window 948 on top of the automated annotation 160 using previous annotation window option 940 and/or next annotation window option 942, thereafter click on the annotated waveform representation 944. As a result, the color of annotation segment 948a-n may change accordingly to indicate that a change has been made.

With continued reference to FIG. 9D, user interface 148 may receive input 172 to correct automated annotation 160 predicted by a machine learning model. For example, the user may decide to correct automated annotation 160 within a window between 57 s and 58 s. In such a case, user may select ACH 3-4 option 924, which is configured to display or hide a cardiac signal 116 and use previous annotation window option 940 and the next annotation window option 942 to select at least an automated annotation 160 to be corrected. As a nonlimiting example, a yellow color of at least an annotation segment 948a-n may indicate a corrective factor corresponding to the at least an annotation segment 948a-n pertaining to one or more annotated cardiac signals 116.

Referring now to FIG. 10, it is to be noted that any one or more of the aspects and embodiments described herein may be conveniently implemented using one or more machines (e.g., one or more computing devices that are utilized as a user computing device for an electronic document, one or more server devices, such as a document server, etc.) programmed according to the teachings of the present specification, as will be apparent to one of ordinary skill in the computer art. Appropriate software coding can readily be prepared by skilled programmers based on the teachings of the present disclosure, as will be apparent to those of ordinary skill in the software art. Aspects and implementations discussed above employing software and/or software modules may also include appropriate hardware for assisting in the implementation of the machine executable instructions of the software and/or software module. Such software may be a computer program product that employs a machine-readable storage medium. A machine-readable storage medium may be any medium that is capable of storing and/or encoding a sequence of instructions for execution by a machine (e.g., a computing device) and that causes the machine to perform any one of the methodologies and/or embodiments described herein. Examples of a machine-readable storage medium include, but are not limited to, a magnetic disk, an optical disc (e.g., CD, CD-R, DVD, DVD-R, etc.), a magneto-optical disk, a read-only memory “ROM” device, a random-access memory “RAM” device, a magnetic card, an optical card, a solid-state memory device, an EPROM, an EEPROM, and any combinations thereof. A machine-readable medium, as used herein, is intended to include a single medium as well as a collection of physically separate media, such as, for example, a collection of compact discs or one or more hard disk drives in combination with a computer memory. As used herein, a machine-readable storage medium does not include transitory forms of signal transmission. Such software may also include information (e.g., data) carried as a data signal on a data carrier, such as a carrier wave. For example, machine-executable information may be included as a data-carrying signal embodied in a data carrier in which the signal encodes a sequence of instruction, or portion thereof, for execution by a machine (e.g., a computing device) and any related information (e.g., data structures and data) that causes the machine to perform any one of the methodologies and/or embodiments described herein. Examples of a computing device include, but are not limited to, an electronic book reading device, a computer workstation, a terminal computer, a server computer, a handheld device (e.g., a tablet computer, a smartphone, etc.), a web appliance, a network router, a network switch, a network bridge, any machine capable of executing a sequence of instructions that specify an action to be taken by that machine, and any combinations thereof. In one example, a computing device may include and/or be included in a kiosk.

With continued reference to FIG. 10, the figure shows a diagrammatic representation of one embodiment of a computing device in the exemplary form of a computing system 1000 within which a set of instructions for causing the computing system 1000 to perform any one or more of the aspects and/or methodologies of the present disclosure may be executed. It is also contemplated that multiple computing devices may be utilized to implement a specially configured set of instructions for causing one or more of the devices to perform any one or more of the aspects and/or methodologies of the present disclosure. Computing system 1000 may include a processor 1004 and a memory 1008 that communicate with each other, and with other components, via a bus 1012. Bus 1012 may include any of several types of bus structures including, but not limited to, a memory bus, a memory controller, a peripheral bus, a local bus, and any combinations thereof, using any of a variety of bus architectures. Processor 1004 may include any suitable processor, such as without limitation a processor incorporating logical circuitry for performing arithmetic and logical operations, such as an arithmetic and logic unit, which may be regulated with a state machine and directed by operational inputs from memory and/or sensors; processor 1004 may be organized according to Von Neumann and/or Harvard architecture as a non-limiting example. Processor 1004 may include, incorporate, and/or be incorporated in, without limitation, a microcontroller, microprocessor, digital signal processor, field programmable gate array, complex programmable logic device, graphical processing unit, general-purpose graphical processing unit, tensor processing unit, analog or mixed signal processor, trusted platform module, a floating-point unit, and/or system on a chip.

With continued reference to FIG. 10, memory 1008 may include various components (e.g., machine-readable media) including, but not limited to, a random-access memory component, a read only component, and any combinations thereof. In one example, a basic input/output system 1016, including basic routines that help to transfer information between elements within computing system 1000, such as during start-up, may be stored in memory 1008. Memory 1008 (e.g., stored on one or more machine-readable media) may also include instructions (e.g., software) 1020 embodying any one or more of the aspects and/or methodologies of the present disclosure. In another example, memory 1008 may further include any number of program modules including, but not limited to, an operating system, one or more application programs, other program modules, program data, and any combinations thereof.

With continued reference to FIG. 10, computing system 1000 may also include a storage device 1024. Examples of a storage device (e.g., storage device 1024) include, but are not limited to, a hard disk drive, a magnetic disk drive, an optical disc drive in combination with an optical medium, a solid-state memory device, and any combinations thereof. Storage device 1024 may be connected to bus 1012 by an appropriate interface (not shown). Example interfaces include, but are not limited to, small computer system interface, advanced technology attachment, serial advanced technology attachment, universal serial bus, IEEE 1394 (FIREWIRE), and any combinations thereof. In one example, storage device 1024 (or one or more components thereof) may be removably interfaced with computing system 1000 (e.g., via an external port connector (not shown)). Particularly, storage device 1024 and an associated machine-readable medium 1028 may provide nonvolatile and/or volatile storage of machine-readable instructions, data structures, program modules, and/or other data for computing system 1000. In one example, software 1020 may reside, completely or partially, within machine-readable medium 1028. In another example, software 1020 may reside, completely or partially, within processor 1004.

With continued reference to FIG. 10, computing system 1000 may also include an input device 1032. In one example, a user of computing system 1000 may enter commands and/or other information into computing system 1000 via input device 1032. Examples of input device 1032 include, but are not limited to, an alpha-numeric input device (e.g., a keyboard), a pointing device, a joystick, a gamepad, an audio input device (e.g., a microphone, a voice response system, etc.), a cursor control device (e.g., a mouse), a touchpad, an optical scanner, a video capture device (e.g., a still camera, a video camera), a touchscreen, and any combinations thereof. Input device 1032 may be interfaced to bus 1012 via any of a variety of interfaces (not shown) including, but not limited to, a serial interface, a parallel interface, a game port, a USB interface, a FIREWIRE interface, a direct interface to bus 1012, and any combinations thereof. Input device 1032 may include a touch screen interface that may be a part of or separate from display 1036, discussed further below. Input device 1032 may be utilized as a user selection device for selecting one or more graphical representations in a graphical interface as described above.

With continued reference to FIG. 10, user may also input commands and/or other information to computing system 1000 via storage device 1024 (e.g., a removable disk drive, a flash drive, etc.) and/or network interface device 1040. A network interface device, such as network interface device 1040, may be utilized for connecting computing system 1000 to one or more of a variety of networks, such as network 1044, and one or more remote devices 1048 connected thereto. Examples of a network interface device include, but are not limited to, a network interface card (e.g., a mobile network interface card, a LAN card), a modem, and any combination thereof. Examples of a network include, but are not limited to, a wide-area network (e.g., the Internet, an enterprise network), a local area network (e.g., a network associated with an office, a building, a campus or other relatively small geographic space), a telephone network, a data network associated with a telephone/voice provider (e.g., a mobile communications provider data and/or voice network), a direct connection between two computing devices, and any combinations thereof. A network, such as network 1044, may employ a wired and/or a wireless mode of communication. In general, any network topology may be used. Information (e.g., data, software 1020, etc.) may be communicated to and/or from computing system 1000 via network interface device 1040.

With continued reference to FIG. 10, computing system 1000 may further include a video display adapter 1052 for communicating a displayable image to a display device, such as display device 1036. Examples of a display device include, but are not limited to, a liquid crystal display (LCD), a cathode ray tube (CRT), a plasma display, a light emitting diode (LED) display, and any combinations thereof. Display adapter 1052 and display device 1036 may be utilized in combination with processor 1004 to provide graphical representations of aspects of the present disclosure. In addition to a display device, computing system 1000 may include one or more other peripheral output devices including, but not limited to, an audio speaker, a printer, and any combinations thereof. Such peripheral output devices may be connected to bus 1012 via a peripheral interface 1056. Examples of a peripheral interface include, but are not limited to, a serial port, a USB connection, a FIREWIRE connection, a parallel connection, and any combinations thereof.

The foregoing has been a detailed description of illustrative embodiments of the invention. Various modifications and additions can be made without departing from the spirit and scope of this invention. Features of each of the various embodiments described above may be combined with features of other described embodiments as appropriate in order to provide a multiplicity of feature combinations in associated new embodiments. Furthermore, while the foregoing describes a number of separate embodiments, what has been described herein is merely illustrative of the application of the principles of the present invention. Additionally, although particular methods herein may be illustrated and/or described as being performed in a specific order, the ordering is highly variable within ordinary skill to achieve methods, systems, and software according to the present disclosure. Accordingly, this description is meant to be taken only by way of example, and not to otherwise limit the scope of this invention.

Exemplary embodiments have been disclosed above and illustrated in the accompanying drawings. It will be understood by those skilled in the art that various changes, omissions and additions may be made to that which is specifically disclosed herein without departing from the spirit and scope of the present invention.

APPARATUS AND METHOD FOR CORRECTING MACHINE LEARNING MODEL PREDICTIONS

Information

Publication Number

Date Filed

Date Published

Inventors

Original Assignees

CPC

International Classifications

Abstract

Description

Claims

CROSS-REFERENCE TO RELATED APPLICATIONS

Provisional Applications (1)