The invention relates to methods and apparatus for use in emergency rooms and in other clinical settings, and particularly apparatus and methods that are used to increase the diagnostic accuracy and patient throughput during emergency room or clinical procedures.
The execution of emergency room medicine is usually described as being made up of five elements: identification, triage, anamnesis (i.e., obtaining a preliminary medical history relating to the patient), diagnosis, and prognosis.
Emergency room medicine is characterized by there being a need for speedy handling and diagnosis of patients. Speedy diagnoses are especially important for medical conditions relating to cerebrovascular incidents, strokes, and cardiac events. The requirement of providing speedy diagnoses is compounded by the need to commonly operate in high load situations, especially in situations of mass casualty events, as well as extreme weather conditions, when elderly and weak patients are highly prone to illness. Despite the conditions of urgency and the high load in a typical emergency room setting, it is necessary to provide diagnoses with a relatively high degree of accuracy, since the accuracy of the diagnosis can have a bearing on decisions regarding priority of treatment, which could have repercussions on the survival rate both of the patient being examined and of other patients. Incorrect diagnosis is a common cause of death in the medical field, and many such events occur as a result of a delay in treatment or incorrect diagnosis in the setting of the emergency room.
In accordance with some applications of the invention, methods and apparatus and are provided for at least partially automating the process of receiving a patient's details, details of the patient's present medical state, and/or the patient's medical history, and generating a medical summary that is readable by a healthcare professional. Typically, a patient-questionnaire station outputs questions to the patient, and receives answers to the questions from the patient. At least partially based upon the answers that the patient provides, a computer processor generates a medical summary of the patient, and drives a healthcare-professional interface device to display the medical summary. For example, the medical summary may be displayed upon a monitor that is used by a doctor and/or a nurse, and/or a print-out of the medical summary to be read by a doctor and/or a nurse may be generated. Alternatively or additionally, the medical summary is automatically entered into the hospital's electronic record system and/or the patient's electronic medical records. For some applications, a list of patients in the emergency room is presented upon a dashboard, and healthcare professionals are able to see a given patient's automatically-generated medical summary by selecting that patient from the list.
Typically, the medical summary is generated in prose form. For some applications, the computer processor is configured to generate the medical summary in a language that is different from the language in which the questions were output to the patient, and/or in a language that is different from the language in which the patient inputted their responses to the questions. In this manner, if, for example, a patient is not a native speaker of the language that is used by the doctor, the patient is able to receive questions in a language that he/she understands and to respond in that language, while the doctor is able to receive the medical summary in the language that he/she best understands.
There is therefore provided, in accordance with some applications of the invention, a method for generating a medical summary of a patient, the method including:
using a patient-interface device, outputting a plurality of questions to the patient, and receiving respective answers from the patient to the plurality of questions; and
using at least one computer processor:
There is further provided, in accordance with some applications of the invention, a computer software product, for generating a medical summary of a patient, and for use with a patient-interface device and a healthcare-professional interface device, the computer software product including a non-transitory computer-readable medium in which program instructions are stored, which instructions, when read by a computer cause the computer to perform the steps of:
driving the patient-interface device to output a plurality of questions to the patient and to receive respective answers from the patient to the plurality of questions;
for each of the answers received from the patient, generating a corresponding question sub-template;
embedding the question sub-templates into respective pre-defined locations within a medical summary template; and
driving the healthcare-professional interface device to display a medical summary of the patient in prose form, using the question sub-templates embedded within the medical summary template.
There is further provided, in accordance with some applications of the invention, apparatus for generating a medical summary of a patient, the apparatus including:
a healthcare-professional interface device;
a patient-interface device configured to output a plurality of questions to the patient and to receive respective answers from the patient to the plurality of questions; and
at least one computer processor configured:
In some applications, the computer processor is configured:
to drive the patient-interface device to output the plurality of questions to the patient, and to receive respective answers from the patient to the plurality of questions, in a first language, and
to drive the healthcare-professional interface device to display the medical summary of the patient in prose form, in a second language that is different from the first language.
In some applications, the computer processor is configured to embed the question sub-templates into respective pre-defined locations within the medical summary template by:
based upon at least one symptom that the patient indicates that they are suffering from, selecting a symptom representative template; and
embedding the question sub-templates into respective pre-defined locations within the symptom representative template.
In some applications, the computer processor is further configured, in response to receiving a given answer from the patient to at least one of the questions, to generate an alert on the healthcare-professional interface device.
In some applications, the computer processor is further configured to automatically add the medical summary into an electronic medical record of the patient.
In some applications, the computer processor is further configured, at least partially in response to receiving one or more of the answers from the patient, to generate a first output selected from the group consisting of: an output indicating that the patient should be hospitalized, an output indicating a triage score for the patient, an output recommending that one or more tests be performed on the patient, and an output indicating a differential diagnosis of the patient.
In some applications, the computer processor is further configured to generate a second output indicating which data relating to the patient led to generating the first output.
In some applications, the computer processor is further configured to update the first output in real time, in response to receiving additional data relating to the patient.
In some applications, the computer processor is configured to generate the first output in response to performing machine-learning analysis with respect to the one or more answers.
In some applications, the computer processor is configured to automatically receive additional data relating to the patient, and to drive the healthcare-professional interface device to display the medical summary of the patient in prose form by incorporating at least some of the additional data into the medical summary.
In some applications, the computer processor is configured to automatically receive additional data relating to the patient by automatically receiving medical records of the patient.
In some applications, the computer processor is configured to automatically receive additional data relating to the patient by automatically receiving a result of a test performed upon the patient.
In some applications, the computer processor is configured to embed the question sub-templates into respective pre-defined locations within the medical summary template by, in response to the patient not providing an answer to one of the questions, not including text corresponding to the question sub-template within the medical summary template.
In some applications, the computer processor is configured, in a designated section within the medical summary, to indicate that the patient did not provide an answer to the question.
There is further provided, in accordance with some applications of the invention, a method for generating a medical summary of a patient, the method including:
using a patient-interface device, outputting a plurality of questions to the patient in a first language, and receiving respective answers from the patient to the plurality of questions in the first language;
using at least one computer processor, generating a medical summary of the patient in a second language that is different from the first language, the medical summary being at least partially based upon the answers that were received from the patient; and using the computer processor, driving a healthcare-professional interface device to display the medical summary of the patient in the second language.
There is further provided, in accordance with some applications of the invention, a computer software product, for generating a medical summary of a patient, and for use with a patient-interface device and a healthcare-professional interface device, the computer software product including a non-transitory computer-readable medium in which program instructions are stored, which instructions, when read by a computer cause the computer to perform the steps of:
using the patient-interface device, outputting a plurality of questions to the patient in a first language, and receiving respective answers from the patient to the plurality of questions in the first language;
generating a medical summary of the patient in a second language that is different from the first language, the medical summary being at least partially based upon the answers that were received from the patient; and
driving the healthcare-professional interface device to display the medical summary of the patient in the second language.
There is further provided, in accordance with some applications of the invention, apparatus for generating a medical summary of a patient, the apparatus including:
a healthcare-professional interface device;
a patient-interface device; and
at least one computer processor configured:
In some applications, the computer processor is configured to generate the medical summary in the second language by:
for each of the answers received from the patient, generating a corresponding question sub-template; and
embedding the question sub-templates into respective pre-defined locations within a medical summary template.
In some applications, the computer processor is configured to generate the medical summary in the second language by using known translations of each of the question sub-templates and the medical summary template.
In some applications, the computer processor is configured to embed the question sub-templates into respective pre-defined locations within the medical summary template by:
based upon at least one symptom that the patient indicates that they are suffering from, selecting a symptom representative template; and
embedding the question sub-templates into respective pre-defined locations within the symptom representative template.
In some applications, the computer processor is configured to embed the question sub-templates into respective pre-defined locations within the medical summary template by, in response to the patient not providing an answer to one of the questions, not including text corresponding to the question sub-template within the medical summary template.
In some applications, the computer processor is configured to generate the medical summary by, in a designated section within the medical summary, indicating that the patient did not provide an answer to the question.
The invention will be more fully understood from the following detailed description of applications thereof, taken together with the drawings, in which:
Reference is now made to
Typically, the medical summary is generated in prose form. For some applications, the computer processor is configured to generate the medical summary in a language that is different from the language in which the questions were output to the patient, and/or in a language that is different from the language in which the patient inputted their responses to the questions. In this manner, if, for example, a patient is not a native speaker of the language that is used by the doctor, the patient is able to receive questions in a language that he/she understands and to respond in that language, while the doctor is able to receive the medical summary in the language that he/she best understands.
Typically, the patient-questionnaire station includes a computer processor 26, which communicates with a memory (not shown), and with patient-interface device 24. The computer processor typically drives an output unit of the patient-interface device 24 to output questions to the patient, and receives the patient's inputs from an input unit of the patient-interface device. For some applications, the input unit of the patient-interface device includes a keyboard, a mouse, a joystick, a touchscreen device (such as a smartphone or a tablet computer), a touchpad, a trackball, a voice-command interface, and/or other types of input devices that are known in the art. For some applications, the output portion of the patient-interface device includes a display, and/or a different type of visual, text, graphics, tactile, audio, and/or video output device, e.g., speakers, headphones, a smartphone, or a tablet computer. Typically, the healthcare-professional interface device 30 includes generally similar hardware components to those described with reference to the patient-interface device.
As described hereinabove, a computer processor generates a medical summary of the patient and drives healthcare-professional interface device 30 to display the medical summary. For some applications, computer processor 26 of the patient-questionnaire station is configured to perform the aforementioned steps. Alternatively or additionally, one or more additional computer processors (not shown) that are in communication with computer processor 26 are configured to perform these steps. For example, additional computer processors that are connected to the hospital server may be configured to perform these steps, and/or computer processors that are outside the hospital and disposed within a remote server may be configured to perform these steps. For some applications, any one of the aforementioned computer processors is configured to analyze the patient's responses using machine-learning techniques and to generate a diagnosis of the patient in response thereto (e.g., using techniques as described in WO 18/220565 to Amir, which is incorporated herein by reference). For some applications, any one of the aforementioned computer processors is configured to generate an alert, in response to a given response or set of responses from a patient. For example, in response to a patient indicating that he/she is over a certain age and is suffering from severe chest pain, the computer processor may generate an alert on a healthcare professional interface device indicating that the patient is in urgent need of an assessment by a doctor. In accordance with respective applications, the computer processor generates outputs on an interface device associated with a given healthcare professional, and/or a given set of healthcare professionals, e.g., as described hereinabove. For some applications, the computer processor generates an output on a computer-readable medium (e.g., a non-transitory computer-readable medium), such as a disk, or a portable USB drive, and/or generates an output on a printer.
Reference is now made to
Reference is now made to
In step 44, for each of the answers received by the patient, a corresponding question sub-template is generated, and in step 46, the question sub-templates are embedded into respective pre-defined locations within a medical summary template. Typically, the structure of the medical summary template depends on the main symptoms that the patient is suffering from. Further typically, based upon the main symptoms that the patient is suffering from, a “symptom template representation” is selected, the symptom template representation being a template that contains sections relating to information that is pertinent to such symptoms. The question sub-templates are then embedded within the selected symptom template representation, as described in further detail hereinbelow.
Steps 44 and 46 may be understood with reference to an example shown below of a symptom template representation and a corresponding medical summary that is the output of step 46:
As shown, the symptom template representation typically includes sentence templates (denoted by [square brackets], in the example shown above), and question templates (denoted by {curly brackets}, in the example shown above), and question sub-templates (denoted by <angled brackets>, in the example shown above). The asterisk followed by a comma in the example shown above denote joining of question templates that allow for multiple answers to be entered, whereby the answers are then punctuated correctly with commas, the word “and” before the final entry, etc. A final asterisk denoted the end of such a sentence structure.
As indicated in the above examples, typically the questions in the symptom template representation and the corresponding medical summary are divided into three categories: demographics, history of present illness, and past medical history. For some applications, the three categories are presented in three separate paragraphs, as shown above. It is noted that the example shown above is for when the patient presents with one main symptom. In case in which there are multiple main symptoms, the medical summary typically includes a corresponding number of paragraphs relating to the history of the present illness, with one paragraph corresponding to each of the main symptoms.
As described hereinabove, in step 44, for each of the answers received by the patient, a corresponding question sub-template is generated. Typically, the question category imposes properties that appear in the corresponding question sub-template. For example, for the multiple-choice questions, the question sub-template may (a) contain wording corresponding to the multiple choice question and allow the patient's answer(s) to become embedded within that wording, but (b) also allow for that wording to be modified if the patient answers “None of the above.” By way of example, the multiple choice question may be “Does the chest pain spread or radiate to any of these areas?” and the corresponding multiple-choice answers may be (i) Left arm, (ii) Left shoulder, (iii) Right Arm, (iv) Right shoulder, and (v) None of the above. If the patient selects any one of the first four answers, then the patient's answer is embedded in text of the question sub-template, which states “radiating to <answer>.” However, if the patient answers “None of the above,” then the text of this question sub-template will indicate that the pain does not radiate. For some applications, if a patient doesn't answer a given question, indicated that they didn't understand the question, and/or indicated that they didn't know the answer, the corresponding question sub-template is deleted from the medical summary. Typically, in such cases, an indication of this having happened is provided to the healthcare professional in a separate section of the medical summary.
As described hereinabove, in step 46, the question sub-templates are embedded into respective pre-defined locations within a medical summary template. Typically, the structure of the medical summary template depends on the main symptoms that the patient is suffering from. For example, as described hereinabove, a symptom template representation may be selected based upon the main symptoms that the patient presents, and the question sub-templates may then be arranged within the selected symptom template representation. Typically, the questions that the patient is asked are selected at least partially based upon the answers that patient provided to previous questions, e.g., as described in WO 18/220565 to Amir, which is incorporated herein by reference. In the above example, the questions that were asked and the medical summary that was generated are pertinent to a patient that is suffering from chest pain. However, had the patient initially presented with a suspected broken leg, then the medical summary template would be structured accordingly, and, for example, may include a section relating to how the injury came about, whether the patient is able to walk on the leg, whether there is bruising on the leg, etc.
Referring again to
As described hereinabove, for some applications, the computer processor is configured to generate the medical summary in a language that is different from the language in which the questions were output to the patient, and/or in a language that is different from the language in which the patient inputted their responses to the questions. It is noted that in accordance with the above description, the medical summary is typically built from predefined portions of text. For example, the question sub-templates and the sentence templates of the medical summary template are typically predefined. The computer processor is typically preprogrammed such that the translations all of the options for each of the question sub-templates are known, and the translations of the sentence templates are known. Thus, in order to perform the translation, the computer processor translates each of the components of the medical summary using the known translations of these components. Typically, the result of performing the translation in this manner is that the translated medical summary is a more accurate and readable medical summary, than, for example, if the entire medical summary in the first language was simply to be machine translated to the second language.
For some applications, in addition to generating a patient medical summary, based upon the inputs from the patient (and/or additional data, e.g., as described hereinabove), the computer processor is configured to (a) recommend whether the patient shall be hospitalized, (b) provide a triage score, (c) suggest medical tests, (d) provide a differential diagnosis, and/or (e) provide a patient score. For some applications, in addition to providing one or more of the aforementioned outputs, the computer processor is configured to generate an indication of which data led the computer processor to generate such an output (e.g., which data led the computer processor to recommend that the patient should be hospitalized, and/or to provide a differential diagnosis). For some applications, the computer processor performs such techniques using machine-learning techniques. Typically, the computer processor updates the outputs in real time, in response to receiving additional data (e.g., additional information from the patient, additional test results, etc.) For some applications, such techniques are performed in conjunction with techniques described in WO 18/220565 to Amir, which is incorporated herein by reference.
Applications of the invention described herein can take the form of a computer program product accessible from a computer-usable or computer-readable medium (e.g., a non-transitory computer-readable medium) providing program code for use by or in connection with a computer or any instruction execution system, such as computer processor 26. For the purpose of this description, a computer-usable or computer readable medium can be any apparatus that can comprise, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The medium can be an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system (or apparatus or device) or a propagation medium. Typically, the computer-usable or computer readable medium is a non-transitory computer-usable or computer readable medium.
Examples of a computer-readable medium include a semiconductor or solid-state memory, magnetic tape, a removable computer diskette, a random-access memory (RAM), a read-only memory (ROM), a rigid magnetic disk and an optical disk. Current examples of optical disks include compact disk-read only memory (CD-ROM), compact disk-read/write (CD-R/W) and DVD.
A data processing system suitable for storing and/or executing program code will include at least one processor (e.g., computer processor 26) coupled directly or indirectly to memory elements through a system bus. The memory elements can include local memory employed during actual execution of the program code, bulk storage, and cache memories which provide temporary storage of at least some program code in order to reduce the number of times code must be retrieved from bulk storage during execution. The system can read the inventive instructions on the program storage devices and follow these instructions to execute the methodology of the embodiments of the invention.
Network adapters may be coupled to the processor to enable the processor to become coupled to other processors or remote printers or storage devices through intervening private or public networks. Modems, cable modem and Ethernet cards are just a few of the currently available types of network adapters.
Computer program code for carrying out operations of the invention may be written in any combination of one or more programming languages, including an object-oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the C programming language or similar programming languages.
It will be understood that blocks of the flowcharts shown in the figures and combinations of blocks in the flowcharts, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general-purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer (e.g., computer processor 26) or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowcharts and/or algorithms described in the present application. These computer program instructions may also be stored in a computer-readable medium (e.g., a non-transitory computer-readable medium) that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable medium produce an article of manufacture including instruction means which implement the function/act specified in the flowchart blocks and algorithms. The computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions/acts specified in the flowcharts and/or algorithms described in the present application.
Computer processor 26 is typically a hardware device programmed with computer program instructions to produce a special purpose computer. For example, when programmed to perform the algorithms described with reference to the figures, computer processor 26 typically acts as a special purpose patient-analysis computer processor. Typically, the operations described herein that are performed by computer processor 26 transform the physical state of a memory, which is a real physical article, to have a different magnetic polarity, electrical charge, or the like depending on the technology of the memory that is used. For some applications, operations that are described as being performed by a computer processor are performed by a plurality of computer processors in combination with each other.
It will be appreciated by persons skilled in the art that the invention is not limited to what has been particularly shown and described hereinabove. Rather, the scope of the invention includes both combinations and subcombinations of the various features described hereinabove, as well as variations and modifications thereof that are not in the prior art, which would occur to persons skilled in the art upon reading the foregoing description.
The present application claims priority from U.S. Provisional patent application 62/745,480 to Amir, filed Oct. 15, 2018, entitled “Apparatus and methods for generation of a medical summary,” which is incorporated herein by reference.
Filing Document | Filing Date | Country | Kind |
---|---|---|---|
PCT/IB2019/058214 | 9/27/2019 | WO | 00 |
Number | Date | Country | |
---|---|---|---|
62745480 | Oct 2018 | US |