This disclosure generally relates to systems including medical devices and, more particularly, to monitoring of patients during conception, gestation, labor, delivery, and post-partum using such systems.
Reproductive system checkups are periodically conducted during and/or before conception, gestational, delivery, and post-partum periods to evaluate the health and progress of a maternal patient and/or a fetal patient. During the checkup, a clinician may evaluate various physiological traits to assess fertility, conception, pregnancy, post-partum health, and other wellness aspects of the patient. Similarly, a patient may conduct self-evaluations to assess fertility, conception, pregnancy, post-partum health, and other wellness aspects. The indications observed may be generally tracked to assess, for example, ovulation, conception, maternal and/or fetal health during pregnancy, indications of delivery, post-partum conditions, and other health aspects related to the reproductive system of the patient. In some cases, the physiological traits of the patient are obtained and assessed using medical equipment located within a medical clinic, requiring a physical presence of the patient. In some cases, the physiological traits are obtained and assessed by the patient, placing a tracking and/or evaluation burden on the patient outside of a medical clinic setting.
In general, the disclosure describes a system configured to sense one or more physiological traits of a patient to monitor and/or assess a likelihood of obstetric conditions in the patient, such as an obstetric condition indicative of a fertility phase, pregnancy, labor, post-partum conditions, and other conditions related to the reproductive system of the patient. The system is configured to sense one or more of the physiological traits using one or more sensors implanted subcutaneously and/or positioned cutaneously on the skin, or other sensors accessible to the patient outside of a medical clinic environment. The system may use the one or more physiological traits sensed to define one or more patient attributes for the patient, such as a hormone level, heart rate, heart rate variability, blood pressure, respiration rate, temperature, oxygen saturation level, uterine contractions, fluid level or impedance, and/or other patient attributes. The system is configured to compare the one or more patient attributes to an attribute sign describing a threshold for the one or more patient attributes. The system is configured to generate an indication for output (e.g., issue a communication or alert) to the patient and/or a clinician based on the comparisons.
In examples, the system regularly or asynchronously communicates the one or more patient attributes to an output device of the maternal patient, interested participants (e.g., a co-parent), and/or a clinician, such that the maternal patient, interested participants (e.g., a co-parent), and/or the clinician may remain updated on the various attributes without requiring a physical presence within the medical clinic. Hence, the system may provide indications to the patient and/or a clinician when the physiological traits obtained indicate the patient may be experiencing a fertility phase (e.g., menses, a follicular phase, ovulation, a luteal phase), pregnant, in labor, or experiencing a concerning post-partum condition. The system may thus be configured to assess and indicate reproductive phases for the patient over a life-cycle from the fertility phase to the post-partum phase.
The system may include sensing circuitry operably connected to the one or more sensors. The sensing circuitry may be configured to communicate one or more output signals indicative of the physical traits sensed to processing circuitry operably connected to the sensing circuitry. The processing circuitry may define the one or more patient attributes using the one or more output signals. The processing circuitry issue the communication based on a comparison of one or more of the one or more patient attributes with one or more of the one or more attribute signs. The one or more attribute signs may describe a threshold for one or more of the one or more patient attributes.
The system provides for continuous monitoring (e.g., periodic, scheduled, or triggered without requiring human intervention, over a period of time that may be weeks, months, or years) using one or more sensors implanted in and/or wearable by the patient. Continuous monitoring may include periodic sensing at intervals of 0 to 1 seconds, 1 to 10 seconds, 1 to 5 minutes, 1 to 60 minutes, 1 to 12 hours, or 12 to 24 hours, as examples. Hence, the system may communicate sensed physiological traits and/or patient attributes more frequently and on a more consistent schedule than might otherwise be available when monitoring requires presence with a medical facility setting and/or a concerted action by the patient. Further, the sensed patient data and/or prior patient data may be provided to and/or evaluated by a clinician in a more expeditious and consistent manner. In examples, the system is configured to alter its operation based on prior patient data and/or an input received from a clinician IO device. For example, the system may increase or decrease a frequency at which a sensor or group of sensors senses a particular patient physical trait and/or one or more physiological traits sensed by the system, a scheduled basis for providing patient physiological data, one or more patient attributes used by the system, one or more attribute signs, and/or other operations. Thus, the system may update and/or adjust monitoring of a patient without a necessity for physical visitation to a medical facility and/or with a clinician.
The use of a patient attribute based on one or more physiological traits sensed from the patient may enhance the detection of obstetric conditions such as a fertility phase, pregnancy, labor, post-partum conditions, and others as the patient experiences the reproductive cycle. Typical monitoring of patients generally occurs by sensing and evaluating patient physiological traits often individually and/or largely within the setting of a medical facility. Example systems disclosed herein may monitor and define a patient attribute using a combination of physiological traits, and further compare the physiological trait to an attribute sign which considers the combined physiological traits. Example obstetric conditions which may be surveilled by systems according to this disclosure include preeclampsia, chronic hypertension, gestational hypertension, gestational diabetes, sepsis, cardiac arrhythmias, heart failure, pre-term labor, hemorrhage, arteriovenous fistula, stroke, and pre-partum or post-partum depression.
In examples, the system uses a machine learning algorithm to improve monitoring and/or indications provided to the patient and/or a clinician. The machine learning algorithm may assist in interpreting patient attributes to, for example, identify whether an obstetric condition (e.g., a fertility phase, pregnancy, labor, post-partum) may be present for the patient. For example, processing circuitry of the system may be configured to train the machine learning algorithm using prior patient data sensed for the patient, such that an attribute sign is based at least in part on physiological traits somewhat specific to the patient rather than, for example, based broadly on other metrics which may be relatively insensitive to the specific physiological traits of an individual patient. In examples, the system may incorporate prior patient data obtained by the system to evaluate and/or update attribute signs. Hence, the machine learning algorithm may allow the system to provide substantially personalized interpretations, evaluations, and/or communications specific to the individual physiological traits exhibited by the patient. Implementing such personalized approaches in the systems and techniques described herein realize an increase in accuracy for detecting true episodes, for instance, by detecting fewer false positives and overlooking fewer false negatives for obstetric conditions that may be present in the patient.
The system may improve identification and/or responsiveness to trends and/or indications which might emerge from physiological data collected from a population of users. The system may assist in defining a patient attribute and/or attribute sign, a schedule for sensing physiological traits, and/or other operations based on the population data. For example, the machine learning algorithm may define and/or refine an attribute sign using population data sensed from a population of other individual patients. The machine learning algorithm may be trained using a training data set including the population data. In examples, the system is configured to communicate with a plurality of individual medical devices worn, implanted within, and/or otherwise utilized by the population of other individual patients. The medical system may communicate with the plurality of individual medical devices to gather the population data. Hence, the machine learning algorithm may allow the system to more rapidly respond to the identification of and use of trends that might emerge as a result of monitoring a broad population of patients.
The techniques and systems of this disclosure may be implemented in a medical device such as an implantable medical device (IMD) that can continuously (e.g., on a periodic or triggered basis without human intervention) sense physiological traits while being worn or subcutaneously implanted in a patient over months or years, and perform numerous operations per second on patient data to enable the systems herein to detect potential obstetric conditions. Using techniques of this disclosure with a medical device such as an IMD may be advantageous when a physician cannot be continuously present with the patient over weeks or months to evaluate physiological traits sensed by the system, and/or where performing the operations of the system on the physiological traits (e.g., personalization of maternal and/or fetal limits, incorporation of trends identified from population data) on weeks or months of data gathered through physiological monitoring could not practically be performed in the mind of a physician.
In an example, a system comprises an implantable medical device and processing circuitry. The implantable medical device comprises one or more sensors configured to continuously sense one or more physiological characteristics of a body of a maternal patient, and sensing circuitry operably connected to the one or more sensors and configured to issue one or more output signals indicative of the one or more physiological characteristics. The processing circuitry is configured to define one or more patient attributes using the one or more output signals, and generate an output based on the one or more patient attributes, the output configured to cause a computing device to provide an indication of preeclampsia of the maternal patient to a user.
In another example a system comprises an implantable medical device and processing circuitry. The implantable medical device is configured to issue an output signal based on cardiac activity of a maternal patient continuously sensed by the implantable medical device. The processing circuitry is configured to define one or more heart rate variability metrics using the output signal, and generate an output based on a comparison of the one or more heart rate variability metrics to one or more thresholds, the output configured to cause a computing device to provide an indication of an obstetric condition of the maternal patient to a user.
In another example, an implantable medical device comprises communication circuitry configured for wireless communication with a computing device, a plurality of electrodes, sensing circuitry configured to measure impedances of a maternal patient via the plurality of electrodes, and processing circuitry configured to: compare the measured impedances to one or more thresholds; and generate an output for communication to the computing device via the communication circuitry based on the comparison, the output configured to cause the computing device to provide an indication of possible hemorrhage of the maternal patient to a user.
The details of one or more examples are set forth in the accompanying drawings and the description below. Other features, objects, and advantages will be apparent from the description and drawings, and from the claims.
In general, the disclosure describes a system configured to sense one or more physiological traits of a patient to monitor and/or assess a likelihood of obstetric conditions in the patient, such as a fertility phase (e.g., menses, a follicular phase, ovulation, and/or a luteal phase), pregnancy, labor, post-partum conditions, and other conditions related to the reproductive system of the patient. The system may use the physiological traits sensed to substantially monitor and track the health of the patient over the course of a conception, a pregnancy, and a post-partum phase when, for example, the patient is outside of a medical clinic setting. The system may provide indications to the patient and/or a clinician when the physiological traits obtained indicate the patient may be ovulating, pregnant, in labor, or experiencing a concerning condition. Example concerning conditions include hypertensive disorders associated pregnancy, e.g., preeclampsia, chronic hypertension, and gestational hypertension, pre-term labor, hemorrhage, arteriovenous fistula, stroke, gestational diabetes, sepsis, cardiac arrhythmias, heart failure, and pre-partum or post-partum depression. The system may thus be configured to assess and indicate reproductive phases and conditions during such phases for the patient over a life-cycle from the fertility phase to the post-partum phase.
The system may use the physiological traits sensed to monitor and track the health of the patient, as well as indicate when the patient is likely to be experiencing an obstetric condition indicative of a fertility phase, pregnancy, labor, or a post-partum condition. Hence, the system may be used by the patient and/or a clinician as an aid for interpreting when a pregnancy may be relatively likely or relatively unlikely, an aid for tracking the progress of a pregnancy, and/or an aid for indicating health of the patient, pre-partum, during pregnancy, and post-partum. The system uses the one or more physiological traits sensed from the patient to define one or more patient attributes, such as a hormone level, a muscle contraction, a temperature, a heart rate, heart rate variability, a blood pressure level (e.g., systolic and/or diastolic), an oxygen saturation level, a respiration rate, an activity level, a glucose level, a fluid level or impedance, and/or other patient attributes. In some examples, to sense the one or more physiological traits, the system may sense ECG signals, optical sensor signals, impedance sensor signals, accelerometer signals, and/or biochemical sensor signals, e.g., may include sensor hardware configured to produce such signals, the signals varying based on the physiological traits. The system is configured to provide communications to the patient and/or a clinician indicating, for example, whether the one or more patient attributes may indicate an obstetric condition of the patient, such as a fertility phase (e.g., menses, a follicular phase, ovulation, a luteal phase), a pregnancy (e.g., indications of a conception, a gestational condition during a pregnancy, and/or health conditions of the maternal or fetal patient), labor, or a post-partum condition.
In examples, during a pregnancy of the patient, the system is configured to use the sensed physiological traits to monitor and track the health of a fetal patient carried by the patient. As used herein, the one or more physiological traits of the patient may include one or more fetal physiological traits of the fetal patient. A fetal physiological trait may be some measurable phenomena generated by and/or resulting from an anatomical function of the fetal patient carried by the patient. The system may be configured to define one or more fetal attributes using one or more fetal physiological traits. The patient attribute, as used herein, may include one or more fetal attributes, and/or the attribute sign may include a threshold for the one or more fetal attributes. In some examples, the system may identify patient physiological traits and fetal physiological traits via blind source separation or wavelet methodologies. Techniques for identifying patient and fetal traits via blind source separation are described in U.S. Provisional Patent Application Ser. No. 63/498,965, filed Apr. 28, 2023, the entire content of which is incorporated herein by reference. Techniques for identifying patient and fetal traits via wavelet methodologies may include association of different components of the with respective ones of patient or fetal traits. Hence, the system may be configured to monitor patient for obstetric conditions which might impact the patient during a pre-conception or post-partum phase as well as obstetric conditions (e.g., gestational conditions during a pregnancy) which might impact the patient and/or a fetal patient during a pregnancy. The system may additionally be configured to monitor for fetal cardiac arrhythmias and/or fetal distress, e.g., a nuchal chord.
The system is configured to sense the one or more physiological traits using one or more sensors accessible to the patient outside of a medical clinic environment. For example, the one or more sensors may be mechanically supported by a wearable or implantable device. The system may define the one or more patient attributes and communicate information to the patient and/or a clinician, such that the patient and/or the clinician may remain updated without requiring a physical presence of the patient within the medical clinic, and/or without the requiring the patient to laboriously obtain and record the one or more patient attributes (e.g., during a self-evaluation). The system may issue a communication indicative of the one or more patient attributes to a patient input/output device (“patient IO device”), such as a mobile phone, a tablet, a smart speaker, smart home device, or other Internet of Things (IoT) device, or another IO device. The system may issue a communication indicative of the one or more patient attributes to a clinician input/output device (“clinician IO device”), such as a workstation or other IO device. The system may be configured to display the one or more patient attributes or a history of the one or more patient attributes to the patient and/or the clinician, such that the patient and/or clinician may be apprised of the likelihood or unlikelihood of a given obstetric condition for the patient.
Unlike some conventional monitoring and detection systems, the techniques and systems of this disclosure may use a machine learning algorithm to more accurately determine whether one or more sensed physiological traits and/or patient attributes indicate an obstetric condition of the patient. In some examples, the machine learning algorithm is trained with a set of training data comprised of and/or indicative of previously received patient physiological data and/or an assessment input of a clinician. Because the machine learning algorithm is trained with potentially thousands or millions of training instances (e.g., training input vectors), the machine learning algorithm may offer improved performance in the detection of obstetric conditions over a reproductive cycle when compared to conventional monitoring systems and/or techniques. For example, the system may more expeditiously and/or accurately detect indications of a fertility phase, pregnancy, labor, a post-partum phase, and/or other obstetric conditions which might arise over the reproductive cycle.
Additionally, the techniques and systems of this disclosure may be implemented in a medical device such as an IMD and/or wearable device that can continuously sense physiological traits of the patient without human intervention and perform millions of operations per second on physiological data to identify obstetric conditions with the machine learning algorithm. Using techniques of this disclosure with a medical device such as an IMD and/or wearable device may be advantageous when a physician cannot be continuously present with the patient over weeks or months to gather and evaluate physiological data and/or where performing millions of operations on weeks or months of physiological data could not practically be performed in the mind of a physician using the techniques of this disclosure (e.g. techniques employing a machine learning algorithm).
The one or more physiological traits (e.g., an electrocardiogram) sensed by the system may be indicative of the one or more patient attributes (e.g., a heart rate or heart rate variability). The one or more patient attributes may be indicative of one or more physiological characteristics of the body of the patient (e.g., cardiac activity). In examples, the system compares the one or more patient attributes indicated to an attribute sign indicative of an obstetric condition, such as an obstetric condition indicative of a fertility phase, a pregnancy, labor, or a post-partum condition of the patient. The system may be configured to issue the communication (e.g., to the patient IO device and/or clinician IO device) based on the comparison of the one or more patient attributes indicated with the attribute sign. In some examples, the system is configured to provide recommendations to the patient to take an action in response to the communication. For example, the system might recommend the patient contact a clinician and/or medical facility, go to labor and delivery triage at the hospital, stand and/or walk, and/or make other recommendations. In some examples, the system is configured such that the clinician may input the recommendations to the patient using the clinician IO device, and the system may communicate the recommendations from the clinician IO device to the patient IO device. In some examples, the system may be configured to enable communication between the patient and one or more other individual patients who may be subject to an obstetric condition indicative of a fertility phase, a pregnancy, labor, and/or a post-partum phase to, for example, foster communication between patients and/or enable creation and/or delivery of education materials to the patient and other individual patients.
The system may be configured to define and check the one or more patient attributes on a regular schedule (e.g., twice daily), on a schedule based on an assessed risk, on a substantially continuous basis, when prompted by the patient, clinician, and/or other user, or some combination thereof. For example, the system may increase a frequency at which one or more of the one or more patient attributes are monitored based on an increase in occurrences of a patient attribute exceeding a threshold defined by an attribute sign. The system may decrease a frequency at which one or more patient attributes are monitored based on a decrease in occurrences of a patient attribute falling outside thresholds defined by an attribute sign. In examples, the system is configured to define the patient attribute based on an indicated and/or assessed schedule of the patient. For example, the system may be configured to define the one or more patient attributes when the patient is in a resting condition (based on, e.g., a level of activity movement of the patient, a heart rate of the patient, a schedule provided by the patient, or some other indication). Such scheduling based on a schedule of the patient may improve the indications of the system due to, for example, consistency in the state of the patient (e.g., a resting state, basal state, and/or other state) when the one or more patient attributes are defined). In some examples, the system may be configured to communicate with the patient (e.g., using a patient IO device) to prompt the patient to facilitate sensing of additional physiological traits by the system (e.g., in response to a patient attribute). The system may be configured to prompt the patient to engage one or more additional sensors to facilitate the sensing of the additional physiological traits. For example, the system may communicate with the patient to prompt the patient to engage a percutaneous sensor such as a glucose sensor, a sensor supported by a wearable device, an external sensor such as a weight scale or blood pressure cuff, or some other sensor. The system may be configured to receive sensed outputs from the one or more additional sensors. In examples, the system may be configured to communicate with the patient (e.g., using the patient IO device) when such additional sensing may be discontinued.
The system may be configured to substantially assess the one or more patient attributes to determine if the one or more patient attributes are a normally expected value (e.g., within a normally expected range) or if the one or more patient attributes potentially indicate a condition of concern. The system may assess the one or more patient attributes through comparison with the attribute sign. The attribute sign may describe, for example, a maximum or minimum hormone level for an obstetric condition, a maximum or minimum temperature for an obstetric condition, a maximum or minimum heart rate or heart rate variability for an obstetric condition, a maximum or minimum blood pressure for an obstetric condition, a maximum or minimum oxygen saturation level for an obstetric condition, a maximum or minimum respiration rate or depth for an obstetric condition, a maximum or minimum impedance or fluid level (e.g., amniotic fluid, breast milk (e.g., indicative of lactation), interstitial or thoracic, blood, etc.) for an obstetric condition, and/or other limits based on a body function of the patient. In examples, a patient attribute and/or attribute sign is based on a plurality and/or combination of the one or more physiological traits sensed (e.g., an ECG and a temperature, or others), such that the system substantially assesses the plurality and/or combination of the one or more physiological traits sensed.
The one or more physiological traits sensed by the system may include any physiological trait sensible by the one or more sensors and influenced by a body function of the patient. For example, the one or more physiological traits may include an electrocardiogram (“ECG”), echocardiogram, electromyography (“EMG”), impedance magnitude, optical signal, a pressure magnitude, an accelerometry reading, an audible sound (e.g., a heart sound), a temperature, a biochemical signal, and/or any other physiological trait influenced by a body and/or body function of the patient. The patient attribute may be any measure or metric of anatomical function that may be inferred from the one or more physiological traits, such as a hormone level, a body temperature, a fluid level, a heart rate or heart rate variability, a blood pressure, an oxygen saturation level (e.g., an SpO2 and/or StO2), a respiration rate, an activity level, or some other anatomical function of the patient. In examples, the system may be configured to define the patient attribute using the one or more physiological traits sensed.
The patient attribute may be based on a combination of substantially different physiological traits indicative of substantially different physiological measures, such as heart rate and blood pressure, respiration rate and muscle contractions, and/or other combinations indicative of substantially different physiological measures. The patient attribute may be substantially based on any singular patient attribute and/or singular physiological trait, and/or may be substantially based on a combination of patient attributes and/or combination of physiological traits indicating a physiological state of the patient. For example, the patient attribute defined may be based substantially on an individual patient attribute, a plurality of patient attributes defined over a time frame, a trend of patient attributes, and/or some other characteristic of one or more patient attributes indicative of an obstetric condition of the patient. The patient attribute defined may be based substantially on an individual physiological trait, a plurality of physiological traits defined over a time frame, a trend of physiological traits, and/or some other characteristic of one or more physiological traits indicative of an obstetric condition of the patient. The patient attribute may be based on a combination of substantially different physiological traits indicative of substantially different physiological characteristics of the patient, such as a combination of an ECG and an optical signal to indicate a hormone level, a combination of an EMG and an accelerometry reading to indicate a uterine contraction, combinations of heart rate variability and one or more of impedance, heart sound metrics, respiration metrics, or blood pressure to indicate a hypertensive disorder of pregnancy, e.g., preeclampsia, and/or other combinations indicative of substantially different physiological measures to indicate a patient attribute of the patient.
In examples, the system is configured to adjust one or more of the obstetric parameters (e.g., one or more physiologic traits sensed, one or more patient attributes, and/or the one or more attribute signs) utilized based on a particular obstetric condition. For example, the system may assess that the patient is likely in an obstetric condition indicative of a fertility phase (e.g., menses, a follicular phase, ovulation, a luteal phase), pregnancy, labor, or a post-partum condition based on a comparison of the patient attribute and the attribute sign. The system may receive an input (e.g., from the clinician IO device and/or the patient IO device) indicating the patient is likely in an obstetric condition indicative of a fertility phase (e.g., menses, a follicular phase, ovulation, a luteal phase), pregnancy, labor, or a post-partum condition. The system may be configured to adjust the obstetric parameters sensed and/or utilized based on the assessment and/or input. For example, the system may be configured to use one or more sets of first obstetric parameters to assess whether the patient is ovulating. The system may be configured to use one or more second obstetric parameters once ovulation is assessed or otherwise indicated to detect, for example, a possible pregnancy. The system may be configured to use one or more third obstetric parameters once pregnancy is assessed or otherwise indicated to, for example, monitor the health of the patient and/or a fetal patient during the pregnancy. The system may be configured to use one or more fourth obstetric parameters once labor is assessed or otherwise indicated to, for example, monitor the health of the patient and/or a fetal patient during labor. The system may be configured to use one or more fifth obstetric parameters once a post-partum phase is assessed or otherwise indicated to, for example, monitor the patient for one or more post-partum conditions. Likewise, the system may be configured to adjust a schedule by which the obstetric parameters are obtained and/or assessed based on a particular obstetric condition. The system may be configured to direct the one or more sensors to sense the one or more physiological traits based on the obstetric condition. In examples, the system is configured to communicate with the patient (e.g., using a patient IO device) and/or a clinician (e.g., using a clinician IO device) when the system adjusts one or more of the obstetric parameters and/or assesses and obstetric condition. Hence, the system may be configured to assess and indicate reproductive phases for the patient over a life-cycle from the fertility phase to the post-partum phase.
In addition to issuing the communication based on the patient attribute and the attribute sign, the system may be configured to record and/or store the periodically sensed one or more physiological traits and patient attributes to enable a clinician and/or the patient to review a history over some portion of or substantially all of a time interval. The system may be configured to record and/or store the periodically sensed one or more physiological traits and patient attributes to provide the history. In examples, the system is configured to communicate the sensed one or more physiological traits and/or patient attributes on a scheduled basis (e.g., twice daily), such that the history remains substantially updated. The system may communicate the sensed one or more physiological traits and/or patient attributes to the external device to indicate the history to a clinician using the clinician IO device. The system may communicate the sensed one or more physiological traits and/or patient attributes to the patient IO device to indicate the history to the patient or another user. In some examples, the system is configured to communicate a first set of the one or more sensed physiological traits and/or patient attributes to the external device for review by a clinician and communicate a second set of the one or more sensed physiological traits and/or patient attributes to the patient IO device for review by the patient or other user. The first set communicated to the clinician IO device may be different from or substantially similar to the second set communicated to the patient IO device.
The system includes one or more sensors configured to sense the one or more physiological traits. The system may include sensing circuitry operably connected to the one or more sensors. The sensing circuitry may be configured to communicate one or more output signals indicative of the one or more physiological traits sensed to processing circuitry operably connected to the sensing circuitry. The processing circuitry may be configured to cause the one or more sensors and/or the sensing circuitry to communicate (e.g., periodically communicate) the one or more output signals. The processing circuitry may be configured to receive (e.g., periodically receive) the one or more output signals and define one or more patient attributes using the one or more output signals. In examples, the system includes a medical device mechanically supporting one or more of the sensors. The medical device may be, for example, an implantable medical device (“IMD”) or other medical device configured to remain with and/or accessible to the patient when the patient is in an ambulatory state (e.g., outside of a clinic setting). The medical device may mechanically support at least some portion of the sensing circuitry and/or the processing circuitry. In some examples, the medical device mechanically supports a first portion of the processing circuitry and/or sensing circuitry, and an external device separate from (e.g., displaced from) the medical device mechanically supports a second portion of the processing circuitry. The medical device may include communications circuitry configured to cause the first portion of the processing circuitry to communicate with the second portion of the processing circuitry to, for example, issue a communication indicative of an assessment of a patient attribute, record and/or store the periodically sensed physiological traits and/or patient attributes, and/or for other reasons.
In examples, the system is configured to sense a plurality of physiological traits using the one of more sensors. The system may be configured to define a plurality of patient attributes using the plurality of physiological traits. The attribute sign may be dependent on one or more of the plurality of patient attributes. For example, an attribute sign may be dependent on a single patient attribute (e.g., a body temperature indicative of, for example, ovulation, a fluid level indicative of lactation), and the system may issue the communication based on comparison of the single patient attribute defined and the singly-dependent attribute sign. An attribute sign may be dependent on a combination of patient attributes defined (e.g., patient heart rate and uterine muscle contractions indicative of, for example, false labor), and the system may issue the communication based on a comparison of the combination of multiple patient attributes defined and the multiply-dependent attribute sign. Hence, the system may be configured to monitor for the obstetric condition using one or more patient attributes sensed from the patient.
The system (e.g., the processing circuitry) may be configured to define and/or refine the attribute sign to reduce a rate of false positives when comparing the one or more patient attributes to the attribute sign. For example, the system may be configured to utilize the periodically sensed one or more physiological traits, patient parameters indicative of the one or more physiological traits, and/or patient attributes (also termed “patient physiological data”) to define and/or refine the attribute sign. In examples, the system (e.g., the processing circuitry) implements a machine learning algorithm trained with a training data set based on the patient physiological data. The machine learning algorithm may be configured to define and/or refine the attribute sign using the patient physiological data, such that the system may be substantially personalized to the patient.
In examples, the system is configured to receive an assessment input from a user input device (e.g., the patient IO device and/or the clinician IO device) indicative of an assessment of whether the system issued an appropriate communication (e.g., an appropriately tiered communication) when a set of patient physiological data was previously received. The training data set of the machine learning algorithm may be based on the previously received patient physiological data and/or the assessment input, such that the communications may be substantially tailored to the one or more physiological traits of the individual patient. The substantial tailoring to the individual patient may reduce a rate of false positives indicating necessary action communicated by the system.
In some examples, the system (e.g., the processing circuitry) may be configured to define and/or refine the attribute sign based on population data sensed from a population of other individual patients potentially subject to one or more of the obstetric conditions. The system (e.g., the processing circuitry) may include a machine learning algorithm configured to define and/or refine the attribute sign using the population data. In examples, the machine learning algorithm is trained using a training data set including the population data. The population data may include, for example, individual physiological traits sensed from the individual patients, individual patient parameters based on the individual physiological traits, and/or individual patient attributes defined for the individual patients. In examples, an external device of the system may be configured to communicate with a plurality of individual medical devices worn, implanted within, and/or otherwise utilized by the population of other individual patients. The medical system may communicate with the plurality of individual medical devices to gather the population data.
In examples, the medical system may be implemented using one or more computer programs implemented on programmable computers, such as computers that include, for example, processing capabilities, data storage (e.g., volatile, or nonvolatile memory and/or storage elements), input devices, and output devices. Program code and/or logic described herein may be applied to input data to perform the functionality described herein and generate desired output information. The programs may be stored on any suitable device, e.g., a storage media, readable by a general or special purpose program running on a computer system (e.g., including processing apparatus) and configuring the computer system to perform functions described herein. Computer-implemented instructions, data structures, screen displays, and other data under aspects of the technology may be stored or distributed on computer-readable storage media, including magnetically or optically readable computer disks, as microcode on semiconductor memory, nanotechnology memory, organic or optical memory, or other portable and/or non-transitory data storage media. In some embodiments, aspects of the technology may be distributed over the Internet or over other networks (e.g., a Bluetooth network) on a propagated signal on a propagation medium (e.g., an electromagnetic wave(s), a sound wave) over a period of time, or may be provided on any analog or digital network (packet switched, circuit switched, or other scheme).
In examples, medical system 100 is configured to determine and/or alter the obstetric parameters of patient 102 (e.g., a physiologic trait, the patient attribute, and/or the attribute sign) obtained and evaluated utilized based on a particular obstetric condition of patient 102. For example, the system may assess and/or receive an indication (e.g., from patient 102 and/or a clinician) that the patient is likely in an obstetric condition indicative of a fertility phase, pregnancy, labor, or a post-partum condition based on a comparison of one or more patient attributes and one or more attribute signs. The system may be configured to adjust the obstetric parameters sensed and/or utilized based on the assessment and/or input. For example, the system may be configured to use a one or more first obstetric parameters to monitor patient 102 for ovulation, one or more second obstetric parameters once ovulation is indicated, one or more third obstetric parameters once pregnancy is indicated, one or more fourth obstetric parameters once labor is indicated, and/or one or more fifth obstetric parameters once a post-partum phase is indicated. Likewise, medical system 100 may be configured to determine and/or alter the obstetric parameters based on an individual phase of an obstetric condition, such as an individual trimester of a pregnancy of another phase of an obstetric condition. Hence, the system may be configured to assess and indicate reproductive phases for the patient over a life-cycle from a fertility phase (e.g., menses, a follicular phase, ovulation, a luteal phase) to a post-partum phase.
Medical system 100 may be configured to monitor patient 102 for obstetric conditions which might occur over a reproductive lifecycle 101 of patient 102, such as illustrated in
Hence, medical system 100 may be configured to monitor patient 102 for obstetric conditions over substantially all or some portion of reproductive lifecycle 101. Medical system 100 may be configured to monitor patient 102 over time periods exceeding a typical extent of reproductive cycle 101 and/or between occurrences of some portion or all of reproductive cycle 101, such that medical system 100 may monitor patient 102 during at least a portion of the child-bearing years of patient 102. For example, medical system 100 may be configured to provide monitoring of patient 102 over multiple reproductive lifecycles, such as a first reproductive lifecycle including a first pregnancy and second reproductive lifecycle including a second pregnancy. Further, although reproductive cycle 101 is illustrated at
For example, medical system 100 may be configured to substantially monitor patient 102 for an obstetric condition associated with fertility phase 103 (e.g., a high or low likelihood of pregnancy) until the physiological traits of patient 102 indicate patient 102 may have entered a subsequent phase of reproduction cycle 101 (e.g., pregnancy 105). Medical system 100 may be configured to substantially monitor patient 102 for an obstetric condition associated with pregnancy phase 105 until labor 107 is indicated. Medical system 100 may be configured to substantially monitor patient 102 for an obstetric condition associated with labor 107 until post-partum phase 109 is indicated. Further, although reproductive cycle 101 is illustrated at
Medical system 100 may be configured to provide an indication to patient 102 that patient 102 may be experiencing a fertility phase 103, a pregnancy 105, labor 107, or a post-partum phase 109. Medical system 100 may thus be configured to assess and/or provide an indication that patient 102 may be more or less likely to conceive based on the physiological traits sensed, whether patient 102 may have experienced or be experiencing one of more prenatal conditions of concern, and/or whether patient 102 may have experienced or be experiencing one of more post-partum conditions of concern. In examples, medical system 100 may be configured to monitor patient 102 over time periods when a fertility phase 103, a pregnancy 105, labor 107, or a post-partum phase 109 is not occurring, such that medical system 100 may apprise patient 102 of when an obstetric condition is likely or unlikely to occur during a particular time period and/or particular point in time. In examples, medical system 100 is configured for use over one or more of life-cycles 101. Hence, the system may be configured to assess and indicate reproductive phases for patient 102 over a life-cycle from fertility phase 103 to post-partum phase 109, as well as assess and indicate to patient 102 whether that one or more of the obstetric conditions may be likely or unlikely.
Medical system 100 is configured to obtain and evaluate one or more of the obstetric parameters (e.g., one or more of the patient limit, the physiologic traits sensed, the patient attribute, and/or the attribute sign) utilized based on a particular obstetric condition. For example, the system may assess that the patient is likely in an obstetric condition indicative of a fertility phase, pregnancy, labor, or a post-partum condition based on a comparison of the patient attribute and the attribute sign. The system may receive an input (e.g., from the clinician IO device and/or the patient IO device) indicating the patient is likely in an obstetric condition indicative of a fertility phase, pregnancy, labor, or a post-partum condition. The system may be configured to adjust the obstetric parameters sensed and/or utilized based on the assessment and/or input. For example, the system may be configured to use one or more sets of first obstetric parameters to assess whether the patient is ovulating. The system may be configured to use one or more second obstetric parameters once ovulation is assessed or otherwise indicated to detect, for example, a possible pregnancy. The system may be configured to use one or more third obstetric parameters once pregnancy is assessed or otherwise indicated to, for example, monitor the health of the patient and/or a fetal patient during the pregnancy. The system may be configured to use one or more fourth obstetric parameters once labor is assessed or otherwise indicated to, for example, monitor the health of the patient and/or a fetal patient during labor. The system may be configured to use one or more fifth obstetric parameters once a post-partum phase is assessed or otherwise indicated to, for example, monitor the patient for one or more post-partum conditions. Likewise, the system may be configured to adjust a schedule by which the obstetric parameters are obtained and/or assessed based on a particular obstetric condition. Hence, the system may be configured to assess and indicate reproductive phases for the patient over a life-cycle from the fertility phase to the post-partum phase.
One or more sensors 110 are configured to sense one or more physiological traits of patient 102. Sensors 110 may include one or more of an optical sensor, an impedance sensor, an accelerometer, or a biochemical sensor. A physiological trait may be some measurable phenomena generated by the body of patient 102 and indicative of one or more patient attributes of patient 102. For example, the physiological trait may be an electrocardiogram (“ECG”), echocardiogram, electromyography, impedance magnitude, optical signal, a body temperature, a pressure magnitude, an accelerometry reading, an audible sound, an impedance, a biochemical signal, and/or any other physiological trait influenced by a body of patient and fetus 102. Sensing circuitry 112 is configured to provide one or more output signals indicative of the one or more physiological traits to processing circuitry 114.
Processing circuitry 114 is configured to define one or more patient attributes of patient 102 using the one or more output signals. A patient attribute may be any measure of anatomical function that may be inferred from the one or more physiological traits, such as a hormone level of patient 102, a body temperature of patient 102, a heart rate of patient 102, a blood pressure of patient 102, an oxygen saturation level of patient 102, a respiration rate of patient 102, a fluid level of patient 102, an activity level of patient 102, or some other anatomical function of patient 102. In some examples, a patient attribute may be substantially based on a single physiological trait (e.g., a heart rate based on an ECG, a body temperature based on a temperature measurement, and/or other patient attributes based substantially on a single physiological trait). In some examples, a patient attribute may be based on a plurality of physiological traits (e.g., a hormone level based on two or more of an ECG, an oxygen saturation, an optical signal, a biochemical signal, and/or another physiological trait, a uterine contraction based on two or more of an electromyography, an accelerometry reading and/or another physiological trait, and/or other patient attributes based substantially on two or more physiological traits).
In examples, medical device 108 is configured to position relative to patient 102 such that sensor 110 may sense the physiological trait. Medical device 108 may be, for example, an implantable device configured to be implanted within patient 102 to position sensor(s) 110. Medical device 108 may be a device configured to substantially non-invasively contact a body of patient 102 to position sensor(s) 110 (e.g., smartwatch and/or other smart apparel). Medical device 108 may be a device configured to position sensor(s) 110 through a manipulation by and/or action of patient 102 (e.g., a weight scale, a blood pressure cuff, a urine sampling device, and/or a glucose testing device). Although described primarily in the context of examples in which medical device 108 takes the form of a device configured to be implanted within patient 102, the techniques of this disclosure may be implemented in systems including any one or more implantable or external devices configured to position sensor 110 such that sensor 110 may sense a physiological trait of patient 102.
In some examples, medical device 108 may be an insertable cardiac monitor or loop recorder, such as that disclosed in U.S. Pat. No. 10,413,207, incorporated herein by reference in its entirety. In some examples, medical device 108 may be implanted subcutaneously, e.g., entirely implanted subcutaneously. In some examples, medical device 108 may be implanted at a location near a heart, abdomen, placenta, uterus, or cranium of patient 102. In some examples, medical device 108 may be implanted in a lateral abdominal or inframammary region of patient 102. In some examples, system 100 may include multiple medical devices at respective ones of or any combination of such locations.
Sensing circuitry 112 is configured to communicate (e.g., via link 113) one or more output signals to processing circuitry 114 indicative of the physiological trait sensed by sensor 110. Processing circuitry 114 is configured to define the patient attribute of patient 102 using the one or more output signals. For example, processing circuitry 114 may be configured to define a patient attribute such as a hormone level, a temperature, a heart rate, a systolic blood pressure, a diastolic blood pressure, an oxygen saturation (e.g., an SpO2 indicative of blood oxygen saturation and/or an StO2 indicative of tissue oxygen saturation), a respiration rate, a fluid level (e.g., amniotic fluid, breastmilk, or other fluid), a blood glucose level, a body weight, a muscle contraction, an activity level, and/or other patient attribute of patient 102 using the one or more output signals. Processing circuitry 114 is configured to issue a communication to patient IO device 118, external device 116, and/or clinician IO device 120 indicative of the patient attribute, such that the patient 102 and/or the clinician may remain apprised of the likelihood or unlikelihood of a given obstetric condition for patient 102.
In examples, processing circuitry 114 is configured to communicate at least some portion of the patient physiological data sensed and/or defined (e.g., the physiological trait, a patient parameter indicative of the physiological trait, and/or the patient attribute) to patient IO device 118, external device 116, and/or clinician IO device 120. In some examples, processing circuitry 114 is configured to communicate a first portion of the patient physiological data to patient IO device 118 and a second portion of the patient physiological data to external device 116 such that, for example, patient IO device 118 displays information useful to patient 102 while external device 116 causes the display of additional and/or different information which might be useful to a clinician.
In examples, patient IO device 118, external device 116, and/or clinician IO device 120 may take the form of personal computing devices of patient 102 and/or a clinician, such as a smartphone, smartwatch, or other smart apparel of patient 102 or the clinician. Patient IO device 118, external device 116, and/or clinician IO device 120 may be any computing device configured for wireless communication with processing circuitry 114, such as a desktop, laptop, or tablet computer, a smart home controller, alarm, thermostat, speaker, or other smart appliance, or any Internet of Things (IoT) device. Patient IO device 118, external device 116, and/or clinician IO device 120 may be configured to communicate with processing circuitry 114 and each other according to the Bluetooth® or Bluetooth® Low Energy (BLE and/or BTLE) protocols, as examples. In some examples, the processing circuitry 114 may be configured to enable communication between patient IO device 118 and one or more other individual patient IO devices (e.g., patient IO devices of individual patients 148, 150, 156). This may foster communication between patient 102 and individual patients 148, 150, 156 to, for example, enable and/or assist in the creation and/or delivery of education materials to patient 102 and/or individual patients 148. 150, 156.
Processing circuitry 114 is configured to compare the patient attribute to an attribute sign to substantially monitor patient 102. The attribute sign may define, for example, a maximum or minimum hormone level, a maximum or minimum body temperature, a maximum or minimum heart rate, a maximum or minimum systolic blood pressure, a maximum or minimum diastolic blood pressure, a maximum or minimum oxygen saturation level, a maximum or minimum respiration rate, a maximum or minimum body weight, a maximum or minimum blood glucose level, a maximum or minimum activity level, a maximum or minimum amniotic fluid level, and/or some other defined attribute sign. Processing circuitry 114 may be configured to issue the communication to patient IO device 118 (e.g., via link 119), external device 116 (e.g., via link 117), and/or clinician IO device 120 (e.g., via link 121 or another communication link) based on the comparison. Processing circuitry 114 may be configured to cause patient IO device 118, external device 116, and/or clinician IO device 120 to provide an output sensible (e.g., able to be sensed) by the prenatal patient, a clinician, or another user when processing circuitry 114 issues the communication. For example, the sensible output may include a visual output, audio output, haptic output, or some other output which may be sensed by one or more of the senses of a human being.
In examples, processing circuitry 114 may be configured to issue the communication using a tiered communication indicative of an assessment of the comparison. The tiered communication system may provide for earlier and/or more accurate notifications to the maternal patient and/or a clinician regarding the likelihood or unlikelihood of a given obstetric condition for the patient. The tiered communication system may provide an indication that a fertility phase, pregnancy, labor, and/or a post-partum condition is unlikely, somewhat likely, and/or very likely to have occurred or be occurring based on the comparison of a patient attribute and an attribute sign. For example, when patient 102 is assessed as pregnant, the tiered communication system may serve as an indication that preeclampsia, chronic hypertension, gestational hypertension, sepsis, heart failure, cardiac arrhythmias, gestational diabetes, hemorrhage, and/or other conditions potentially placing the patient 102 and/or a carried fetal patient at risk may have occurred or could potentially occur.
Processing circuitry 114 may be configured to define a tier of a communication based on a plurality of attribute signs (e.g., a first attribute sign, a second attribute sign, and/or a third attribute sign) defined for patient 102. For example, processing circuitry 114 may be configured to issue a Tier I communication when the patient attribute is assessed to be a normally expected value (e.g., within a range defined by the first attribute sign). Processing circuitry 114 may be configured to issue a Tier II communication when the patient attribute is assessed to potentially indicate a condition warranting further evaluation and/or action by patient 102 and/or a clinician (e.g., within a range defined by the second attribute sign.) Processing circuitry 114 may be configured to issue a Tier III communication when the patient attribute is assessed to indicate a condition potentially more serious and/or warranting more urgent action and/or action by patient 102 and/or a clinician (e.g., within a range defined by the third attribute sign). The tiered communication system may define any number of tiers and any number of attribute signs. In some examples, processing circuitry 114 may be configured to cause patient IO device 118 and/or clinician IO device 120 to provide visible, audible, or other indicia associated with a tier of the communication. For example, processing circuitry 114 may be configured to cause patient IO device 118 and/or clinician IO device 120 to provide a first indicia (e.g., a green background) for a Tier I communication, a second indicia (e.g., a yellow background) for a Tier II communication, and/or a third indicia (e.g., a red background) for a Tier III communication.
In addition to or instead of issuing the communications, processing circuitry 114 may be configured to record and/or store the patient physiological data periodically sensed to enable a clinician and/or patient 102 to review a history over some portion of or substantially the entirety of a time interval. For example, processing circuitry 114 may be configured to communicate the patient physiological data from medical device 108 to external device 116, clinician IO device 120, and/or patient IO device 118. Processing circuitry 114 may be configured to communicate the patient physiological data on a scheduled basis (e.g., twice daily, or on some other schedule), such that the history remains substantially updated. In examples, processing circuitry 114 is configured to alter the operation of medical system 100 based on an input received from clinician IO device 120, based on one or more tiered communications, and/or for other reasons. For example, processing circuitry 114 may cause medical system 100 to increase or decrease a frequency at which sensor 110 senses a particular patient physical trait based on a received input from clinician IO device 120, based on one or more tiered communications, and/or for other reasons. Processing circuitry 114 may cause medical system 100 to alter and/or adjust the one or more physiological traits sensed by medical device 108 based on a received input from clinician IO device 120, based on one or more tiered communications, and/or for other reasons. Processing circuitry 114 may cause medical system 100 to alter and/or adjust the scheduled basis by which processing circuitry 114 provides the patient physiological data to external device 116 based on a received input from clinician IO device 120, based on one or more tiered communications, and/or for other reasons. Processing circuitry 114 may cause medical system 100 to alter and/or adjust one or more attribute signs used by processing circuitry 114 based on a received input from clinician IO device 120, based on one or more tiered communications, and/or for other reasons. In examples, processing circuitry 114 is configured to communicate with patient IO device 118 and/or a clinician IO device 120 when the processing circuitry 114 adjusts and/or alters the patient physiological data sensed, and/or assesses that one or more obstetric conditions indicative of a fertility phase, a pregnancy, labor, and/or a post-partum condition has been or may be experienced by patient 102.
In some examples, medical system 100 includes a plurality of sensors. The plurality of sensors may be configured to sense a physiological trait of patient 102. For example, medical system 100 may include a second medical device 122 including one or more sensors 124 and/or sensing circuitry 126. Sensing circuitry 126 may be configured to communicate (e.g., via link 127) one or more output signals to processing circuitry 114 indicative of a physiological trait sensed by sensor 124. For example, medical device 108 may be configured to primarily sense a first physiological trait using sensor 110 and a second physiological trait using sensor 124. Medical system 100 may be configured to define a first patient attribute using the first physiological trait and define a second patient attribute using the second physiological trait. In some examples, processing circuitry may be configured to define the patient attribute using either or both of the first physiological trait and the second physiological trait. Second medical device 122 may mechanically support at least some portion of processing circuitry 114. Second medical device 122, sensor 124, and/or sensing circuitry 126 may be configured similar to medical device 108, sensor 124, and/or sensing circuitry 112 respectively. In some examples, second medical device 122 (e.g., a housing of medical device 122) is configured to contact the body of patient 102 at an anatomical location different from the location of medical device 108 (e.g., a housing of medical device 108) to, for example, more effectively sense the first physiological trait and/or the second physiological trait, and/or for some other reason. In examples, processing circuitry 114 may be configured to communicate with patient 102 (e.g., using patient IO device 118) to prompt patient 102 to facilitate sensing of additional physiological traits. Processing circuitry 114 may be configured to prompt patient 102 to engage one or more additional sensors to facilitate the sensing of the additional physiological traits. For example, processing circuitry 114 may be configured to prompt the patient to engage a percutaneous sensor such as a glucose sensor, a sensor supported by a wearable device, an external sensor such as a weight scale, or some other sensor. Processing circuitry 114 may be configured to receive sensed outputs from the one or more additional sensors. In examples, the processing circuitry 114 may be configured to communicate with patient 102 (e.g., using patient IO device 118) when the additional physiological traits have been sufficiently sensed (e.g., such that the additional sensing may be discontinued). In some examples, medical device 122 may be an insertable cardiac monitor or loop recorder, such as that disclosed in U.S. Pat. No. 10,413,207, incorporated herein by reference in its entirety.
In some examples, medical system 100 (e.g., one or more of electrodes, an optical sensor, an accelerometer, a sound sensor, a temperature sensor, pressure sensor, a biochemical sensor, and/or another of sensor 110, 124) is configured to sense a signal indicative of a hormone level within patient 102. Processing circuitry 114 may be configured to define a patient attribute indicative of a hormone level of patient 102 using the one or more output signals provided by sensing circuitry 112, 126. For examples, processing circuitry 114 may be configured to define the patient attribute indicative of a hormone level using one or more sensors including a sensor configured to detect a physiological trait indicative of a heart rate of patient 102 (e.g., an ECG). Processing circuitry 114 may be configured to define the patient attribute indicative of a hormone level using, for example, a heart rate variability and/or other parameters defined using the heart rate. Processing circuitry 114 may define the patient attribute indicative of a hormone level using additional sensors and/or output signals, such as a urine sampling device, a weight scale, a blood pressure cuff, a temperature sensor, and/or other sensors and/or output signals indicative of a hormone level of patient 102. In examples, the patient attribute indicative of the hormone level (and/or any patient attribute) may be based on a plurality of signals indicative of the hormone level received over a period of time (e.g., a statistical parameter, a trend, or other attributes based on the plurality). Processing circuitry 114 may compare the patient attribute to an attribute sign indicative of a maximum hormone level of patient 102 for an obstetric condition, a minimum hormone level of patient 102 for an obstetric condition, and/or another attribute sign defined using the hormone level singly or in combination with other physiological traits. In some examples, processing circuitry 114 may use the hormone level sensed (e.g., as indicated by the one or more output signals) to define a patient attribute combining the hormone level and another physiological trait sensed by medical system 100. Processing circuitry 114 may issue a communication to patient IO device 118, external device 116, and/or clinician IO device 120 based on the comparison of the patient attribute and the attribute sign.
For example, processing circuitry 114 may compare a hormone level of patient 102 to a maximum hormone level for Luteinizing hormone, Follicle-stimulating hormone, Human chorionic gonadotropin hormone, estrogen, progesterone, or a maximum hormone level for another hormone indicative of an obstetric condition. Processing circuitry 114 may compare a hormone level of patient 102 to a minimum hormone level for Luteinizing hormone, Follicle-stimulating hormone, Human chorionic gonadotropin hormone, estrogen, progesterone, or a minimum hormone level for another hormone indicative of an obstetric condition. Processing circuitry 114 may issue a tiered communication based on the maximum hormone level, the minimum hormone level, another attribute sign, and/or determined deviations therefrom.
In examples, processing circuitry 114 is configured to monitor patient 102 for an obstetric condition associated with one or more of a fertility phase, pregnancy, labor, and/or a post-partum phase using the patient attribute indicative of a hormone level. The patient attribute may be defined using the signal indicative of the hormone level, e.g., a biochemical signal, singly or in combination with other patient attributes and/or physiological characteristics, such as a body temperature (e.g., basal body temperature), an impedance value, a weight measure (e.g., a body mass index (BMI)), a blood sample, and/or others. In examples, processing circuitry 114 is configured to assess that patient 102 is likely to be experiencing ovulation based on a patient attribute defined using a hormone level of Luteinizing hormone. Processing circuitry 114 may be configured to assess that patient 102 may have a high likelihood of becoming pregnant (e.g., peak fertility) based on the assessment of ovulation. For example, processing circuitry 114 may be configured to assess a high likelihood of pregnancy based on a period of time (e.g., 1 or more days) since ovulation was assessed. In some examples, processing circuitry 114 may be configured to determine a patient attribute using a hormone level, a temperature, and/or an impedance to assess a likelihood that the patient is pregnant.
Processing circuitry 114 may be configured to communicate an indication of peak fertility to patient 102 (e.g., using patient IO device 118). In examples, processing circuitry 114 may be configured to estimate a time period when ovulation might be expected for patient 102 using the patient attribute indicative of a hormone level (e.g., based on a trend of the patient attribute), and use the estimated ovulation time period to inform patient 102 (e.g., using patient IO device 118) when a peak fertility period is likely to occur (e.g., inform patient 102 prior to an assessment of ovulation by patient 102). In some examples, processing circuitry may be configured to assess a risk of miscarriage using the patient attribute indicative of a hormone level. For example, Processing circuitry 114 may be configured to determine a patient attribute defined using a hormone level of progesterone (PdG) singly or in combination with other patient attributes and/or physiological characteristics to assess the risk of miscarriage. (e.g., based on a low PdG level).
In some examples, medical system 100 (e.g., an electrode of sensor 110, 124) is configured to sense a signal indicative of an ECG of patient 102. Processing circuitry 114 may be configured to define a patient attribute (e.g., a heart rate and/or another patient attribute defined using the ECG) of patient 102 using the one or more output signals provided by sensing circuitry 112, 126. Processing circuitry 114 may compare the patient attribute to an attribute sign indicative of, for example, a maximum heart rate of patient 102 for an obstetric condition, a minimum heart rate of patient 102 for an obstetric condition, and/or another attribute sign defined using one or more output signals indicative of the ECG singly or in combination with other physiological traits. In some examples, processing circuitry 114 may use the ECG sensed (e.g., as indicated by the one or more output signals) to define a patient attribute combining the ECG sensed and another physiological trait sensed by medical system 100. Processing circuitry 114 may issue a communication to patient IO device 118, external device 116, and/or clinician IO device 120 based on the comparison of the patient attribute and the attribute sign.
For example, processing circuitry 114 may compare the heart rate of patient 102 to a maximum heart rate (e.g., 100 beats/minute (bpm) or another maximum heart rate) for an obstetric condition and/or a minimum heart rate (e.g., 60 bpm or another minimum heart rate) for an obstetric condition. Processing circuitry 114 may issue a tiered communication based on the maximum heart rate, the minimum heart rate, another attribute sign, and/or determined deviations therefrom.
In some examples, medical system 100 (e.g., an optical sensor of sensors 110, 124) is configured to sense a signal indicative of a blood pressure of patient 102. Processing circuitry 114 may be configured to define a patient attribute indicative of a systolic pressure and/or diastolic pressure of patient 102 using the one or more output signals provided by sensing circuitry 112, 126. Processing circuitry 114 may compare the patient attribute to an attribute sign indicative of, for example, a maximum systolic pressure of patient 102 for an obstetric condition, a minimum systolic pressure of patient 102 for an obstetric condition, a maximum diastolic pressure of patient 102 for an obstetric condition, a minimum diastolic pressure of patient 102 for an obstetric condition, and/or another attribute sign defined using the blood pressure singly or in combination with other physiological traits. In some examples, processing circuitry 114 may use the blood pressure sensed (e.g., as indicated by the one or more output signals) to define a patient attribute combining the blood pressure sensed and another physiological trait sensed by medical system 100. In examples, the patient attribute indicative of the blood pressure (and/or any patient attribute) may be based on a plurality of signals indicative of the blood pressure received over a period of time (e.g., a statistical parameter, a trend, or other attributes based on the plurality). Processing circuitry 114 may issue a communication to patient IO device 118, external device 116, and/or clinician IO device 120 based on the comparison of the patient attribute and the attribute sign.
For example, processing circuitry 114 may compare the systolic pressure of patient 102 to a maximum systolic pressure (e.g., 130 mmHg or another maximum systolic pressure) for an obstetric condition and/or a minimum systolic pressure (e.g., 100 mmHg or another minimum systolic pressure) for an obstetric condition. Processing circuitry 114 may compare the diastolic pressure of patient 102 to a maximum diastolic pressure (e.g., 80 mmHg or another maximum diastolic pressure) for an obstetric condition and/or a minimum diastolic pressure (e.g., 60 mmHg or another minimum diastolic pressure) for an obstetric condition. Processing circuitry 114 may issue a tiered communication based on the maximum systolic pressure, minimum systolic pressure, maximum diastolic pressure, minimum diastolic pressure, another attribute sign, and/or determined deviations therefrom. Example techniques for determining values indicative of patient blood pressure based on optical signals are described in U.S. Provisional Application Ser. No. 63/498,903, filed on Apr. 28, 2023 and titled “A MEDICAL SYSTEM CONFIGURED TO DETERMINE HEALTH CONDITION STATUS BASED ON BLOOD PRESSURE CHANGES DETECTED BY IMPLANTABLE OPTICAL SENSOR,” the entire content of which is incorporated herein by reference. In some examples, other implantable or external sensors may additionally or alternatively be used to determine patient blood pressure metrics.
In some examples, medical system 100 (e.g., an optical sensor of sensor 110, 124) is configured to sense a signal indicative of an oxygen saturation of patient 102. Processing circuitry 114 may be configured to define a patient attribute indicative of an oxygen saturation level of patient 102 using the one or more output signals provided by sensing circuitry 112, 126. Processing circuitry 114 may compare the patient attribute to an attribute sign indicative of a maximum oxygen saturation level of patient 102 for an obstetric condition, a minimum oxygen saturation level of patient 102 for an obstetric condition, and/or another attribute sign defined using the oxygen saturation singly or in combination with other physiological traits. In some examples, processing circuitry 114 may use the oxygen saturation level sensed (e.g., as indicated by the one or more output signals) to define a patient attribute combining the oxygen saturation level and another physiological trait sensed by medical system 100. Processing circuitry 114 may issue a communication to patient IO device 118, external device 116, and/or clinician IO device 120 based on the comparison of the patient attribute and the attribute sign.
For example, processing circuitry 114 may compare the oxygen saturation of patient 102 to a maximum oxygen saturation (e.g., 100%) for an obstetric condition and/or a minimum oxygen saturation (e.g., 95%) for an obstetric condition. Processing circuitry 114 may issue a tiered communication based on the maximum oxygen saturation, the minimum oxygen saturation, and/or determined deviations therefrom.
In some examples, medical system 100 (e.g., an accelerometer and/or an electrode of sensor 110, 124) is configured to sense a signal indicative of a respiration of patient 102. Processing circuitry 114 may be configured to define a patient attribute indicative of a respiration rate or depth of patient 102 using the one or more output signals provided by sensing circuitry 112, 126. Processing circuitry 114 may compare the patient attribute to an attribute sign indicative of a maximum respiration rate or depth of patient 102 for an obstetric condition, a minimum respiration rate or depth of patient 102 for an obstetric condition, and/or another attribute sign defined using the respiration rate or depth singly or in combination with other physiological traits. In some examples, processing circuitry 114 may use the respiration rate sensed (e.g., as indicated by the one or more output signals) to define a patient attribute combining the respiration rate and another physiological trait sensed by medical system 100. Processing circuitry 114 may issue a communication to patient IO device 118, external device 116, and/or clinician IO device 120 based on the comparison of the patient attribute and the attribute sign.
For example, processing circuitry 114 may compare the respiration rate of patient 102 to a maximum respiration rate (e.g., 16 breaths per minute (bpm)) and/or a minimum respiration rate (e.g., 12 bpm). Processing circuitry 114 may compare the respiration rate of fetal patient 104 to a maximum respiration rate (e.g., 70 bpm) and/or a minimum respiration rate (e.g., 30 bpm). Processing circuitry 114 may issue a tiered communication based on the maximum respiration rate, the minimum respiration rate, and/or determined deviations therefrom.
In some examples, medical system 100 (e.g., a resistive network and/or an optical sensor of sensor 110, 124) is configured to sense a signal indicative of a temperature of patient 102. Processing circuitry 114 may be configured to define a patient attribute indicative of a body temperature of patient 102 using the one or more output signals provided by sensing circuitry 112, 126. Processing circuitry 114 may compare the patient attribute to an attribute sign indicative of a maximum body temperature of patient 102 for an obstetric condition, a minimum body temperature of patient 102 for an obstetric condition, and/or another attribute sign defined using the body temperature singly or in combination with other physiological traits. In some examples, processing circuitry 114 may use the body temperature sensed (e.g., as indicated by the one or more output signals) to define a patient attribute combining the body temperature and another physiological trait sensed by medical system 100. Processing circuitry 114 may issue a communication to patient IO device 118, external device 116, and/or clinician IO device 120 based on the comparison of the patient attribute and the attribute sign.
For example, processing circuitry 114 may compare the temperature of patient 102 to a maximum temperature (e.g., 99.3 degrees F.) and/or a minimum temperature (e.g., 97.9 degrees F.). Processing circuitry 114 may compare the temperature of fetal patient 104 (e.g., a temperature of patient 102+1 degree F.) to a maximum temperature and/or a minimum temperature. Processing circuitry 114 may issue a tiered communication based on the maximum temperature, the minimum temperature, and/or determined deviations therefrom.
In examples, processing circuitry 114 is configured to monitor patient 102 for an obstetric condition associated with one or more of a fertility phase, pregnancy, labor, and/or a post-partum phase using the patient attribute indicative of a body temperature (e.g., a basal body temperature) of patient 102. For example, processing circuitry 114 may be configured to assess than patient 102 is likely to be experiencing ovulation based on a patient attribute defined using the body temperature of patient 102. The patient attribute may be defined using the signal indicative of the temperature singly or in combination with other patient attributes and/or physiological characteristics, such as a weight measure (e.g., a body mass index (BMI)), a fluid level (e.g., a level of cervical mucus), and/or others. For example, processing circuitry 114 may be configured to assess a body temperature of patient 102 during a time period (e.g., over a menstrual cycle, over a fertility phase, or substantially over a reproductive cycle) to establish a temperature history of patient 102. Processing circuitry 114 may be configured to assess patient 102 as potentially ovulating based on an increase in body temperature above that expected based on the temperature history. In examples, processing circuitry 114 is configured to sense the body temperature when patient 102 is in a resting state (e.g., based on sensed motion of patient 102 or other indicators), such that the body temperature is representative of a basal body temperature. Processing circuitry 114 may be configured to assess that patient 102 may have a high likelihood of pregnancy (e.g., peak fertility) based on the assessment of ovulation.
In some examples, medical system 100 (e.g., an electrode of sensor 110, 124) is configured to sense a signal indicative of an electromyography signal of patient 102, an electrohysterography signal of patient 102, or another signal indicative of a muscle contraction (e.g., a uterine muscle contraction) of patient 102. Processing circuitry 114 may be configured to define a patient attribute indicative of a muscle contraction of patient 102 using the one or more output signals provided by sensing circuitry 112, 126. Processing circuitry 114 may compare the patient attribute to an attribute sign indicative of a maximum muscle contraction of patient 102 for an obstetric condition, a minimum muscle contraction of patient 102 for an obstetric condition, and/or another attribute sign defined using the muscle contraction singly or in combination with other physiological traits. In some examples, processing circuitry 114 may use the muscle contraction sensed (e.g., as indicated by the one or more output signals) to define a patient attribute combining the muscle contraction and another physiological trait sensed by medical system 100. Processing circuitry 114 may issue a communication to patient IO device 118, external device 116, and/or clinician IO device 120 based on the comparison of the patient attribute and the attribute sign.
In examples, processing circuitry 114 is configured to monitor patient 102 for an obstetric condition associated with one or more of a fertility phase, pregnancy, labor, and/or a post-partum phase using the patient attribute indicative of a muscle contraction (e.g., a uterine muscle contraction) of patient 102. The patient attribute indicative of the muscle contraction may be defined using the signal indicative of the muscle contraction singly or in combination with other patient attributes and/or physiological characteristics, such as a heart rate, a blood pressure, and/or others. In examples, the patient attribute is indicative of a repetition of the sensed muscle contraction (e.g., a pattern of muscle contractions versus time). Processing circuitry 114 may compare the patient attribute to an attribute sign indicative of a maternal labor experienced by patient 102 or a false labor experienced by patient 102. Processing circuitry 114 may issue a communication to patient IO device 118, external device 116, and/or clinician IO device 120 based on the comparison of the patient attribute and the attribute sign.
In some examples, medical system 100 (e.g., a glucose sensor of sensor 110, 124, and/or an electrode (e.g., an electrooxidizing anode) of sensor 110, 124) is configured to sense a glucose signal of patient 102, a signal indicative of a glucose level of patient 102 (e.g., an ECG), or another signal indicative of a glucose level of patient 102 (e.g., an optical signal). Processing circuitry 114 may be configured to define a patient attribute indicative of a glucose level of patient 102 using the one or more output signals provided by sensing circuitry 112, 126. Processing circuitry 114 may compare the patient attribute to an attribute sign indicative of a maximum glucose level of patient 102 for an obstetric condition, a minimum glucose level of patient 102 for an obstetric condition, and/or another attribute sign defined using the glucose level singly or in combination with other physiological traits. In some examples, processing circuitry 114 may use the glucose level sensed (e.g., as indicated by the one or more output signals) to define a patient attribute combining the glucose level and another physiological trait sensed by medical system 100. For example, processing circuitry 114 may compare the patient attribute to an attribute sign indicative of a maximum glucose level potentially indicating gestational diabetes when patient 102 is carrying fetal patient 104. In examples, the patient attribute indicative of the glucose level (and/or any patient attribute) may be based on a plurality of signals indicative of the glucose level received over a period of time (e.g., a statistical parameter, a trend, or other attributes based on the plurality). Processing circuitry 114 may issue a communication to patient IO device 118, external device 116, and/or clinician IO device 120 based on the comparison of the patient attribute and the attribute sign.
In some examples, medical system 100 (e.g., an electrode of sensor 110, 124) is configured to sense an impedance or another signal indicative of a fluid (e.g., amniotic fluid, breast milk (e.g., indicative of lactation), cervical mucus (e.g., indicative of ovulation)), interstitial or thoracic fluid, or blood) in patient 102. Processing circuitry 114 may be configured to define a patient attribute indicative of a fluid level of patient 102 using the one or more output signals provided by sensing circuitry 112, 126. Processing circuitry 114 may compare the patient attribute to an attribute sign indicative of a maximum fluid level of patient 102 for an obstetric condition, a minimum fluid level of patient 102 for an obstetric condition, and/or another attribute sign defined using the fluid level singly or in combination with other physiological traits. In some examples, processing circuitry 114 may use the fluid level sensed (e.g., as indicated by the one or more output signals) to define a patient attribute combining the fluid level and another physiological trait sensed by medical system 100. Processing circuitry 114 may issue a communication to patient IO device 118, external device 116, and/or clinician IO device 120 based on the comparison of the patient attribute and the attribute sign.
In addition to the examples above, processing circuitry 114 may use at least a first physiological trait sensed and a second physiological trait sensed to define a patient attribute combining at least the first physiological trait and the second physiological trait. The first physiological trait may be, for example, one of an ECG, echocardiogram, electromyography, impedance magnitude, optical signal, a pressure magnitude, an accelerometry reading, an audible sound, a temperature, a biochemical signal, and/or any other physiological trait influenced by a body function of patient 102. The second physiological trait may be, for example, another of an ECG, echocardiogram, electromyography, impedance magnitude, optical signal, a pressure magnitude, an accelerometry reading, an audible sound, a temperature, a biochemical signal, and/or any other physiological trait influenced by a body function of patient 102. Processing circuitry 114 may compare the patient attribute defined using the combined first physiological trait and the second physiological trait sensed to an attribute sign defining a threshold for the combined first physiological trait and the second physiological trait. Processing circuitry 114 may issue a communication to patient IO device 118, external device 116, and/or clinician IO device 120 based on the comparison of the patient attribute and the attribute sign.
In some examples, processing circuitry 114 may use at least a first patient attribute sensed and a second patient attribute sensed to define a patient attribute combining at least the first patient attribute and the second patient attribute. The first patient attribute may be, for example, one of a hormone level, a muscle contraction, a body temperature, a heart rate, a blood pressure level, an oxygen saturation level, a respiration rate, an activity level, a glucose level, a fluid level, and/or another patient attribute defined using a physiological trait of patient 102. The second patient attribute may be, for example, another of a hormone level, a muscle contraction, a body temperature, a heart rate, a blood pressure level, an oxygen saturation level, a respiration rate, an activity level, a glucose level, a fluid level, and/or another patient attribute defined using a physiological trait of patient 102. Processing circuitry 114 may compare the patient attribute defined using the combined first patient attribute and the second patient attribute to an attribute sign defining a threshold for the combined first patient attribute and the second patient attribute. Processing circuitry 114 may issue a communication to patient IO device 118, external device 116, and/or clinician IO device 120 based on the comparison of the patient attribute and the attribute sign.
Processing circuitry 114 may be configured to communicate with patient IO device 118, external device 116, and/or clinician IO device 120 via a network 136. For example, similar to the use of link 119 (
Processing circuitry 114 may transmit data (e.g., patient physiological data) received from sensing circuitry 112 to patient IO device 118, external device 116, and/or clinician IO device 120 via network 136. Clinician IO device 120, external device 116, and or patient IO device 118 may comprise computing devices configured to allow users, e.g., clinicians treating patient 102 and other patients, to interact with data collected from sensing circuitry 112 and/or determined by processing circuitry 114. In some examples, sensor(s) 110, sensing circuitry 112, processing circuitry 114, clinician IO device 120, external device 116, and/or patient IO device 118 include one or more handheld computing devices, computer workstations, servers, or other networked computing devices, e.g., a cloud computing system. For example, external device 116 may comprise a cloud computing system configured to receive data from IMD 108 via network 136 and, in some cases, patient or clinician IO devices. In some examples, sensor(s) 110, sensing circuitry 112, and/or at least some portion of processing circuitry 114 is mechanically supported by medical device 108. In some examples, at least a portion of processing circuitry 114 is mechanically supported by one or more of IO devices 118, 120 or external device 116.
Network 136 may include one or more computing devices (not shown), such as one or more non-edge switches, routers, hubs, gateways, security devices such as firewalls, intrusion detection, and/or intrusion prevention devices, servers, cellular base stations and nodes, wireless access points, bridges, cable modems, application accelerators, or other network devices. Network 136 may include one or more networks administered by service providers, and may thus form part of a large-scale public network infrastructure, e.g., the Internet. Network 136 may provide circuitry and/or devices, such as processing circuitry 114, sensing circuitry 112, external device 116, clinician IO device 120, and/or patient IO device 118, access to the Internet, and may provide a communication framework that allows processing circuitry 114, sensing circuitry 112, external device 116, clinician IO device 120, and/or patient IO device 118 to communicate with one another. In some examples, network 136 may include a private network that provides a communication framework that allows processing circuitry 114, sensing circuitry 112, external device 116, clinician IO device 120, and/or patient IO device 118 to communicate with each other, but isolates one or more of these devices or data flows between these devices from devices external to the private network for security purposes. In some examples, the communications between processing circuitry 114, sensing circuitry 112, external device 116, clinician IO device 120, and/or patient IO device 118 are encrypted.
Medical device 108 may mechanically support at least some portion of processing circuitry 114. In some examples, medical device 108 mechanically supports a first portion of processing circuitry 114, and external device 116, clinician IO device 120, patient IO device 118, and/or network 136 mechanically supports a second portion of processing circuitry 114. Processing circuitry 114 may include any circuitry and/or devices of external device 116, clinician IO device 120, patient IO device 118, and/or network 136 to perform the techniques described herein. In examples, processing circuitry 114 is configured to utilize population data sensed from a population of individual patients potentially subject to one or more of the obstetric conditions. In examples, external device 116 and/or network 136 is configured to communicate with a plurality of individual medical devices worn, implanted within, and/or otherwise utilized by the population of individual patients to gather the population data. For example, external device 116 and/or network 136 may be configured to communicate with individual medical device 144 (e.g., via link 146) to sense one or more physiological traits from an individual patient 148, communicate with individual medical device 150 (e.g., via link 152) to sense one or more physiological traits from an individual patient 154, and/or communicate with individual medical device 156 (e.g., via link 159) to sense one or more physiological traits from an individual patient 160.
Sensor(s) 110 may include any devices, circuitry, structures, reagents, or other materials configured such that sensor 110 may sense input information 130 indicative of one or more physiological traits of patient 102. The one or more physiological traits of patient 102 may include one or more fetal physiological traits of fetal patient 104. For example, sensor 110 may include an electrode configured to sense an electric potential, an impedance, a current, and/or some other electrical phenomena influenced by (e.g., generated by and/or transmitted through) a body of patient 102 (e.g., to sense an ECG signal, an electromyography signal, a temperature, a glucose level, and/or some other physiological trait). Sensor 110 may include a sound transducer configured to sense a sound wave influenced by (e.g., generated by, reflected by, and/or transmitted through) a body of patient 102 (e.g., to sense an echocardiogram signal, a generated sound, and/or some other physiological trait). Sensor 110 may include a light transmitter and/or receiver configured to transmit light to and/or sense light emitted from (e.g., reflected by) a body of patient 102 (e.g., to sense a blood pressure, an oxygen saturation, and/or some other physiological trait). Sensor 110 may include an accelerometer configured to sense a motion generated by a body of patient 102 and/or a body of fetal patient 104 (e.g., to sense a patient activity level, a fetal activity level, a respiration, and/or some other physiological trait). Sensor 110 may include a force transducer configured to sense a force imparted from a body of patient 102 and/or fetal patient 104 (e.g., to sense a patient weight, a blood pressure, and/or some other physiological trait).
Sensing circuitry 112 is configured to receive the output information 132 from sensor 110 and issue output signals 134 to processing circuitry 114. In examples, sensing circuitry 112 may be configured to define and/or refine the output information using a machine learning algorithm trained using population data indicative of output signals sensed from patient 102 and/or a population of other individual patients potentially subject to one or more of the obstetric conditions (e.g., patient 148, patient 154, and/or patient 160). In some examples, sensor 110 includes a first sensor configured to sense a first physiological trait of patient 102 and a second sensor configured to sense a second physiological trait of patient 102. In some examples, the first physiological trait or the second physiological trait includes a fetal physiological trait of fetal patient 104. Output signals 134 may include a first output signal indicative of the first physiological trait and a second output signal indicative of the fetal physiological trait. In some examples, sensor 110 is configured to sense a mixed physiological trait indicative of both a physiological trait of patient 102 and a fetal physiological trait of fetal patient 104, and output signals 134 is a mixed output signal indicative of both the physiological trait and the fetal physiological trait.
Processing circuitry 114 may be configured to define any patient attribute indicative of a physiological characteristic of patient 102 using output signal 134. In examples, processing circuitry 114 is configured to define one or more patient attributes including one or more of a hormone level of patient 102, a body temperature of patient 102, a heart rate of patient 102, a systolic pressure of patient 102, a diastolic pressure of patient 102, an oxygen saturation level of patient 102, a respiration rate of patient 102, and/or other patient attributes. As discussed, the one or more patient attributes may include one or more fetal attributes including one or more of a heart rate of fetal patient 104, a systolic pressure of fetal patient 104, a diastolic pressure of fetal patient 104, an oxygen saturation level of fetal patient 104, a respiration rate of fetal patient 104, a temperature of fetal patient 104, and/or other fetal attributes. Processing circuitry 114 is configured to compare the patient attribute to an attribute sign to substantially monitor patient 102 for an obstetric condition. The attribute sign may define any threshold for a patient attribute, including a maximum of minimum hormone level, a maximum or minimum heart rate, a maximum or minimum heart rate variability, a maximum or minimum systolic blood pressure, a maximum or minimum diastolic blood pressure, a maximum or minimum oxygen saturation level, a maximum or minimum respiration rate or depth, a maximum or minimum body temperature, a maximum or minimum fluid level, a maximum or minimum body weight, a maximum or minimum blood glucose level, a maximum or minimum activity level, or some other defined attribute sign.
In examples, processing circuitry 114 is configured to receive a mixed output signal indicative of both the first physiological trait of patient 102 and the second physiological trait of patient 102. Processing circuitry may define a first patient attribute and a second patient attribute using the mixed output signal. Processing circuitry 114 and/or sensing circuitry 112 may be configured to preprocess the mixed output signal (e.g., using linear filtering or another preprocessing technique) to enhance a patient signal source indicative of the first patient attribute and/or the second patient attribute. In examples, processing circuitry 114 is configured to use a machine learning algorithm to, for example, improve an accuracy of and/or reduce input requirements of the patient signal source. In examples, processing circuitry 114 is configured to use at least a first mixed output signal and a second mixed output signal to define the patient attribute. The first mixed output signal and the second mixed output signal may be indicative of the patient signal source. For example, the first mixed output signal may be indicative of a mixed physiological trait sensed using a first sensing element (e.g., a first electrode) of sensor 110 or sensor 124 (
In some examples, processing circuitry 114 is configured to perform some portion of or substantially all of the signal separation technique to define the first patient attribute and/or the second patient attribute. In some examples, processing circuitry 114 is configured to communicate data indicative of the mixed output signal to circuitry of another device (e.g., external device 116, network 136, patient IO device 118, and/or clinician device 120) and receive a communication indicative of the first patient attribute and/or second from the other device. Processing circuitry 114 may be configured to define the first patient attribute and/or the second patient attribute using the communication indicative of the first patient attribute and/or second patient attribute received from the other device. Example techniques for separating signal sources, such as physiological signals of a maternal patient and physiological signals of a fetal patient, are described in U.S. Provisional Patent Application Ser. No. 63/498,965, filed Apr. 28, 2023, and titled “MEDICAL SYSTEM CONFIGURED TO USE SOURCE SEPARATION TO IDENTIFY PATIENT PARAMETERS FROM SIGNALS RECEIVED FROM MULTIPLE MEDICAL DEVICES,” the entire content of which is incorporated herein by reference.
Processing circuitry 114 may be configured to define and/or refine the attribute sign to, for example, reduce a rate of false positives when comparing the patient attribute to the attribute sign. In examples, processing circuitry 114 is configured to utilize a model developed by a machine learning algorithm trained with a training data set based on the patient physiological data sensed using sensor 110 to define and/or refine the attribute sign. In examples, processing circuitry 114 is configured to receive an assessment input from a user input device (e.g., clinician IO device 120) indicative of an assessment of whether processing circuitry 114 issued an appropriate communication (e.g., an appropriately tiered communication) when a previously received set of patient physiological data (“prior patient data”) was communicated. Processing circuitry 114 may be configured to train the machine learning algorithm using the prior patient data and/or the assessment input provided, such that the attribute sign may be substantially personalized to patient 102. In examples, rather than or in addition to being provided from a user input device, the assessment input may be accessed by processing circuitry 114 via one or more of medical device 108, second medical device 122, external device 116, patient input/output device 118, network 136, or another portion of system 100.
In examples, processing circuitry 114 is configured to formulate one or more training data sets using the assessment input (e.g., from clinician IO device 120) and the prior patient data. A training data set formulated may include a plurality of training input vectors representative of the prior patient data and a plurality of training output vectors representative of the assessment input received for the prior patient data, with each training input vector associated with a corresponding training output vector. Processing circuitry 114 may formulate a given input vector by defining one or more elements of the given input vector, where the one or more elements are indicative of some portion of the prior patient data. Processing circuitry 114 may formulate an associated training output vector by defining one or more elements of the associated training output vector, where the one or more elements of the training output vector are indicative of the assessment input received. The assessment input received may indicate, for example, whether a training input vector described or is likely to describe one or more obstetric condition for the patient.
Processing circuitry 114 may group each training input vector and associated training output vector in a data pair, such that processing circuitry 114 formulates a plurality of data pairs. Processing circuitry 114 may define a training data set using the plurality of data pairs and, in some examples, train the machine learning algorithm using the training data set. Once trained with the training data set, the machine learning algorithm may be trained to receive a current input vector indicative of patient physiological data and map the current input vector onto an output space defined at least in part by the plurality of training output vectors. Processing circuitry 114 may define and/or refine the attribute sign based on the output space defined. In examples, processing circuitry 114 is configured to compare the patient attribute to the attribute sign based on the mapping of the current input vector onto the output space defined. In some examples, the attribute sign defines a vector within the output space.
In examples, processing circuitry 114 may be configured to define and/or refine the attribute sign using a machine learning algorithm trained using population data sensed from a population of other individual patients potentially subject to one or more of the obstetric conditions (e.g., patient 148, patient 154, and/or patient 160). The machine learning algorithm may be trained using the population data. For example, machine learning algorithm may be trained using a population training data set including a plurality of population input vectors representative of the population data and a plurality of population output vectors indicative of an associated evaluation input. A population input vector may describe, for example, physiological data received for an individual patient within the population. An evaluation input may indicate, for example, whether a population input vector described one or more obstetric conditions for the individual prenatal patient. Each population input vector may be associated with a population output vector. Once trained with the population training data set, the machine learning algorithm may be trained to receive a current input vector indicative of patient physiological data and map the current input vector onto a population output space defined at least in part by the plurality of population output vectors. Processing circuitry 114 may define and/or refine the attribute sign based on the population output space defined. In examples, processing circuitry 114 is configured to compare the patient attribute to the attribute sign based on the mapping of the current input vector onto the population output space defined. In some examples, the patient attribute defines a vector within the population output space.
In examples, processing circuitry 114 is configured to gather the population data from the population of other individual patients potentially subject to one or more of the obstetric conditions (e.g., patient 148, patient 154, and/or patient 160). For example, processing circuitry 114 may be configured to communicate with individual medical device 144 to collect one or more physiological traits from individual patient 148, communicate with individual medical device 150 to collect one or more physiological traits from individual patient 154, and/or communicate with individual medical device 156 to collect one or more physiological traits from individual patient 160. Processing circuitry 114 may be configured to formulate the population training data set using the population data gathered. In examples, processing circuitry is configured to train the machine learning algorithm using the population training data set.
Processing circuitry 114 (and/or sensing circuitry 112) may include one or more processing circuits configured to implement the machine learning algorithm, such as a neural network, a deep learning system, or another type of machine learning system. In examples, processing circuitry 114 is configured to implement the machine learning algorithm using one or more neural network systems, deep learning systems, or other types of supervised or unsupervised machine learning systems. For example, the machine learning algorithm may be implemented by a feedforward neural network, such as a convolutional neural network, a radial basis function neural network, a recurrent neural network, a modular or associative neural network. Examples of machine learning algorithms that may be so configured to perform aspects of this disclosure include can include various learning styles, such as supervised learning, unsupervised learning, and semi-supervised learning. Example types of algorithms include Bayesian algorithms, Clustering algorithms, decision-tree algorithms, regularization algorithms, regression algorithms, instance-based algorithms, artificial neural network algorithms, deep learning algorithms, dimensionality reduction algorithms and the like. Various examples of specific algorithms include Bayesian Linear Regression, Boosted Decision Tree Regression, and Neural Network Regression, Back Propagation Neural Networks, Convolution Neural Networks (CNN), Long Short Term Networks (LSTM), the Apriori algorithm, K-Means Clustering, k-Nearest Neighbour (kNN), Learning Vector Quantization (LVQ), Self-Organizing Map (SOM), Locally Weighted Learning (LWL), Ridge Regression, Least Absolute Shrinkage and Selection Operator (LASSO), Elastic Net, and Least-Angle Regression (LARS), Principal Component Analysis (PCA) and Principal Component Regression (PCR).
In examples, a neural network utilized by processing circuitry 114 includes a plurality of artificial neurons. The artificial neurons may be present within one or more layers of the neural network. For example, the artificial neurons may present within an input layer of the neural network, an output layer of the neural network, and one or more hidden layers between the input layer and the output layer. The input layer may include one or more input artificial neurons. The output layer may include one or more output artificial neurons. The artificial neurons may be configured to receive a signal at an input of the artificial neuron and process the signal at an output of the artificial neuron (e.g., process the signal using a parameter of the artificial neuron). The artificial neuron may include a plurality of inputs and a plurality of outputs. The artificial neuron may be configured to receive the input from the output of a separate artificial neuron, and may be configured to pass the processed signal from its output to the input of another artificial neuron. The processing of the signal conducted by the artificial neuron may be adjusted by the artificial neuron as training of the machine learning algorithm proceeds. Processing circuitry 114 may be configured to train the machine learning algorithm using the training data set and/or population training data set in any manner causing the machine learning algorithm to converge as the training proceeds. In examples, processing circuitry 114 is configured to use a first portion of the training data set and/or population training data set to cause the machine learning algorithm to converge and a second portion of the training data set and/or population training data set to validation test and/or blind test the training conducted with the first portion.
As discussed, any of external device 116, clinician IO device 120. Patient IO device 118, network 136, and/or medical devices 108, 122, 144, 150, 156 may include, mechanically support, and/or house some portion of or substantially all of processing circuitry 114. Any of external device 116, clinician IO device 120. Patient IO device 118, network 136, and/or medical devices 108, 122, 144, 150, 156 may perform any of the functionality ascribed to processing circuitry 114. Likewise, any of external device 116, clinician IO device 120. Patient IO device 118, network 136, and/or medical devices 108, 122, 144, 150, 156 may perform any of the functionality ascribed to any other of external device 116, clinician IO device 120. Patient IO device 118, network 136, and/or medical devices 108, 122, 144, 150, 156. In some examples, some or substantially all of the functionality ascribed to processing circuitry 114 may be performed by one or more devices and/or circuitries not shown in
System 100 (e.g., processing circuitry 114) may also be configured to retrieve data regarding patient 102 and/or fetal patient 104 from electronic health records (EHR) via network 136. The EHR may include data regarding historical (e.g., baseline) physiological parameter values, previous health events and treatments, disease states, comorbidities, demographics, height, weight, and body mass index (BMI), as examples, of patients including maternal patient 102 and/or fetal patient 104. System 100 may use data from the EHR to configure algorithms implemented by processing circuitry 114, medical device 108, and/or other devices within system 100 to detect and/or define patient attributes and or attribute signs.
Detection of patient attributes and or attribute signs can be achieved by looking at a number of possible physiological traits that occur prior to and while defining a patient attribute and or attribute sign. The advantageous markers to detect an impending or ongoing event may be determined based on an etiology of the patient. The etiology of patient 102 and/or fetal patient 104 may include baseline characteristics, medical history, or disease state. The etiology may include any EHR data, as well as patient activity level or metabolite level. With such possible inputs, processing circuitry 114 may be configured to determine patient physiological traits to exhibit certain trends or threshold crossings to detect an impending or ongoing acute health event, e.g., one or more of a patient attribute and or attribute sign. In some examples, system 100 may be configured to utilize a set of rules to determine one or more patient attributes and/or attribute signs. System 100 may be configured to modify the rule set to modify certain rules (e.g., turn certain rules on or off), change the weighting of certain rules, or conduct other modifications.
Processing circuitry 114 may include fixed function circuitry and/or programmable processing circuitry. Processing circuitry 114 may include any one or more of a microprocessor, a controller, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a tensor processing unit (TPU) and/or other AI processing unit, or equivalent discrete or analog logic circuitry. In some examples, processing circuitry 114 may include multiple components, such as any combination of one or more microprocessors, one or more controllers, one or more DSPs, one or more ASICs, or one or more FPGAs, as well as other discrete or integrated logic circuitry. The functions attributed to processing circuitry 114 herein may be embodied as software, firmware, hardware, or any combination thereof.
Sensing circuitry 112 may be selectively connected to sensing elements 168 and other sensors 110, e.g., via switching circuitry 166 as controlled by processing circuitry 114. Sensing elements 168, e.g., electrodes, and sensor(s) 110 may be configured to sense physiological characteristics of patient 102, such as an electrocardiogram (“ECG”), echocardiogram, electromyography, impedance magnitude, optical signal, a pressure, an accelerometry, an audible sound, a biochemical signal, and/or any other physiological trait influenced by a body and/or body function of patient 102. Sensor(s) 110 may include, for example, accelerometers, microphones, optical sensors, temperature sensors, force sensors, biochemical sensors, and/or pressure sensors. Sensing circuitry 112 may monitor signals from sensing elements 168 and other sensors 110 and provide output signals 134 to processing circuitry 114. Sensing circuitry 112 and/or processing circuitry 114 may include one or more filters and amplifiers for filtering and amplifying signals received from one or more of sensing elements 168 and/or other sensors 110. In some examples, sensing circuitry 112 and/or processing circuitry 114 may include a rectifier, filter and/or amplifier, a sense amplifier, comparator, and/or analog-to-digital converter. Processing circuitry 114 may define and/or monitor patient physiological data store the patient physiological data in memory 164.
Processing circuitry 114 may issue, via communication circuitry 162, a communication to patient IO device 118, external device 116, and/or clinician IO device 120, based on a comparison of a patient attribute and a attribute sign. Processing circuitry 114 may communicate, via communication circuitry 162, at least a portion of the patient physiological data to patient IO device 118, external device 116, and/or clinician IO device 120. Such transmissions may occur on a daily or other basis. Communication circuitry 162 may include any suitable hardware, firmware, software, or any combination thereof for communicating with another device, such as computing devices 12, with the aid of an internal or external antenna, e.g., antenna 170.
Medical device 108 may be any device configured to sense a physiological trait of patient 102 and communicate patient physiological data. In examples, medical device 108 may include a leadless, subcutaneously-implantable monitoring device configured to be implanted with patient 102. Medical device 108 may be a device configured to substantially non-invasively contact a body of patient 102 to position sensor 110 (e.g., smartwatch and/or other smart apparel). Medical device 108 may be a device configured to position sensor 110 through a manipulation by and/or action of patient 102 (e.g., a weight scale, a blood pressure cuff, and/or a glucose testing device). Although described primarily in the context of examples in which medical device 108 takes the form of a device configured to be implanted within patient 102, the medical device 108 may be any device configured to position sensor 110 such that sensor 110 may to sense a physiological trait of patient 102. As discussed, the physiological trait of patient 102 may include a fetal physiological trait of fetal patient 104 (
One or more of antenna 170, sensing elements 168, sensor 110, and/or circuitries 112, 114, 162, 166 may be formed on cover 174, such as by using flip-chip technology. Cover 174 may be flipped onto a housing 172. When flipped and placed onto housing 172, the components of medical device 108 formed on the inner side of cover 174 may be positioned in a gap 176 defined by housing 172. Sensing elements 168 may be electrically connected to switching circuitry 166 through one or more vias (not shown) formed through cover 174. Cover 174 may be formed of sapphire (i.e., corundum), glass, parylene, and/or any other suitable material. Housing 172 may be formed from titanium or any other suitable material (e.g., a biocompatible material). Sensing elements 168 (e.g., an electrode) may be formed from any of stainless steel, titanium, platinum, iridium, alloys thereof, or other suitable materials. In addition, sensing elements 168 may be coated with a material such as titanium nitride or fractal titanium nitride, although other suitable materials and coatings for such electrodes may be used.
In the example shown in
Processing circuitry 180, in one example, is configured to implement functionality and/or process instructions for execution within computing device 178. For example, processing circuitry 180 may be capable of processing instructions, including applications 190, stored in storage device 182. Examples of processing circuitry 180 may include, any one or more of a microprocessor, a controller, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a tensor processing unit (TPU) and/or other AI processing unit, or equivalent discrete or integrated logic circuitry.
Storage device 182 may be configured to store information within computing device 178, including applications 190 and data 200. Data 200 may include patient physiological data 202 and/or population physiological data 206. In examples, data 200 may include fetal physiological data 204 (e.g., based on the one or more physiological traits of patient 102). Storage device 182, in some examples, is described as a computer-readable storage medium. In some examples, storage device 182 includes a temporary memory or a volatile memory. Examples of volatile memories include random access memories (RAM), dynamic random access memories (DRAM), static random access memories (SRAM), and other forms of volatile memories known in the art. Storage device 182, in one example, is used by applications 190 running on computing device 178 to temporarily store information during program execution. Storage device 182, in some examples, also includes one or more memories configured for long-term storage of information, e.g., including non-volatile storage elements. Examples of such non-volatile storage elements include magnetic hard discs, optical discs, floppy discs, flash memories, or forms of electrically programmable memories (EPROM) or electrically erasable and programmable (EEPROM) memories.
Computing device 178 utilizes communication circuitry 184 to communicate with other devices, such as external device 116, clinician IO device 120, patient IO device 118, and/or medical device 108. Communication circuitry 184 may include a network interface card, such as an Ethernet card, an optical transceiver, a radio frequency transceiver, or any other type of device that can send and receive information. Other examples of such network interfaces may include 3G, 4G, 5G, LoRaWAN, and WiFi radios.
Computing device 178 also includes a user interface 186. User interface 186 may be configured to provide output to a user using tactile, audio, or video stimuli and receive input from a user through tactile, audio, or video feedback. User interface 186 may include, as examples, a presence-sensitive display, a mouse, a keyboard, a voice responsive system, video camera, microphone, or any other type of device for detecting a command from a user, a sound card, a video graphics adapter card, or any other type of device for converting a signal into an appropriate form understandable to humans or machines, a speaker, a cathode ray tube (CRT) monitor, a liquid crystal display (LCD), or any other type of device that can generate intelligible output to a user. In some examples, a presence-sensitive display includes a touch-sensitive screen.
Example applications 190 executable by processing circuitry 180 of computing device 178 may include an interface application 192 configured to facilitate a user interface with, for example, clinician IO device 120, patient IO device 118, external device 116, and/or medical device 108. Example applications 190 may include a monitoring system 194 that may utilize one or more machine learning algorithms 196. Execution of interface application 192 by processing circuitry 180 may configure computing device 178 to interface with clinician IO device 120, patient IO device 118, external device 116, and/or medical device 108. For example, interface application 192 may configure computing device 178 to communicate with clinician IO device 120, patient IO device 118, external device 116, and/or medical device 108 via communication circuitry 184. Processing circuitry 180 may receive patient physiological data 202 and/or fetal physiologic data 204 from medical device 108 and/or population physiological data 206 from medical devices 144, 150, 156, and store patient physiological data 202, fetal physiological data 204, and/or population physiological data in storage device 182. Interface 192 application may also configure user interface 186 for a user to interact with data 200, and/or interact with clinician IO device 120, patient IO device 118, external device 116, and/or medical device 108. Processing circuitry 180 may execute monitoring system 194 to facilitate monitoring the health of patient 102 and/or fetal patient 104, e.g., based on data 200 and/or other data collected by computing device 178. Monitoring system 194 may cause processing circuitry 180 and computing device 178 to perform any of the techniques described herein related to the patient physiological data of patient 102 and/or the fetal physiologic data of fetal patient 104.
In some examples, processing circuitry 180 executes monitoring system 194 to define a patient attribute. Processing circuitry 180 may execute monitoring system 194 to define and/or redefine an attribute sign. Processing circuitry 180 may execute monitoring system 194 to gather patient physiological data 202, fetal physiological data 204, and/or population physiological data 206. Processing circuitry 180 may execute monitoring system 194 define a patient parameter based on patient physiological data 202. Processing circuitry 180 may execute monitoring system 194 to define a training data set and/or population training data set and train machine learning algorithm 196 using the training data set and/or population training data set. Processing circuitry 180 may execute monitoring system 194 to perform any of the techniques described herein for medical system 100.
In some examples, computing device 178 includes a housing 179 mechanically supporting and/or at least partially enclosing substantially all or at least some part of circuitry and/or other components configured to perform functions ascribed to processing circuitry 180, storage device 182, communication circuitry 184, user interface 186, sensors 188, applications 190, interface application 192, monitoring system 194, machine learning algorithms 196, data 200, patient physiological data 202, fetal physiological 204, and/or population physiological data 206.
One or more of medical device 108, second medical device 122, processing circuitry 114, external device 116, clinician IO device 120, and/or patient input/output device 118 may select training data set 800 comprising a set of data pairs. A prediction by the machine learning algorithm 802 may be compared 804 to a target output 803 (e.g., a target output described by a training output vector), and an error signal and/or machine learning model weights modification may sent/applied to machine learning algorithm 802 based on the comparison to modify/update machine learning model 802. For example, one or more of medical device 108, second medical device 122, processing circuitry 114, external device 116, clinician IO device 120, and/or patient input/output device 118 may, for each training instance in the training set, modify machine learning model 802 to change a score generated by machine learning model 802 in response to subsequent input vectors applied to machine learning algorithm 802. In examples, the error signal and/or machine learning model weights modification modifies and/or alters the mapping of a subsequent training vector onto an output space defined by one or more training output vectors.
The technique includes sensing one or more physiological traits of a patient 102 using one or more sensors 110, 124, 188 (902). The one or more physiological traits are indicative of one or more patient attributes of patient 102. The one or more physiological traits of patient 102 may include one or more physiological traits indicative of a fetal attribute of a fetal patient 104 carried by patient 102. The one or more patient attributes of patient 102 may include one or more fetal attributes of fetal patient 104. The patient attribute is indicative of a physiological characteristic of a body and/or body function of patient 102. In examples, the patient attribute at least one of a hormone level of patient 102, a heart rate of patient 102, a systolic blood pressure of patient 102, a diastolic blood pressure of patient 102, an oxygen saturation level of patient 102, a respiration rate of patient 102, a temperature of patient 102, a muscle contraction of patient 102, a blood glucose level of patient 102, and/or a weight of patient 102. The patient attribute may include at least one of a heart rate of fetal patient 104, a systolic blood pressure of fetal patient 104, a diastolic blood pressure of fetal patient 104, an oxygen saturation level of fetal patient 104, a respiration rate of fetal patient 104, and/or a temperature of fetal patient 104.
The physiological trait sensed may be an electrocardiogram of patient 102, an echocardiogram of patient 102, an audible sound generated by patient 102, an accelerometer signal indicative of a movement of patient 102, an electromyography signal indicative of a muscle contraction of patient 102, an oxygen saturation signal indicative of an oxygen saturation of patient 102, an optical signal influenced by the body of patient 102, and/or another physiological trait. In some examples, sensors 110, 124, 188 sense a mixed physiological trait indicative of both a first patient attribute and a second fetal attribute. In some examples, sensors 110, 124, 188 sense the first physiological attribute using a first sensor and sense the second physiological attribute using a second sensor. In examples, the first physiological trait and/or the second physiological trait includes a fetal physiological trait of fetal patient 104.
The technique includes receiving, by processing circuitry 114, 180 output signals 134 generated by sensing circuitry 112, 126, operably connected to sensors 110, 124, 188 (904). Output signals 134 are indicative of the patient attribute. The technique includes defining, using processing circuitry 114, 180 the patient attribute using output signals 134 (906). In examples, output signals 134 may include a first output signal indicative of a first patient attribute and a second output signal indicative of a second patient attribute, and processing circuitry 114, 180 defines the first patient attribute using the first output signal and defines the second patient attribute using the second output signal. In examples, output signals 134 includes a mixed output signal indicative of both the first patient attribute and the second patient attribute, and processing circuitry 114, 180 defines the first patient attribute and the second patient attribute using the mixed output signal. Processing circuitry 114, 180 may perform a signal separation technique to define the first patient attribute and the second patient attribute. In examples, the first patient attribute and/or the second patient attribute includes a fetal attribute of fetal patient 104.
The technique includes issuing a communication, using processing circuitry 114, 180 based on a comparison of the patient attribute and an attribute sign. (908). Processing circuitry 114, 180 may convey the communication using communications circuitry 162, 184. Processing circuitry 114, 180 may issue the communication to device circuitry of at least one of patient input/output device 118, external device 116, and/or clinician IO device 120. In examples, processing circuitry 114, 180 communicates data indicative of at least one of the physiological trait, a patient physiological parameter indicative of the physiological trait, and/or the patient attribute, to device circuitry of at least one of a patient input/output device 118, external device 116, and/or clinician IO device 120. Processing circuitry 114, 180 may communicate data indicative of at least one of the fetal physiological trait, a fetal physiological parameter indicative of the fetal physiological trait, or the fetal attribute to device circuitry of at least one of a patient input/output device 118, external device 116, and/or clinician IO device 120.
Processing circuitry 114, 180 may compare the patient attribute to an attribute sign which describes a threshold for an obstetric condition of patient 102. In examples, the patient attribute is indicative of a hormone level of patient 102 and the obstetric condition of patient 102 is one of a maximum hormone level for the obstetric condition or a minimum hormone level for the obstetric condition. In examples, the patient attribute is indicative of a heart rate of patient 102 and the obstetric condition of patient 102 is one of a maximum heart rate for the obstetric condition or a minimum heart rate for the obstetric condition. In examples, the patient attribute is indicative of a systolic blood pressure of patient 102 and the obstetric condition of patient 102 is one of a maximum systolic blood pressure for the obstetric condition or a minimum systolic blood pressure rate for the obstetric condition. In examples, the patient attribute is indicative of a diastolic blood pressure of patient 102 and the obstetric condition of patient 102 is one of a maximum diastolic blood pressure for the obstetric condition or a minimum diastolic blood pressure for the obstetric condition. In examples, the patient attribute is indicative of an oxygen saturation level of patient 102 and the obstetric condition of patient 102 is one of a maximum oxygen saturation level for the obstetric condition or a minimum oxygen saturation level for the obstetric condition. In examples, the patient attribute is indicative of a respiration rate of patient 102 and the obstetric condition of patient 102 is one of a maximum respiration rate for the obstetric condition or a minimum respiration rate for the obstetric condition. In examples, the patient attribute is indicative of a temperature of patient 102 and the obstetric condition of patient 102 is one of a maximum temperature for the obstetric condition or a minimum temperature for the obstetric condition. In examples, the patient attribute is indicative of an activity level of patient 102 and the obstetric condition of patient 102 is one of a maximum activity level for the obstetric condition or a minimum activity level for the obstetric condition. In examples, the patient attribute is indicative of a muscle contraction of patient 102 and the obstetric condition of patient 102 is one of false labor for the obstetric condition or maternal labor for the obstetric condition. In examples, the patient attribute is indicative of a blood glucose level of patient 102 and the obstetric condition of patient 102 is one of a maximum blood glucose level for the obstetric condition (e.g., a maximum blood glucose level indicative of gestational diabetes) or a minimum blood glucose level for the obstetric condition. In examples, the patient attribute is indicative of a weight of patient 102 and the obstetric condition of patient 102 is one of a maximum weight for the obstetric condition or a minimum weight for the obstetric condition. In examples, the patient attribute is indicative of a fluid level of patient 102 and the obstetric condition of patient 102 is one of a maximum fluid level for the obstetric condition or a minimum fluid level for the obstetric condition.
In examples, the patient attribute is indicative of one or more of a heart rate of fetal patient 104, a systolic blood pressure of fetal patient 104, a diastolic blood pressure of fetal patient 104, an oxygen saturation level of fetal patient 104, a respiration rate of fetal patient 104, a temperature of fetal patient 104, and/or an activity level of fetal patient 104. The obstetric condition may be one or more of a maximum heart rate of fetal patient 104, a minimum heart rate of fetal patient 104, maximum systolic blood pressure of fetal patient 104, a minimum systolic blood pressure of fetal patient 104, maximum diastolic blood pressure of fetal patient 104, a minimum diastolic blood pressure rate of fetal patient 104, a maximum oxygen saturation level of fetal patient 104, a minimum oxygen saturation level of fetal patient 104, a maximum respiration rate of fetal patient 104, a minimum respiration rate of fetal patient 104, a maximum temperature of fetal patient 104, a minimum temperature of fetal patient 104, a maximum activity level of fetal patient 104, or a minimum activity level of fetal patient 104.
In examples, processing circuitry 114, 180 issues the communication using a tiered communication indicative of an assessment of the comparison of the patient attribute and the attribute sign. Processing circuitry 114, 180 may define a tier of a communication based on a plurality of attribute signs (e.g., a first attribute sign, a second attribute sign, and/or a third attribute sign). In examples, processing circuitry 114, 180 issues a Tier I communication when the patient attribute is assessed to be a normally expected value (e.g., within a range defined by the first attribute sign). Processing circuitry 114, 180 may issue a Tier II communication when the patient attribute is assessed to potentially indicate a condition warranting further evaluation and/or action by patient 102 and/or a clinician (e.g., within a range defined by the second attribute sign.) Processing circuitry 114, 180 may issue a Tier III communication when the patient attribute is assessed to indicate a condition potentially more serious and/or warranting more urgent action and/or action by patient 102 and/or the clinician (e.g., within a range defined by the third attribute sign).
The tiered communication system may define any number of tiers and any number of attribute signs. In some examples, processing circuitry 114 causes patient IO device 118 and/or clinician IO device 120 to provide visible, audible, or other indicia associated with a tier of the communication. For example, processing circuitry 114 may cause patient IO device 118 and/or clinician IO device 120 to provide a first indicia (e.g., a green background) for a Tier I communication, a second indicia (e.g., a yellow background) for a Tier II communication, and/or a third indicia (e.g., a red background) for a Tier III communication. In examples, processing circuitry 114, 180 may select and/or communicate one or more treatment recommendations based on the communication.
Processing circuitry 114, 180 may define and/or refine the attribute sign to reduce a rate of false positives when comparing the patient attribute to the attribute sign. Processing circuitry 114, 180 may utilize patient physiological data to define and/or refine the attribute sign. In examples, processing circuitry 114, 180 uses a machine learning algorithm 196 trained with a training data set based on the patient physiological data. Machine learning algorithm 196 may define and/or refine the attribute sign using the patient physiological data. In examples, medical system 100 receives an assessment input from patient input/output device 118, external device 116, and/or clinician IO device 120, or another input device. Machine learning algorithm 196 may be trained using a training data set including the assessment input. In some examples, processing circuitry 114, 180 may define and/or refine the attribute sign based on population data sensed from a population of other individual patients 148, 154, 160. Processing circuitry 114, 180 may utilize machine learning algorithm 196 to define and/or refine the attribute sign using the population data. Processing circuitry 114, 180 may communicate with individual medical devices 144, 150, 156 to gather the population data.
According to the example of
Processing circuitry 116 may determine HRV metrics by determining differences between cardiac cycle lengths in the set, e.g., consecutive, or adjacent cardiac cycle lengths. Processing circuitry 116 may determine HRV metrics using time-domain methods, frequency-domain methods, or other methods. Time-domain HRV metrics may include the standard deviation of NN intervals (SDNN), root mean square of successive differences (RMSSD), or standard deviation of successive differences (SDSD), or metrics indicating the amount of cardiac cycle length pairs from a set that differ from each other by more than a threshold, as examples.
Frequency-domain metrics may include at least one of a magnitude of cardiac cycle length differences in a first frequency band, or a ratio of magnitudes of cardiac cycle length differences in the first frequency band and a second frequency band, different than the first frequency band. For example, a frequency domain metric may include a ratio of power in a higher frequency band (e.g., 0.15 to 0.4 Hertz (Hz)) to power in a lower frequency band (e.g., 0.04 to 0.15 Hz).
The one or more patient attributes may comprise one or more heart sound metrics, blood pressure metrics, activity/posture metrics, respiration metrics, and/or impedance/fluid metrics. Heart sound metrics that processing circuitry 116 may determine from a heart sounds signal may include, as example morphological metrics of one or more heart sounds, a cardiac electromechanical activation interval (e.g., an R-SI interval), or a metric indicative of the presence of a heart sound not normally present in healthy individuals (e.g., the S3 heart sound). In some examples, processing circuitry 116 may determine blood pressure values based on a photoplethysmography signal, as described above.
According to the example of
In some examples, processing circuitry 116 is configured to determine that the HRV metric is below a heart rate variability threshold, and generate the output based on the determination. In some examples, the HRV metric is a current HRV metric, and processing circuitry 116 is configured to determine the HRV threshold based on based on a plurality of prior HRV metrics. In this manner, satisfaction of the threshold may indicate a decrease or other change in HRV over a period of time including the cardiac activity signal that produced the current and prior HRV metric measurements.
In some examples, processing circuitry 116 is configured to determine the HRV threshold based on a duration of pregnancy of the maternal patient, e.g., the threshold may change or only be applied after a certain duration of pregnancy. Preeclampsia may be more prevalent later in pregnancy. Furthermore, typically pregnancy may include an increase in HRV later in the term that may not occur in preeclamptic patients. In some examples, processing circuitry 116 is configured to determine that a blood pressure is above a blood pressure threshold, an impedance is above an impedance threshold, or an activity level is below an activity level threshold, and generate the output based on such determinations. In some examples, processing circuitry 116 is configured to activate one or more other sensors, e.g., the photoplethysmography sensor, based on the HRV metric being below the HRV threshold, which may conserve power associated with operation of such sensors until there is some indication of preeclampsia in the maternal patient.
According to the example of
In some examples, the obstetric condition comprises pre-term birth. HRV of maternal patients may typically increase around a predetermined time prior to birth. As such, increases in HRV occurring prior to the predetermined time may be considered indicative of an increase in likelihood of pre-term birth. In some examples, processing circuitry 116 is configured to determine that the HRV metric is above an HRV threshold, and generate the output based on the determination. The HRV metric may be a current HRV metric, and the processing circuitry may be configured to determine the HRV threshold based on based on a plurality of prior HRV metrics.
Processing circuitry 116 receives one or more impedances measured by sensing circuitry 114 via electrodes 168 (1202) and compares the measured impedances to one or more thresholds (1204). If the impedances do not satisfy, e.g., meet or exceed, the threshold(s) (N of 1204), processing circuitry 116 receives further impedance measurements (1202). If the impedances do satisfy the threshold(s) (Y of 1204), processing circuitry 116 generates an output for communication to a computing device (e.g., IO device 118, 120, or external device 116) via communication circuitry 162 (1206). The output is configured to cause the computing device to provide an indication of possible hemorrhage of the maternal patient to a user.
IMD 108, 122 may be configured to position electrodes 168 proximate to at least one of an abdomen, a placenta, or a uterus of maternal patient 102, e.g., in locations such as those illustrated in
In some examples, processing circuitry 116 may similarly detect an obstetric condition of arteriovenous fistula, e.g., of the uterus, as based on changes in impedance resulting from redistribution of fluid. Processing circuitry 116 may additionally or alternatively detect arteriovenous fistula based on changes in temperature, or O2 saturation/blood flow indicated in a photoplethysmography signal.
Another obstetric condition that may be detected by system 100 is stroke of maternal patient 102. For maternal patient 102, processing circuitry 116 and IMDs 108,122 may implement any techniques for detection of stroke described in U.S. Patent Application Publication No. 2021/0251497, filed Feb. 16, 2021 and titled “SYSTEMS AND METHODS FOR DETECTING STROKES” and U.S. Patent Application Publication No. 2022/0061678, filed Aug. 27, 2021 and titled “DETECTION OF PATIENT CONDITIONS USING SIGNALS SENSED ON OR NEAR THE HEAD,” the entire contents of which are incorporated herein by reference. In some examples, for detection of stroke, an IMD may be implanted on or near the head of maternal patient 102 (or external devices positioned in such a location), or in other locations, as described in those patent applications.
Atrial fibrillation (AF) is a common cardiac arrhythmia in maternal patients. IMDs described herein may detect AF based on cardiac cycle lengths indicating in ECG or other cardiac signals. Processing circuitry 116 may determine AF burden-a metric of an amount of AF experienced by a patient. Risk of stroke increases with AF burden. In some examples, processing circuitry 116 may generate an output to cause a computing device to indicate AF burden and/or stroke risk based on AF burden. In some examples, processing circuitry 116 may cause IMD 108,122 to activate additional sensor(s) 110 for detection of stroke (e.g., as described in the above-incorporated references) in response to AF burden satisfying a threshold.
Another pre-partum or post-partum condition that may be detected by system 100 is depression or another mental state. While post-partum depression is prevalent, mental state may be impacted by pre-partum concerns, such as difficulty conceiving, which may also contribute to depression. For maternal patient 102, processing circuitry 116 and IMDs 108,122 may implement any techniques for detection of depression or other mental states escribed in U.S. Provisional Patent Application Ser. No. 63/386,120, filed Dec. 5, 2022, and titled “IMPLANTABLE MENTAL STATE MONITOR,” the entire contents of which are incorporated herein by reference. Such techniques may include surveilling and causing patient interaction with patient IO device to gather inputs for a mental state determination, such as to prompt patient 102 to complete the Edinburgh Post-Natal Depression scale. Such techniques may additionally or alternatively include determining a patient attribute based on an activity level signal of patient 102 with one or more of sensor(s) 110, e.g., an accelerometer signal. In some examples, decreases in activity level of patient 102 may be indicative of depression, e.g., post-partum depression.
It should be understood that various aspects disclosed herein may be combined in different combinations than the combinations specifically presented in the description and accompanying drawings. It should also be understood that, depending on the example, certain acts or events of any of the processes or methods described herein may be performed in a different sequence, may be added, merged, or left out altogether (e.g., all described acts or events may not be necessary to carry out the techniques). In addition, while certain aspects of this disclosure are described as being performed by a single module, unit, or circuit for purposes of clarity, it should be understood that the techniques of this disclosure may be performed by a combination of units, modules, or circuitry associated with, for example, a medical device.
In one or more examples, the described techniques may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions may be stored as one or more instructions or code on a computer-readable medium and executed by a hardware-based processing unit. Computer-readable media may include non-transitory computer-readable media, which corresponds to a tangible medium such as data storage media (e.g., RAM, ROM, EEPROM, flash memory, or any other medium that can be used to store desired program code in the form of instructions or data structures and that can be accessed by a computer).
Instructions may be executed by one or more processors, such as one or more digital signal processors (DSPs), general purpose microprocessors, application specific integrated circuits (ASICs), field programmable logic arrays (FPGAs), tensor processing units (TPUs) and/or other AI processing units, or other equivalent integrated or discrete logic circuitry. Accordingly, the term “processor” or “processing circuitry” as used herein may refer to any of the foregoing structure or any other physical structure suitable for implementation of the described techniques. Also, the techniques could be fully implemented in one or more circuits or logic elements.
The disclosure includes the following examples.
Example 1. A system comprising: an implantable medical device comprising: one or more sensors configured to continuously sense one or more physiological characteristics of a body of a maternal patient; and sensing circuitry operably connected to the one or more sensors and configured to issue one or more output signals indicative of the one or more physiological characteristics; and processing circuitry configured to: define one or more patient attributes using the one or more output signals; and generate an output based on the one or more patient attributes, the output configured to cause a computing device to provide an indication of preeclampsia of the maternal patient to a user.
Example 2. The system of example 1, wherein the one or more sensors comprise a plurality of electrodes, and the one or more output signals comprise an electrocardiogram.
Example 3. The system of example 1 or 2, wherein the one or more patient attributes comprise one or more heart rate variability metrics.
Example 4. The system of example 3, wherein the one or more heart rate variability metrics comprise at least one of a time-domain metric or a frequency-domain metric of a set of cardiac cycle lengths determined based on at least one of the one or more output signals.
Example 5. The system of example 4, wherein the frequency-domain metric comprises at least one of a magnitude of cardiac cycle length differences in a first frequency band, or a ratio of magnitudes of cardiac cycle length differences in the first frequency band and a second frequency band, different than the first frequency band.
Example 6. The system of any one or more of examples 3 to 5, wherein the processing circuitry is configured to determine that the heart rate variability metric is below a heart rate variability threshold, and generate the output based on the determination.
Example 7. The system of example 6, wherein the heart rate variability metric is a current heart rate variability metric, and the processing circuitry is configured to determine the heart rate variability threshold based on based on a plurality of prior heart rate variability metrics.
Example 8. The system of example 6 or 7, wherein the processing circuitry is configured to determine the heart rate variability threshold based on a duration of pregnancy of the maternal patient.
Example 9. The system of any one or more of examples 1 to 8, wherein the one or more sensors comprises a plurality of electrodes, the one or more signals comprise an impedance signal, the one or more patient attributes comprise a patient impedance, and the processing circuitry is configured to generate the output based on a determination that the patient impedance is below a threshold.
Example 10. The system of any one or more of examples 1 to 9, wherein the one or more signals comprise a heart sounds signal, and the one or more patient attributes comprise one or more of a heart sound morphological metric, a cardiac electromechanical activation interval, or presence of an S3 heart sound determined based on the heart sounds signal.
Example 11. The system of any one or more of examples 1 to 10, wherein the one or more sensors comprise a photoplethysmography sensor, the one or more signals comprise a photoplethysmography signal, and the one or more patient attributes comprise a blood pressure determined based on the photoplethysmography signal.
Example 12. The system of examples 6 and 11, wherein the processing circuitry is configured to activate the photoplethysmography sensor based on the heart rate variability metric being below the heart rate variability threshold.
Example 13. The system of example 6, wherein the processing circuitry is configured to activate at least one of the one or more sensors based on the heart rate variability metric being below the heart rate variability threshold.
Example 14. A system comprising: an implantable medical device configured to issue an output signal based on cardiac activity of a maternal patient continuously sensed by the implantable medical device; and processing circuitry configured to: define one or more heart rate variability metrics using the output signal; and generate an output based on a comparison of the one or more heart rate variability metrics to one or more thresholds, the output configured to cause a computing device to provide an indication of an obstetric condition of the maternal patient to a user.
Example 15. The system of example 14, wherein the obstetric condition comprises pre-term birth.
Example 16. The system of example 14 or 15, wherein the processing circuitry is configured to determine that the heart rate variability metric is above a heart rate variability threshold, and generate the output based on the determination.
Example 17. The system of example 16, wherein the heart rate variability metric is a current heart rate variability metric, and the processing circuitry is configured to determine the heart rate variability threshold based on based on a plurality of prior heart rate variability metrics.
Example 18. The system of example 16 or 17, wherein the processing circuitry is configured to determine the heart rate variability threshold based on a duration of pregnancy of the maternal patient.
Example 19. The system of any one or more of examples 14 to 18, wherein the implantable medical device comprises a plurality of electrodes configured to sense the cardiac activity and the output signal comprises an electrocardiogram.
Example 20. An implantable medical device comprising: communication circuitry configured for wireless communication with a computing device; a plurality of electrodes; sensing circuitry configured to measure impedances of a maternal patient via the plurality of electrodes; and processing circuitry configured to: compare the measured impedances to one or more thresholds; and generate an output for communication to the computing device via the communication circuitry based on the comparison, the output configured to cause the computing device to provide an indication of possible hemorrhage of the maternal patient to a user.
Example 21. The implantable medical device of example 20, wherein the implantable medical device is configured to position the electrodes proximate to at least one of an abdomen, a placenta, or a uterus of the maternal patient.
Example 22. The implantable medical device of example 21, wherein the implantable medical device in its entirety is configured to be implanted subcutaneously in an abdominal region of the maternal patient.
Example 23. The system of any one or more of examples 2 to 19 or the implantable medical device of any one or more of examples 20 to 22, wherein the implantable medical device comprises a housing configured for subcutaneous implantation within the maternal patient, the housing containing the sensing circuitry, wherein the plurality of electrodes are formed on the housing, wherein a length of the housing is within a range from 40 to 60 millimeters and is greater than a width of the housing, wherein the width of the housing is greater than the depth.
Example 24. The system of any one or more of examples 1 to 19 or the implantable medical device of any one or more of examples 20 to 22, wherein the computing device comprises a computing device of the maternal patient or of a clinician or caregiver for the maternal patient.
Example 25. The system of any one or more of examples 1 to 19 or the implantable medical device of any one or more of examples 20 to 22, wherein the processing circuitry comprises processing circuitry of the implantable medical device.
Example 26. The system of any one or more of examples 1 to 19 or the implantable medical device of any one or more of examples 20 to 22, wherein the processing circuitry comprises processing circuitry of the computing device.
Example 27. The system of any one or more of examples 1 to 19 or the implantable medical device of any one or more of examples 20 to 22, wherein the processing circuitry comprises processing circuitry of a cloud computing system configured to communicate with the implantable medical device and the computing device.
Example 28. A system comprising: an implantable medical device comprising: one or more sensors configured to continuously sense one or more physiological characteristics of a body of a maternal patient; and sensing circuitry operably connected to the one or more sensors and configured to issue one or more output signals indicative of the one or more physiological characteristics; and processing circuitry configured to: define one or more patient attributes using the one or more output signals; and generate an output based on the one or more patient attributes, the output configured to cause a computing device to provide an indication of a post-partum condition of the maternal patient to a user.
Example 29. The system of example 28, wherein the one or more signals comprise an impedance signal.
Example 30. The system of example 29, wherein the post-partum condition of the maternal patient comprises a hemorrhage, and wherein a change in the impedance signal is indicative of the hemorrhage.
Example 31. The system of example 28, wherein the implantable medical device is implanted subcutaneously in an abdominal region of the maternal patient.
Example 32. The system of example 31, wherein the abdominal region comprises a lateral abdominal region.
Example 33. The system of example 28, wherein the post-partum condition of the maternal patient comprises post-partum depression or another post-partum mental state.
Example 34. The system of example 33, wherein the one or more signals comprise an activity signal.
Various examples have been described. These and other examples are within the scope of the following claims.
This application claims the benefit of priority from U.S. Provisional Patent Application No. 63/517,519, filed Aug. 3, 2023, the entire content of which is incorporated herein by reference.
Number | Date | Country | |
---|---|---|---|
63517519 | Aug 2023 | US |