[0001] This application claims the benefit of U.S. Provisional Patent Application Serial No. 63/370,738, filed 8 August 2022, the entire content of which is incorporated herein by reference.

FIELD

[0002] This disclosure generally relates to systems including medical devices and, more particularly, to monitoring of patient health using such systems.

BACKGROUND

[0003] A variety of devices are configured to monitor physiological signals of a patient. Such devices include implantable or wearable medical devices, as well as a variety of wearable health or fitness tracking devices. The physiological signals sensed by such devices include as examples, electrocardiogram (ECG) signals, respiration signals, perfusion signals, activity and/or posture signals, pressure signals, blood oxygen saturation signals, body composition, and blood glucose or other blood constituent signals. In general, using these signals, such devices facilitate monitoring and evaluating patient health over a number of months or years, outside of a clinic setting.

[0004] In some cases, such devices are configured to detect health events, such as episodes of cardiac arrhythmia or worsening of heart failure, based on the physiological signals. Example arrhythmia types include asystole, bradycardia, ventricular tachycardia, supraventricular tachycardia, wide complex tachycardia, atrial fibrillation, atrial flutter, ventricular fibrillation, atrioventricular block, premature ventricular contractions, and premature atrial contractions. The devices may store ECG and other physiological signal data collected during a time period including an episode as episode data. The devices may also store episode data quantifying the episodes, e.g., number and/or duration of episodes. The medical device may also store ECG and other physiological data for a time period as episode data in response to user input, e.g., from the patient or a caregiver.

1

SUBSTITUTE SHEET (RULE 26) SUMMARY

[0005] In general, the disclosure describes techniques for determining a risk level of a health event based on parametric data of a plurality of parameters of a patient. The plurality of parameters may include atrial fibrillation (AF) burden. In some examples, the techniques include applying an AF burden pattern feature to a model to determine the risk level. In some examples, the model is trained with training sets of parametric data that are classified based on classification data collected automatically in response to detection of a trigger. The techniques also include a patient interface system for presenting one or more inquiries to a patient. The patient interface system may also provide one or more suggestions for the patient to change behavior.

[0006] The techniques of this disclosure may provide one or more advantages. For example, by using a patient interface system to ask a patient to identify one or more patient behaviors, the system may more effectively identify behaviors that may be contributing to increased AF burden as compared with systems that do not ask patients to identify behaviors. Outputting a suggestion to change a patient behavior that likely contributes to increased AF burden may more effectively attenuate or eliminate a pattern of increased AF burden as compared with systems that do not output suggestions to patients.

[0007] In one example, a medical device system includes a memory; and processing circuitry in communication with the memory, wherein the processing circuitry is configured to: receive parametric data for a plurality of parameters of a patient, wherein the parametric data is generated by one or more sensing devices based on physiological signals of the patient sensed by the one or more sensing devices; determine, based on the parametric data, an atrial fibrillation (AF) burden of the patient over a period of time, wherein the AF burden of the patient over the period of time includes a pattern of increased AF burden; output, for display by a user device operated by the patient, a request to identify whether the patient engaged in each patient behavior of a set of patient behaviors during the period of time; determine, based on receiving a response indicating that the patient engaged in one or more patient behaviors of the set of patient behaviors, a suggestion to change at least a subset of the one or more patient behaviors to attenuate the pattern of increased AF burden; and output, for display by the user device operated by the patient, the suggestion.

2

SUBSTITUTE SHEET (RULE 26) [0008] In another example, a medical device system includes a memory; and processing circuitry in communication with the memory, wherein the processing circuitry is configured to: receive parametric data for a plurality of parameters of a patient, wherein the parametric data is generated by one or more sensing devices based on physiological signals of the patient sensed by the one or more sensing devices; determine, based on the parametric data, an atrial fibrillation (AF) burden of the patient over a period of time; apply the AF burden of the patient over the period of time to a model; and determine a risk level of a health event for the patient based on the application of the AF burden of the patient over the period of time to the model.

[0009] In another example, s medical device system includes a memory; and processing circuitry in communication with the memory, wherein the processing circuitry is configured to: receive parametric data for a plurality of parameters of a patient, wherein the parametric data is generated by one or more sensing devices based on physiological signals of the patient sensed by the one or more sensing devices; determine, based on the parametric data, a set of parameters of the patient over a period of time; receive information indicating one or more conditions specific to the patient; set a weight corresponding to each parameter of the set of parameters based on the one or more conditions specific to the patient; apply the set of parameters of the patient over the period of time to a model; and determine a risk level of a health event for the patient based on the application of the set of parameters over the period of time to the model.

[0010] This summary is intended to provide an overview of the subject matter described in this disclosure. It is not intended to provide an exclusive or exhaustive explanation of the apparatus and methods described in detail within the accompanying drawings and description below. Further details of one or more examples are set forth in the accompanying drawings and the description below.

BRIEF DESCRIPTION OF DRAWINGS

[0011] FIG. l is a block diagram illustrating an example medical device system configured to predict health events, and to respond to such predictions, in accordance with one or more techniques of this disclosure.

[0012] FIG. 2 is a block diagram illustrating an example configuration of the IMD of FIG. 1, in accordance with one or more techniques of this disclosure.

3

SUBSTITUTE SHEET (RULE 26) [0013] FIG. 3 is a conceptual side-view diagram illustrating an example configuration of the IMD of FIGS. 1 and 2, in accordance with one or more techniques of this disclosure.

[0014] FIG. 4 is a block diagram illustrating an example configuration of an external device that operates in accordance with one or more techniques of this disclosure.

[0015] FIG. 5 is a block diagram illustrating an example computing system that operates in accordance with one or more techniques of this disclosure.

[0016] FIG. 6 is a flow diagram illustrating an example technique for training a machine learning model using training sets of parametric data classified based on automatically collected classification data, in accordance with one or more techniques of this disclosure.

[0017] FIG. 7 is a flow diagram illustrating an example technique for automatically collecting classification data, in accordance with one or more techniques of this disclosure. [0018] FIG. 8 is a flow diagram illustrating an example technique for predicting a health event and responding to the prediction of the health event, in accordance with one or more techniques of this disclosure.

[0019] FIG. 9 is a flow diagram illustrating an example technique for outputting a suggestion to change patient behavior, in accordance with one or more techniques of this disclosure.

[0020] FIG. 10 is a flow diagram illustrating an example technique for monitoring AF burden following a suggestion to change patient behavior, in accordance with one or more techniques of this disclosure.

[0021] FIG. 11 is a flow diagram illustrating an example technique for identifying a pattern of increased AF burden, in accordance with one or more techniques of this disclosure.

[0022] FIG. 12 is a flow diagram illustrating an example technique for determining a risk level of a health event based on the AF burden of a patient over a period of time, in accordance with one or more techniques of this disclosure.

[0023] FIG. 13 is a flow diagram illustrating an example technique for determining a risk level of a health event based on AF burden variability, in accordance with one or more techniques of this disclosure.

4

SUBSTITUTE SHEET (RULE 26) [0024] FIG. 14 is a flow diagram illustrating an example technique for determining a risk level of a health event based on one or more conditions specific to a patient, in accordance with one or more techniques of this disclosure.

[0025] FIG. 15 is a conceptual diagram illustrating a patient behavior inquiry screen for display on a user interface of a device, in accordance with one or more techniques of this disclosure.

[0026] FIG. 16 is a conceptual diagram illustrating a first suggestion screen for display on a user interface of a device, in accordance with one or more techniques of this disclosure.

[0027] FIG. 17 is a conceptual diagram illustrating a second suggestion screen for display on a user interface of a device, in accordance with one or more techniques of this disclosure.

[0028] FIG. 18 is a graph illustrating parametric data of a plurality of patient parameters over a time period around a stroke event, in accordance with one or more techniques of this disclosure.

[0029] FIG. 19 is a graph illustrating timeseries values of moving averages of parametric data of a patient parameter, in accordance with one or more techniques of this disclosure.

[0030] FIG. 20 is a chart illustrating experimentally-determined statistical significances of a plurality of patient parameters in predicting stroke, in accordance with one or more techniques of this disclosure.

[0031] FIG. 21 is a chart illustrating experimentally-determined statistical significances of a plurality of patient parameters in predicting stroke, in accordance with one or more techniques of this disclosure.

[0032] FIGS. 22A-22D are charts illustrating experimentally-determined statistical significances of a plurality of patient parameters in predicting stroke for different patient populations, in accordance with one or more techniques of this disclosure.

[0033] FIGS. 23 A-23D are charts illustrating experimentally-determined statistical significances of a plurality of patient parameters in predicting hospitalization for different patient populations, in accordance with one or more techniques of this disclosure.

[0034] FIG. 24 is a chart illustrating AF burden pattern features for predicting stroke and health care utilization, in accordance with one or more techniques of this disclosure.

5

SUBSTITUTE SHEET (RULE 26) [0035] FIG. 25A and 25B are diagrams illustrating AF burden patterns in patients who experience stroke or a health care utilization event, respectively, for various patient populations, in accordance with one or more techniques of this disclosure.

[0036] FIG. 26 is a graph illustrating detected AT/AF time (burden) over the course of a monitoring period, in accordance with one or more techniques of this disclosure.

[0037] FIG. 27 presents a scatterplot of terminal nodes by labeled HCU rate and percent of patients for balanced training data, in accordance with one or more techniques of this disclosure.

[0038] FIG. 28 presents an example graphical illustration of patterns in AF burden data mapped for a single HCU patient, in accordance with one or more techniques of this disclosure.

[0039] FIG. 29 presents a scatterplot of scored terminal nodes by labelled HCU rate and patient percent for an unbalanced validation set, in accordance with one or more techniques of this disclosure.

[0040] FIG. 30 presents a Venn diagram of AF burden threshold counts for the validation set, in accordance with one or more techniques of this disclosure.

[0041] Like reference characters refer to like elements throughout the figures and description.

DETAILED DESCRIPTION

[0042] A variety of types of implantable and medical devices detect arrhythmia episodes and other health events based on sensed ECGs and, in some cases, other physiological signals. External devices that may be used to non-invasively sense and monitor ECGs and other physiological signals include wearable devices with electrodes configured to contact the skin of the patient, such as patches, watches, or necklaces. Such external devices may facilitate relatively longer-term monitoring of patient health during normal daily activities.

[0043] Implantable medical devices (IMDs) also sense and monitor ECGs and other physiological signals, and detect health events such as arrhythmia episodes and worsening heart failure. Example IMDs include pacemakers and implantable cardioverterdefibrillators, which may be coupled to intravascular or extravascular leads, as well as pacemakers with housings configured for implantation within the heart, which may be

6

SUBSTITUTE SHEET (RULE 26) leadless. Some IMDs do not provide therapy, such as implantable patient monitors. One example of such an IMD is the Reveal LINQ™ Insertable Cardiac Monitor (ICM), available from Medtronic pic, which may be inserted subcutaneously. Such IMDs may facilitate relatively longer-term monitoring of patients during normal daily activities, and may periodically transmit collected data, e.g., episode data for detected arrhythmia episodes, to a remote patient monitoring system, such as the Medtronic Carelink™ Network.

[0044] FIG. l is a block diagram illustrating an example medical device system 2 configured to predict health events of a patient 4, and to respond to such predictions, in accordance with one or more techniques of the disclosure. The example techniques may be used with an IMD 10, which may be in wireless communication with an external device 12. In some examples, IMD 10 is implanted outside of a thoracic cavity of patient 4 (e.g., subcutaneously in the pectoral location illustrated in FIG. 1). IMD 10 may be positioned near the sternum near or just below the level of the heart of patient 4, e.g., at least partially within the cardiac silhouette. IMD 10 includes a plurality of electrodes (not shown in FIG. 1), and is configured to sense an ECG via the plurality of electrodes. In some examples, IMD 10 takes the form of the LINQ™ ICM. Although described primarily in the context of examples in which the IMD takes the form of an ICM, the techniques of this disclosure may be implemented in systems including any one or more implantable or external medical devices, including monitors, pacemakers, or defibrillators.

[0045] External device 12 is a computing device configured for wireless communication with IMD 10. External device 12 retrieves episode and other physiological data from IMD 10 that was collected and stored by IMD 10. In some examples, external device takes the form of a personal computing device of the patient or caregiver, such as a smartphone.

[0046] In the example illustrated by FIG. 1, system 2 also includes a sensor device 14 in wireless communication with external device 12. Sensor device 14 may include electrodes and other sensors to sense physiological signals of patient 4, and may collect and store physiological data and detect episodes based on such signals. In some examples, sensor device 14 is an external device wearable by patient 4. Sensor device 14 may be incorporated into the apparel of patient 4, such as within clothing, shoes, eyeglasses, a

7

SUBSTITUTE SHEET (RULE 26) watch or wristband, a hat, etc. In some examples, sensor device 14 is a smartwatch or other accessory or peripheral for a smartphone external device 12.

[0047] External device 12 retrieves episode and other physiological data from sensor device 14 that was collected and stored by sensor device 14. External device 12 may include a display and other user interface elements. In some examples, external device 12 presents physiological data retrieved from IMD 10 and/or sensor device 14, and/or statistical representations thereof, to patient 4 or another user. External device 12 may communicate with IMD 10 and/or sensor device 14 according to the Bluetooth® or Bluetooth® Low Energy (BLE) protocols, as examples.

[0048] External device 12 may be configured to communicate with a computing system 20 via a network 15. External device 12 may be used to retrieve data from IMD 10 and sensor device 14, and may transmit the data to computing system 20 via network 15. The retrieved data may include values of physiological parameters measured by IMD 10 and sensor device 14, data regarding episodes of arrhythmia or other health events detected by IMD 10 and sensor device 14, and other physiological signals or data recorded by IMD 10 sensor device 14. The data retrieved from IMD 10 and sensor device 14 may include values of various patient parameters, and/or may be used by computing system 20 to determine values of patient parameters. The values of patient parameters may be referred to as patient parametric data. Patient parametric data may be retrieved and or determined on a periodic basis to produce periodic values, e.g., on a daily basis to produce daily values.

[0049] Computing system 20 may comprise computing devices configured to allow users, e.g., clinicians treating patient 4 and other patients, to interact with data collected from IMDs 10 and sensor devices 14 of their patients. In some examples, computing system 20 includes one or more handheld computing devices, computer workstations, servers or other networked computing devices. In some examples, computing system 20 may include one or more devices, including processing circuitry and storage devices, that implement a monitoring system. The monitoring system may present parametric data of patients to clinicians to allow clinicians to remotely track and evaluate their patients. In some examples, the monitoring system may analyze the data and prioritize presentation of data or alerts for certain patients based on the analysis. Computing system 20, network 15,

8

SUBSTITUTE SHEET (RULE 26) and the monitoring system may be implemented by the Medtronic Carelink™ Network, in some examples.

[0050] Network 15 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, computer terminals, laptops, printers, databases, wireless mobile devices such as cellular phones or personal digital assistants, wireless access points, bridges, cable modems, application accelerators, or other network devices. Network 15 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 15 may provide computing devices, such as computing system 20 and external device 12, access to the Internet, and may provide a communication framework that allows the computing devices to communicate with one another. In some examples, network 15 may be a private network that provides a communication framework that allows computing system 20 and external device 12 to communicate with one another but isolates one or more of these devices or data flows between these devices from devices external to network 15 for security purposes. In some examples, the communications between computing system 20 and external device 12 are encrypted.

[0051] Computing system 20 may also retrieve data for patient 4 from electronic medical records (EMR) database 22. EMR database 22 may store electronic medical records, also referred to as electronic health records, for patient 4, which may be generated by various health care providers, laboratories, clinicians, insurance companies, etc. Although illustrated as a single database in FIG. 1, EMR database 22 may include various databases managed by various entities.

[0052] As examples, EMR database 22 may store a medication history of the patient, a surgical procedure history of the patient, a hospitalization history of the patient, emergency or urgent care visit history of the patient, scheduled clinic visit history of the patient, one or more lab or other clinical test results for patient 4, a cardiovascular history of patient 4, or co-morbidities of patient 4 such as atrial fibrillation, heart failure, or diabetes, as examples. As further examples, EMR database 22 may store medical images for patient 4, such as x-ray images, ultrasound images, echocardiograms, anatomical imagery, medical photographs, radiographic images, etc. The data stored in EMR database

9

SUBSTITUTE SHEET (RULE 26) 22 may include the patient specific records for patient 4 and numerous other patients. In some examples, the data stored by EMR database 22 may include broader demographic information or population-type information for a plurality of patients.

[0053] A monitoring system, e.g., implemented by processing circuitry of computing system 20, may implement the techniques of this disclosure including developing an algorithm based on training sets of parametric data of a population of patients or subjects retrieved from IMDs 10 and external devices of the population, and applying the algorithm to parametric data of an individual patient 4 to predict the occurrence of a clinically significant health event. In some examples, monitoring system trains one or more machine learning (ML) models for prediction of the health event. The output of the ML models for a particular patient may be a level of risk of the health event, a probability of the health event occurring within a certain time, and/or whether the risk or probability satisfies a threshold. Computing system 20 is not limited to using ML models. Computing system 20 may use any kind of model to analyze parametric data.

[0054] Example health events that may be predicted using the techniques of this disclosure include stroke, clinically significant AF requiring hospitalization or urgent care, and clinically significant episodes of symptomatic events, such as syncope or dizziness. Parametric data that may be useful for predicting such health events may include cardiac rhythm data, such as heart rate data and data related to atrial fibrillation (AF) or other arrhythmia episodes. AF data may include quantifications of AF, referred to as AF burden, as well as patterns of AF burden over a plurality of periods of time. Parametric data that may be useful for predicting such clinically significant health events may additionally or alternatively include patient activity data or any other patient data or signals described herein.

[0055] Computing system 20 may, in some cases, identify patterns of increased AF burden and provide one or more suggestions for the patient 4 to change behaviors to eliminate or attenuate the patterns increased AF burden. For example, computing system 20 may receive parametric data for a plurality of parameters of patient 4. The parametric data may be generated by one or more sensing devices (e.g., IMD 10 and/or sensor device 14) based on physiological signals of patient 4 sensed by the one or more sensing devices. In some examples, computing system 20 may receive the parametric data from IMD 10 and/or sensor device 14 in real-time. In some examples, computing system 20 may receive

10

SUBSTITUTE SHEET (RULE 26) a set of parametric data when external device 12 retrieves the parametric data from IMD 10 and/or sensor device 14.

[0056] Computing system 20 may determine, based on the parametric data, an atrial fibrillation (AF) burden of the patient over a period of time. The period of time may, in some cases, extend for more than one day (e.g., 7 days, 30 days, or any other duration of time). For example, computing system 20 may determine, based on the parametric data, AF burden as a function of time. In some examples, the AF burden of patient 4 over the period of time may indicate one or more patterns. For example, the AF burden of patient 4 over the period of time may indicate a pattern of increased AF burden. A pattern of increased AF burden may, in some examples, include one or more occurrences of increased AF burden over the period of time. In some cases, the one or more occurrences of increased AF burden occur more frequently during certain times of day, but this is not required. A pattern of increased AF burden represents any pattern including one or more occurrences of increased AF burden.

[0057] Computing system 20 may output, for display by external device 12 based on determining a pattern of increased AF burden, a request to identify whether the patient 4 engaged in one or more behaviors during a period of time. In some examples, computing system 20 may select the one or more behaviors based on the pattern of increased AF burden. For example, if the pattern of increased AF burden includes occurrences of increased AF burden in the mornings, computing system 20 may output a request for patient 4 to indicate whether they consume caffeine in the mornings. In any case, computing system 20 may output a list of patient behaviors for display by external device 12. Each patient behavior of the list of patient behaviors may be selected or deselected so that the patient can select none of the behaviors, one of the behaviors, or a combination of more than one of the behaviors displayed by the external device 12.

[0058] Computing system 20 may determine, based on receiving a response indicating that the patient engaged in one or more patient behaviors of the set of patient behaviors, a suggestion for patient 4 to change behaviors. In some examples, computing system 20 may identify a likely cause of the pattern of increased AF burden based on the response. For example, if the response indicates that the patient 4 consumes caffeine in the mornings, computing system 20 may determine that caffeine consumption likely contributes to the pattern of increased AF burden. Computing system 20 may output a suggestion to

11

SUBSTITUTE SHEET (RULE 26) decrease or eliminate caffeine consumption to eliminate or attenuate the pattern of increased AF burden in the future. Consumption of one or more chemicals or minerals (e.g., Caffeine, Sodium, Potassium) may contribute to increased AF burden. Additionally, or alternatively, exercise or other increased activity may contribute to increased AF burden. When computing system 20 outputs a list of behaviors to external device 12, computing system 20 may select the list of behaviors to include behaviors, e.g., activity and consumption of certain chemicals and minerals, that are likely to contribute to increased AF burden. This may improve an ability of computing system 20 to identify the cause of increased AF burden as compared with systems that do not request patients to select from a list of behaviors that are likely to cause increased AF burden.

[0059] Computing system 20 may output, for display by external device 12, the suggestion to change behavior. In some examples, computing system 20 may receive a response indicating an acceptance of the suggestion. Computing system 20 may determine the AF burden of the patient 4 over a period of time following the acceptance of the suggestion to change behavior to determine if the change in behavior eliminated or attenuated the pattern of increased AF burden. If the change in behavior did not eliminate or attenuate the pattern of increased AF burden, computing system 20 may output another suggestion to change behavior.

[0060] AF burden data may indicate a level of risk that patient 4 will experience a health event (e.g., heart failure). In some examples, computing system 20 may apply a model to the AF burden of patient 4 over a period of time to determine a risk level of a health event for the patient 4. One or more aspects of an AF burden signal may indicate an increased risk of a health event. These risks may include long episodes of increased AF burden, high mean or median levels of increased AF burden, variability of AF burden over time, or any combination thereof.

[0061] In some examples, variability of AF burden over time is a strong indicator of increased risk of a health event. Computing system 20 may determine, based on parametric data, the AF burden of patient 4 over a period of time. Computing system 20 may calculate an AF burden score corresponding to the period of time. In some examples, the AF burden score may represent a mean AF burden over the period of time, a median AF burden over the period of time, or another score that quantifies AF burden. For example, the AF burden score may represent a sum of AF burden data points over the

12

SUBSTITUTE SHEET (RULE 26) period of time. Computing system 20 may, in some cases, split the period of time into a set of time intervals. For example, if the period of time is two weeks, computing system 20 may split the two weeks into fourteen one-day time intervals. This allows computing system 20 to analyze the AF burden within each individual time interval against the AF burden over the entire period of time. Computing system 20 may calculate an AF burden score corresponding to each time interval of a set of time intervals within the period of time. An AF burden score corresponding to each time interval may indicate a variance of AF burden. That is, when AF burden changes by large margins throughout the set of time intervals, this may indicate a higher risk of a health event.

[0062] One or more occurrences of increased AF burden may also indicate a risk level of a health event. Computing system 20 may identify one or more occurrences over a period of time where the AF burden of patient 4 increases above a threshold AF burden, and determine a duration for each occurrence during which the AF burden remains above the threshold AF burden. Numerous occurrences of increased AF burden and/or long occurrences of increased AF burden may indicate an increased risk of a health event.

[0063] Computing system 20 may identify, based on the parametric data, one or more parameters. For example, computing system 20 may determine AF burden (AFB), day heart rate (DHR), activities of daily living (ADL), night heart rate (NHR), heart rate variability (HRV), or any combination thereof based on the parametric data collected by IMD 10 and/or sensor device 14. Computing system 20 may additionally or alternatively receive patient data corresponding to patient 4. For example, computing system 20 may receive history of AF, history of COPD, CHADS-VASc score, prior oral anticoagulant (prior oac), history of chronic kidney disease, history of ablation, history of sleep apnea, history of coronary artery disease, history of valvular heart disease, or any combination thereof corresponding to the patient 4. Computing system 20 assign weight values to each parameter and/or patient data to determine a risk level of a health event.

[0064] The monitoring system may also utilize data from EMR database 22 and/or data entered by the patient or a caregiver via external device 12 in conjunction with the parametric data from IMD 10 or sensor device 14. In some examples, data from EMR database 22 and/or data entered by the patient or caregiver may be used as inputs to the ML model(s) or other health event prediction algorithms implemented by the monitoring system. In some examples, data from EMR database 22 and/or data entered by the patient

13

SUBSTITUTE SHEET (RULE 26) or caregiver via external device 12 may provide classifications for training sets of parametric data from IMD 10 and sensor device 14 used to train one or more models (e.g., ML models) to predict a health event. For example, data from EMR database 22 and/or data entered by the patient or caregiver via external device 12 may indicate whether, when, and to what degree of severity patient 4 experienced the clinically significant health event. Such data may be correlated with the parametric data to create a training set of parametric data. After an initial training phase, such training sets may be used for reinforcement learning and, in some cases, personalization of the one or more ML models. [0065] Although the techniques are described herein as being performed by a monitoring system, and thus by processing circuitry of computing system 20, the techniques may be performed by processing circuitry of any one or more devices or systems of a medical device system, such as computing system 20, external device 12, or IMD 10. The ML models may include, as examples, neural networks, deep learning models, convolutional neural networks, or other types of predictive analytics systems. [0066] FIG. 2 is a block diagram illustrating an example configuration of IMD 10 of FIG. 1, in accordance with one or more techniques of this disclosure. As shown in FIG. 2, IMD 10 includes processing circuitry 50, sensing circuitry 52, communication circuitry 54, storage device 56, sensors 58, switching circuitry 60, and electrodes 16A, 16B (hereinafter “electrodes 16”), one or more of which may be disposed on a housing of IMD 10. In some examples, storage device 56 includes computer-readable instructions that, when executed by processing circuitry 50, cause IMD 10 and processing circuitry 50 to perform various functions attributed herein to IMD 10 and processing circuitry 50. Storage device 56 may include any volatile, non-volatile, magnetic, optical, or electrical media, such as a random-access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), electrically-erasable programmable ROM (EEPROM), flash memory, or any other digital media.

[0067] Processing circuitry 50 may include fixed function circuitry and/or programmable processing circuitry. Processing circuitry 50 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), or equivalent discrete or analog logic circuitry. In some examples, processing circuitry 50 may include multiple components, such as any combination of one or more microprocessors, one or more

14

SUBSTITUTE SHEET (RULE 26) 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 50 herein may be embodied as software, firmware, hardware or any combination thereof. [0068] Sensing circuitry 52 may be selectively coupled to electrodes 16 A, 16B via switching circuitry 60 as controlled by processing circuitry 50. Sensing circuitry 52 may monitor signals from electrodes 16A, 16B in order to monitor electrical activity of a heart of patient 4 of FIG. 1 and produce ECG data for patient 4. In some examples, processing circuitry 50 may identify features of the sensed ECG, such as heart rate, heart rate variability, intra-beat intervals, and/or ECG morphologic features, to detect an episode of cardiac arrhythmia of patient 4. Processing circuitry 50 may store the digitized ECG and features of the ECG used to detect the arrhythmia episode in storage device 56 as episode data for the detected arrhythmia episode. Processing circuitry 50 may also store parametric data in storage device 56 including features of the ECG and data quantifying arrhythmia episodes, such as AF burden data.

[0069] Sensing circuitry 52 and/or processing circuitry 50 may be configured to detect cardiac depolarizations (e.g., P-waves of atrial depolarizations or R-waves of ventricular depolarizations) when the ECG amplitude crosses a sensing threshold. For cardiac depolarization detection, sensing circuitry 52 may include a rectifier, filter, amplifier, comparator, and/or analog-to-digital converter, in some examples. In some examples, sensing circuitry 52 may output an indication to processing circuitry 50 in response to sensing of a cardiac depolarization. In this manner, processing circuitry 50 may receive detected cardiac depolarization indicators corresponding to the occurrence of detected R-waves and/or P-waves. Processing circuitry 50 may use the indications for determining features of the ECG including inter-depolarization intervals, heart rate, and heart rate variability. Sensing circuitry 52 may also provide one or more digitized ECG signals to processing circuitry 50 for analysis, e.g., for use in cardiac rhythm discrimination and/or to identify and delineate features of the ECG, such as QRS amplitudes and/or width, or other morphological features.

[0070] In some examples, sensing circuitry 52 measures impedance, e.g., of tissue proximate to IMD 10, via electrodes 16. The measured impedance may vary based on respiration and a degree of perfusion or edema. Processing circuitry 50 may determine

15

SUBSTITUTE SHEET (RULE 26) parametric data relating to respiration, perfusion, and/or edema based on the measured impedance.

[0071] In some examples, IMD 10 includes one or more sensors 58, such as one or more accelerometers, microphones, optical sensors, temperature sensors, and/or pressure sensors. In some examples, sensing circuitry 52 may include one or more filters and amplifiers for filtering and amplifying signals received from one or more of electrodes 16A, 16B and/or other sensors 58. In some examples, sensing circuitry 52 and/or processing circuitry 50 may include a rectifier, filter and/or amplifier, a sense amplifier, comparator, and/or analog-to-digital converter. Processing circuitry 50 may determine parametric data, e.g., values of physiological parameters of patient 4, based on signals from sensors 58, which may be stored in storage device 56.

[0072] In some examples, processing circuitry 50 transmits, via communication circuitry 54, the parametric and episode data for patient 4 to external device 12 of FIG. 1, which may transmit the data to network 15 for processing by a monitoring system of computing system 20. Computing system 20 may analyze the parametric data and/or the episode data to perform one or more actions, such as determining a risk of a health event, or determining one or more suggestions for outputting for display by external device 12. Communication circuitry 54 may include any suitable hardware, firmware, software or any combination thereof for communicating with another device, such as external device 12. Under the control of processing circuitry 50, communication circuitry 54 may receive downlink telemetry from, as well as send uplink telemetry to, external device 12 or another device with the aid of an internal or external antenna, e.g., antenna 26.

[0073] Although described herein in the context of example IMD 10, the techniques for cardiac arrhythmia detection disclosed herein may be used with other types of devices. For example, the techniques may be implemented with an extra-cardiac defibrillator coupled to electrodes outside of the cardiovascular system, a transcatheter pacemaker configured for implantation within the heart, such as the Micra™ transcatheter pacing system commercially available from Medtronic PLC of Dublin Ireland, an insertable cardiac monitor, such as the Reveal LINQ ™ICM, also commercially available from Medtronic PLC, a neurostimulator, or a drug delivery device.

[0074] As discussed with respect to FIG. 1, sensor device 14 may be an external device such as a smartwatch, a fitness tracker, patch, or other wearable device. Sensor

16

SUBSTITUTE SHEET (RULE 26) device 14 may be configured similarly to IMD 10 in the sense that it may include electrodes, sensors, sensing circuitry, processing circuitry, memory, and communication circuitry, and may function similarly to collect parametric data and communicate with external device 12. The sensors of and parametric data collected by IMD 10 and sensor device 14 may differ as described herein. Sensor device 14 may transmit parametric data for analysis by computing system 20. Computing system 20 may analyze parametric data from sensor device 14 and/or analyze parametric data from IMD 10.

[0075] FIG. 3 is a conceptual side-view diagram illustrating an example configuration of IMD 10, in accordance with one or more techniques of this disclosure. In the example shown in FIG. 3, IMD 10 may include a leadless, subcutaneously-implantable monitoring device having a housing 18 and an insulative cover 74. Electrode 16A and electrode 16B may be formed or placed on an outer surface of cover 74. Circuitries 50-56 and 60, described above with respect to FIG. 2, may be formed or placed on an inner surface of cover 74, or within housing 18. In the illustrated example, antenna 26 is formed or placed on the inner surface of cover 74, but may be formed or placed on the outer surface in some examples. Sensors 58 may also be formed or placed on the inner or outer surface of cover 74 in some examples. In some examples, insulative cover 74 may be positioned over an open housing 18 such that housing 18 and cover 74 enclose antenna 26, sensors 58, and circuitries 50-56 and 60, and protect the antenna and circuitries from fluids such as body fluids.

[0076] One or more of antenna 26, sensors 58, or circuitries 50-56 may be formed on insulative cover 74, such as by using flip-chip technology. Insulative cover 74 may be flipped onto a housing 18. When flipped and placed onto housing 18, the components of IMD 10 formed on the inner side of insulative cover 74 may be positioned in a gap 76 defined by housing 18. Electrodes 16 may be electrically connected to switching circuitry 60 through one or more vias (not shown) formed through insulative cover 74. Insulative cover 74 may be formed of sapphire (i.e., corundum), glass, parylene, and/or any other suitable insulating material. Housing 18 may be formed from titanium or any other suitable material (e.g., a biocompatible material). Electrodes 16 may be formed from any of stainless steel, titanium, platinum, iridium, or alloys thereof. In addition, electrodes 16 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.

17

SUBSTITUTE SHEET (RULE 26) [0077] Sensors 58 may include any sensor configured to be placed on or within housing 18 of IMD 10. Sensors 58 may include accelerometers, microphones, optical sensors, temperature sensors, or any combination thereof. Sensing circuitry 52 may receive one or more signals from sensors 58. Additionally, or alternatively, sensing circuitry 52 may receive one or more signals from electrodes 16. The one or more signals received by sensing circuitry 52 from electrodes 16 and/or sensors 58 may represent parametric data that indicate one or more parameters of the patient 4.

[0078] FIG. 4 is a block diagram illustrating an example configuration of external device 12, in accordance with one or more techniques of this disclosure. In some examples, external device 12 takes the form of a mobile device, such as a mobile phone, a “smart” phone, a laptop, a tablet computer, or a personal digital assistant (PDA). In some examples, external device 12 is a computing device of patient 4. As shown in the example of FIG. 4, external device 12 includes processing circuitry 80, storage device 82, communication circuitry 84, and a user interface 86. Although shown in FIG. 4 as a standalone device for purposes of example, external device 12 may be any component or system that includes processing circuitry or other suitable computing environment for executing software instructions and, for example, need not necessarily include one or more elements shown in FIG. 4 (e.g., in some examples components such as storage device 82 may not be co-located or in the same chassis as other components).

[0079] Processing circuitry 80, in one example, is configured to implement functionality and/or process instructions for execution within external device 12. For example, processing circuitry 80 may be capable of processing instructions, including applications 90, stored in storage device 82. Examples of processing circuitry 80 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), or equivalent discrete or integrated logic circuitry.

[0080] Storage device 82 may be configured to store information within external device 12, including applications 90 and data 100. Storage device 82, in some examples, is described as a computer-readable storage medium. In some examples, storage device 82 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

18

SUBSTITUTE SHEET (RULE 26) the art. Storage device 82, in one example, is used by applications 90 running on external device 12 to temporarily store information during program execution. Storage device 82, 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 nonvolatile 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.

[0081] External device 12 utilizes communication circuitry 84 to communicate with other devices, such as IMD 10, sensor device 14, and computing system 20 of FIG. 1. Communication circuitry 84 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, and WiFi radios.

[0082] External device 12 also includes a user interface 86. User interface 86 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 86 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.

[0083] Example applications 90 executable by processing circuitry 80 of external device 12 include an IMD interface application 92, a sensor device interface application 94, a health monitor application 96, and a location service 98. Execution of IMD interface 92 by processing circuitry 80 configures external device 12 to interface with IMD 10. For example, IMD interface 92 configures external device 12 to communicate with IMD 10 via communication circuitry 84. Processing circuitry 80 may retrieve IMD data 102 from IMD 10, and store IMD data 102 in storage device 82. IMD interface 92 also configures user interface 86 for a user to interact with IMD 10 and/or IMD data 102. For example, IMD interface 92 configures external device 12 to communicate with IMD 10 via

19

SUBSTITUTE SHEET (RULE 26) communication circuitry 84. Processing circuitry 80 may retrieve IMD data 102 from IMD 10, and store IMD data 102 in storage device 82. IMD interface 92 also configures user interface 86 for a user to interact with IMD 10 and/or IMD data 102. Similarly, sensor device interface 94 configures external device 12 to communicate with sensor device 14 via communication circuitry 84, retrieve sensor device data 104 from sensor device 14, and store sensor device data 104 in storage device 82. Sensor device interface 42 also configures user interface 86 for a user to interact with sensor device 14 and/or sensor device data 104.

[0084] Health monitor 96 may be configured facilitate monitoring the health of patient 4 by a user, such as the patient or a caregiver. Health monitor 96 may present health information, such as at least portions of IMD data 102 and/or sensor device data 104, via user interface 86. Health monitor 96 may also collect information regarding the patient’s health from the user via user interface 86, and store the information as user recorded health data 106. In some examples, health monitor 96 present the user with a questionnaire or survey seeking health data 106 from the user. Health monitor 96 may present the surveys according to a schedule, in response to IMD data 102 and/or sensor device data 104 indicating that patient 4 experienced a health event, and/or based on a location of patient 4, e.g., in response to location service 98 indicating that patient 4 entered a geofence area defined by geofence data 108. Presenting surveys in response to health events may facilitate timely capture of user recorded health data 106 regarding the health event. In some examples, geofence areas are defined around clinics, hospitals, or the like, and entry into a such geofence area may similarly indicate that patient 4 experienced a health event meriting timely collection of user recorded health data 106. Processing circuitry 80 may also store the times and durations of patient entering a geofence area as geofence data 108.

[0085] Processing circuitry 80 may execute health monitor 96 in order to display one or more messages on the user interface 86 that request feedback from patient 4. For example, external device 12 may receive an instruction from computing system 20 to display a request for patient 4 to indicate one or more behaviors. Processing circuitry 80 may execute health monitor 96 to control user interface 86 to display a prompt to select one or more behaviors of a set of behaviors. For example, the prompt may ask the patient 4 whether the patient has engaged in any of the listed behaviors within a period of time.

20

SUBSTITUTE SHEET (RULE 26) User interface 85 may display the set of behaviors such that each behavior of the set of behaviors is associated with a user control that allows the patient 4 to select or deselect the respective behavior. The user interface 85 may also display a submit button that allows the patient 4 to submit the selected behaviors. When processing circuitry 80 receives a selection of one or more behaviors, processing circuitry 80 may output the selection to computing system 20 via communication circuitry 84.

[0086] In some examples, external device 12 may receive, from computing system 20, an instruction to display one or more messages on user interface 86 that represent suggestions for the patient 4 to perform one or more actions. For example, the suggestions may include suggestions to change one or more patient behaviors. Computing system 20 may determine the one or more suggestions based on parametric data collected by IMD 10 and/or sensor device 14, and one or more patient responses to prompts displayed on user interface 86. For example, if external device 12 receives a receives indicating that the patient 4 drinks caffeinated beverages in the mornings, and the parametric data indicates increased AF burden in the mornings, computing system 20 may output an instruction for external device 12 display a suggestion on user interface 86 for the patient to decrease or eliminate caffeine consumption.

[0087] IMD data 102 and sensor device data 104 may include patient parametric data derived from sensed physiological signals as described herein. As examples, IMD data 102 may include periodic (e.g., daily) values of one or more of: heart rate, heart rate variability, one or more ECG morphological features or intrabeat intervals, AF and/or other arrhythmia burden (e.g., number, time, or percent time per period), respiratory rate, perfusion, and activity levels. External device 12 may, in some examples, output some or all of IMD data 102 and sensor device data 104 to computing system 20.

[0088] As examples, sensor device data 104 may include one or more of: activity levels, walking/running distance, resting energy, active energy, exercise minutes, quantifications of standing, body mass, body mass index, heart rate, low, high, and/or irregular heart rate events, heart rate variability, walking heart rate, heart beat series, digitized ECG, blood oxygen saturation, blood pressure (systolic and/or diastolic), respiratory rate, maximum volume of oxygen, blood glucose, peripheral perfusion, and sleep patterns.

21

SUBSTITUTE SHEET (RULE 26) [0089] As examples, user recorded health data 106 may include one or more of: exercise and activity data, sleep data, symptom data, medical history data, quality of life data, nutrition data, medication taking or compliance data, allergy data, demographic data, weight, and height. Symptom data may include times a patient experienced a symptom and their characterizations of the symptoms, such as palpitations, atrial flutter, AF, atrial tachycardia, syncope, or dizziness. Medical history data may relate to history of AF, stroke, chronic obstructive pulmonary disease (COPD), renal dysfunction, or hypertension, history of procedures, such as ablation or cardioversion, and healthcare utilization. Sensor device data 104 and/or user recorded health data 106 may include one or more of the types of data listed in Table 1 below.

22

SUBSTITUTE SHEET (RULE 26)

23

SUBSTITUTE SHEET (RULE 26)

TABLE 1

[0090] FIG. 5 is a block diagram illustrating an example configuration of computing system 20, in accordance with one or more techniques of this disclosure. In the illustrated example, computing system 24 includes processing circuitry 202 for executing applications 220 that include monitoring system 222, machine learning models 224, patient interface system 226, or any other applications described herein. Computing system 20 may be any component or system that includes processing circuitry or other suitable computing environment for executing software instructions and, for example, need not necessarily include one or more elements shown in FIG. 5 (e.g., user interface devices 204, communication circuitry 206; and in some examples components such as storage device(s) 208 may not be co-located or in the same chassis as other components). In some examples, computing system 20 may be a cloud computing system distributed across a plurality of devices.

[0091] In the example of FIG. 5, computing system 24 includes processing circuitry 202, one or more user interface (UI) devices 204, communication circuitry 206, and one or more storage devices 208. Computing system 20, in some examples, further includes one or more application(s) 220 such as monitoring system 222, that are executable by computing system 20.

[0092] Processing circuitry 202, in one example, is configured to implement functionality and/or process instructions for execution within computing system 20. For example, processing circuitry 202 may be capable of processing instructions stored in storage device 208. Examples of processing circuitry 202 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), or equivalent discrete or integrated logic circuitry.

[0093] One or more storage devices 208 may be configured to store information within computing system 20 during operation. Storage device 208, in some examples, is described as a computer-readable storage medium. In some examples, storage device 208 is a temporary memory, meaning that a primary purpose of storage device 208 is not long-

24

SUBSTITUTE SHEET (RULE 26) term storage. Storage device 408, in some examples, is described as a volatile memory, meaning that storage device 408 does not maintain stored contents when the computer is turned off. 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. In some examples, storage device 208 is used by software or applications 220 running on computing system 20 to temporarily store information during program execution.

[0094] Storage devices 208 may further be configured for long-term storage of information, such as applications 220 and data 230. In some examples, storage devices 208 include 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 memories (EEPROM).

[0095] Computing system 20, in some examples, also includes communication circuitry 206 to communicate with other devices and systems, such as IMD 10 and external device 12 of FIG. 1. Communication circuitry 206 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, and WiFi radios.

[0096] Computing system 20, in one example, also includes one or more user interface devices 204. User interface devices 204, in some examples, 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 devices 204 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.

[0097] Applications 220 may also include program instructions and/or data that are executable by processing circuitry 202 of computing system 20 to cause computing system 20 to provide the functionality ascribed to it herein. Example application(s) 220 may

25

SUBSTITUTE SHEET (RULE 26) include monitoring system 222. Other additional applications not shown may alternatively or additionally be included to provide other functionality described herein and are not depicted for the sake of simplicity.

[0098] In accordance with the techniques of the disclosure, computing system 20 receives IMD data 102, sensor device data 104, user recorded health data 106, and geofence data 108 from external device 12 via communication circuitry 206. Processing circuitry 202 stores these as data 230 in storage devices 208.

[0099] Computing system 20 may also receive EMR data 230 from EMR database 22 (FIG. 1) vis communication circuitry 206, and store EMR data 230 in storage device 208. EMR data 230 may include, for each of a plurality of patients or subjects a medication history, a surgical procedure history, a hospitalization history, emergency or urgent care visit history, scheduled clinic visit history, one or more lab or other clinical test results, a procedure history, a cardiovascular history, or co-morbidities such as atrial fibrillation, heart failure, syncope, or diabetes, as examples. As further examples, EMR data 230 may include medical images, such as x-ray images, ultrasound images, echocardiograms, anatomical imagery, medical photographs, radiographic images, etc.

[0100] Monitoring system 222, e.g., implemented by processing circuitry of computing system 20, may implement the techniques of this disclosure including developing an algorithm based on training sets of parametric data, e.g., from IMD data 102 and sensor device data 104, and in some cases user recorded health data 106 and EMR data 230, of a population of patients or subjects, and applying the algorithm to parametric data of an individual patient 4 to predict the occurrence of a clinically significant health event. In some examples, monitoring system 222 trains one or more machine learning (ML) models 224 for prediction of the health event. The output of the ML models for a particular patient may be a level of risk of the health event, e.g., a probability of the health event, a level of risk or probability of the health event occurring within a certain predetermined time period, and/or whether the risk or probability satisfies a threshold.

[0101] The plurality of patient parameters may include AF burden, one or more activity parameters, and/or any of the physiological parameters described herein. In some examples, monitoring system 222 may derive features from the parametric data, and apply the features as inputs to the algorithm, e.g., ML model 224, to determine the risk level. One or more of the features may be AF burden features.

26

SUBSTITUTE SHEET (RULE 26) [0102] One or more of the features may be AF burden pattern features. An AF burden pattern feature may quantify a pattern of AF burden over a plurality of periods including the current period for which monitoring system 222 is determining the risk level. AF burden patterns including a change, e.g., spike or increase, in AF relative to an overall AF burden trend may be associated with an increased risk of a health event, such as a stroke of other clinically significant episode related to cardiovascular health. In some examples, monitoring system 222 determines the AF burden pattern feature by comparing, e.g., determining a difference or ratio between, a current AF burden value and an average, e.g., mean or median, of previous AF burden values. The current value may be a single value for the current period of a shorter-term average of values including the current period and a number of preceding periods. The average value may be a longer-term average of previous values, e.g., including more values and/or values from further in the past, which may not include the current period value. In some examples, the features include a patient activity feature, such as a daily activity level, a daytime or nighttime activity level, or a change in such an activity level relative to a baseline or trend in activity levels.

[0103] In some examples, variability of AF burden may indicate an increased risk of a health event. For example, monitoring system 222 may calculate an AF burden score corresponding to a period of time, and calculate an AF burden score corresponding to each time interval of a set of time intervals within the period of time. Monitoring system 222 may compare the AF burden score corresponding to each time interval of the set of time intervals with the AF burden score corresponding to the period of time. In some cases, monitoring system 222 may determine how much the AF burden score for each time interval differs from the AF burden score for the entire period of time. This may indicate a level of AF burden variability. Higher AF burden variability may indicate an increased risk of a health event occurring.

[0104] Monitoring system 222 may determine, based on the parametric data, an AF burden of the patient 4 over a period of time. The AF burden of patient 4 over the period of time a pattern of increased AF burden in the AF burden of the patient 4 over the period of time.

[0105] Processing circuitry 202 is configured to execute patient interface system 226 in order to output one or more instructions to display information on user interface 86 of external device 12 and receive information from external device 12. In some examples,

27

SUBSTITUTE SHEET (RULE 26) patient interface system 226 may be part of the monitoring system 222 of applications 220. In some examples, patient interface system 226 and monitoring system 222 may be separate applications within applications 220. Patient interface system 226 may, in response to monitoring system 222 detecting a pattern of increased AF burden, output an instruction for external device 12 to display information on user interface 86. The instruction may cause external device 12 to display a set of patient behaviors on user interface 86. In some examples, the set of behaviors are likely to contribute to a pattern of increased AF burden. Patient interface system 226 may receive a response indicating a selection of one or more behaviors from the set of behaviors.

[0106] Based on the response, patient interface system 226 may output, for display by user interface 86 of external device 12, one or more suggestions to change patient behavior. If patient interface system 226 receives a response from external device 12 indicating that patient 4 accepts the suggestion to change behavior, monitoring system 222 may determine whether the pattern of increased AF burden is attenuated or eliminated following the patient 4 accepting the suggestion. In cases where the pattern of increased AF burden remains, patient interface system 226 may output another suggestion to change patient behavior. In some examples, patient interface system 226 may output suggestions in order of how likely the suggestion is to attenuate or eliminate the pattern of increased AF burden. That is, when the most likely cause of the increased AF burden is caffeine consumption, the second most likely cause is Sodium consumption, and the third most likely cause is exercise, patient interface system 226 may output a suggestion to reduce caffeine consumption first. If the suggestion to reduce caffeine consumption does not attenuate or eliminate the pattern of increased AF burden, patient interface system 226 may output a suggestion to reduce Sodium consumption. If the suggestion to reduce Sodium consumption does not attenuate or eliminate the pattern of increased AF burden, patient interface system 226 may output a suggestion to reduce exercise. In some examples, monitoring system 222 may determine a likelihood that each action will reduce AF burden.

[0107] Patient interface system 226 may, in some examples, allow a clinician to output one or more messages to a patient and/or allow a patient to output one or more messages to a clinician. For example, the clinician may output a message to the patient via patient interface system 226 to take one or more medications based on clinician analysis of the

28

SUBSTITUTE SHEET (RULE 26) parametric data. The patient interface system 226 may inform a clinician as to one or more patient conditions (e.g., ablation history, beta block history, or other medical history).

Based on the one or more patient conditions, the physician may output one or more suggestions to the patient using the patient interface system 226. For example, a clinician may advise a patient not to work out in the morning because it increases risk of an adverse health event.

[0108] In general, the health event may be any clinically significant health event. In some examples, the health event may be a cardiovascular event. The health event may be a stroke. In some examples, the health event is a health care utilization event, such as a hospitalization. In some examples, the health event comprises a symptomatic event, such as clinically significant syncope or dizziness.

[0109] Monitoring system 222 may initially train ML model 224 with parametric data collected from one or more populations of patients, e.g., during a clinical study. In conventional clinical studies, one or more human experts review the parametric data and collect other information to classify each of the training sets by endpoint, e.g., as either including the health event or not. In contrast, monitoring system 222 may classify the training sets of parametric data based on classification data 232 collected automatically in response to detection of a trigger, which may reduce the cost or manpower overhead associated with the clinical study.

[0110] In some examples, processing circuitry 202 executing monitoring system 222 collects the classification data 232. In some examples, classification data is additionally or alternatively collected by other processing circuitry of system 2 (FIG. 1), such as processing circuitry 80 of external device 12 (FIG. 4), and received by computing system 20 from the other processing circuitry. Classification data 232 includes data indicative of an endpoint for the training set of parametric data, e.g., indicative of whether the patient experienced the health event or not. Classification data 232 may include data from user recorded health data 106, geofence data 108, and/or EMR data 230 indicative of an endpoint for a patient.

[0111] Any one or more of IMD 10, sensor device 14, external device 12, or computing system 20 may detect the trigger for collection of classification data 232. In some examples, the trigger is a geofence event, e.g., detected by external device 12 indicating that the patient went to a hospital or clinic for a threshold amount of time. In

29

SUBSTITUTE SHEET (RULE 26) such examples, external device 12 or computing system 20 may present a survey to the patient to collect information regarding the visit, e.g., confirming the visit and regarding the health issue(s) addressed, as user recorded health data 106 and classification data 230. [0112] In some examples, the trigger comprises a feature of the parametric data for the patient satisfying a criterion, e.g., indicating that the patient may have experienced the health event. For example, a trigger may be AF burden meeting or exceeding a threshold. Other example triggers may include a feature of any physiological parameter described herein meeting a threshold value. In some examples, the trigger feature may be included within a training set of features used to train ML model 224, e.g., a set of features from which monitoring system 222 may choose to be input features based on their predictive value for the health event. In response to the detection of the trigger feature, monitoring system 222 or other processing circuitry of system 2 may collect classification data 230. The collection of classification data 232 may be via a survey as discussed above, or by checking geofence data 108 and/or EMR data 230 to identify a time proximate hospital or clinic visit indicative of the occurrence of the health event.

[0113] Subsequent to training ML model 224, monitoring system 222 may apply the ML model to parametric data, e.g., IMD data 102 and sensor device data 104, of a particular patient, such as patient 4, to determine a risk level that the patient with experience the health event. In some examples, monitoring system 222 may determine whether risk level of the health event satisfies a criterion, e.g., meets or exceeds a threshold risk level. Monitoring system 222 may take one or more actions based on determining that the risk level satisfied the criterion, e.g., as described with respect to FIG. 8.

[0114] Although the techniques are described herein as being performed by monitoring system 222, and thus by processing circuitry 202 of computing system 20, the techniques may be performed by processing circuitry of any one or more devices or systems of system 2. In some examples, external device 12 may additionally or alternatively implement monitoring system 222, e.g., using ML model 224 trained based on population parametric data and, in some examples, personalized based on parametric data of patient 4. ML model 224 may include, as examples, neural networks, deep learning models, convolutional neural networks, or other types of predictive analytics systems. Furthermore, although the techniques of this disclosure are described primarily with

30

SUBSTITUTE SHEET (RULE 26) respect to examples including ML model 224, in some examples the techniques may be implemented with different models or algorithms that do not necessarily require machine learning, such as linear regression, trend analysis, decision trees, or thresholds, as examples.

[0115] FIG. 6 is a flow diagram illustrating an example technique for training a machine learning model using training sets of parametric data classified based on automatically collected classification data, in accordance with one or more techniques of this disclosure. According to the example illustrated by FIG. 6, monitoring system 222 receives parametric data, such as IMD data 102 and sensor device data 104, of a plurality of patients (300). Monitoring system 222 determines training sets of the parametric data (302). Monitoring system 222 classifies the training sets of parametric data based on automatically collected classification data, as discussed above with reference to FIG. 5 (304). Monitoring system 222 trains ML model 224 with the classified training sets of parametric data (306).

[0116] FIG. 7 is a flow diagram illustrating an example technique for automatically collecting classification data, in accordance with one or more techniques of this disclosure. According to the example of FIG. 7, monitoring system 222 collects parametric data of a patient, e.g., among a plurality of patient during a clinical study and ML model training phase (400). As discussed above with respect to FIG. 5, monitoring system determines whether trigger occurred (402). As discussed above with respect to FIG. 5, example triggers include a feature in the parametric data satisfying a criterion or a geofence event. A geofence event may be an event where a patient is within a geofenced area (e.g., an area near or around a hospital, urgent care clinic, and/or healthcare provider) for longer than a threshold time. The patient being with the geofenced area for longer than a threshold hold time may be evidence of unplanned or planned healthcare utilization. Examples of features in the parametric data satisfying a criterion include AF burden or other features derived from an ECG, e.g., heart rate or heart rate variability, exceeding a threshold, and/or a patient activity feature falling below a threshold. If the trigger did not occur (NO of 402), monitoring system 222 may continue to receive parametric data of the patient and monitor for the trigger (400, 402).

[0117] If the trigger occurs (YES of 402), monitoring system 222 collects classification data 232 (404). As discussed above with respect to FIG. 5, example

31

SUBSTITUTE SHEET (RULE 26) classification data 232 may include user recorded health data 106 from a survey delivered to the patient in response to the trigger, or time proximate geofence data 108 (in the case of a parametric data feature trigger) or EMR data 230 indicating the patient visited a hospital or clinic and, in some cases, that the health event occurred. Monitoring system 222 associates the classification data 232 with the parametric data for eventual classification of a training set of parametric data (406).

[0118] FIG. 8 is a flow diagram illustrating an example technique for predicting a health event and responding to the prediction of the health event, in accordance with one or more techniques of this disclosure. As discussed above, example health events include stroke, hospitalization or other health care utilization, or symptomatic events, such as symptomatic AF or other cardiovascular events.

[0119] According to the example illustrated by FIG. 8, monitoring system 222 receives parametric data, e.g., IMD data 102 and sensor device data 104, for patient 4 (500). Monitoring system 222 applies features derived from the parametric data to ML model 224 (502). As discussed above, the features may include an AF feature, such as an AF burden pattern feature, and, in some cases, a patient activity feature or other feature derived from another physiological signal. Monitoring system 222 determines a risk level of the health event based on the application of the features to ML model 224, e.g., ML model 224 outputs a probability of the health event occurring with a predetermined period of time, such as a number of days. Monitoring system 222 determines whether the risk level of the health event satisfies a criterion, e.g., meets or exceeds a threshold (504). If the risk level does not satisfy the criterion (NO of 504), monitoring system 222 continues to receive parametric data and apply features to ML model 224, e.g., on a period by period basis (500, 502). Based on the risk level satisfying the criterion (YES of 504), monitoring system 222 may perform one or more of the optional actions illustrated by FIG. 8 (506- 512).

[0120] Monitoring system 222 may change a sensing behavior of system 2 (506). For example, monitoring system 222 may direct IMD 10 and/or sensing device 104 to employ more sensitive setting for sensing circuitry 52 or sensors 58, sample physiological signals at a higher rate, and or make periodic measurements at a greater frequency.

[0121] As another example, monitoring system 222 may provide an instruction to patient 4 to take a medication or modify the taking of a medication (508). The medication

32

SUBSTITUTE SHEET (RULE 26) may be an anticoagulant. The instruction may be to take a pro re nata dose of the medication or change a dosage of the medication.

[0122] As another example, monitoring system 222 may prioritize patient 4, or the portions of parametric data associated with the risk level of the health event, in a notification for a clinician treating patient 4 (810). Monitoring system 222 implementing the techniques of this disclosure may advantageously reduce the burden of treating patients by prioritizing patients and/or patient data in their notification from system 2 based on the risk level satisfying a criterion indicating a clinically significant risk of the health event. In some examples, monitoring system 222 reduces burden by determining which rhythms should be transmitted or alerted to the patient and/or clinician, e.g., presents a clinically relevant patient report that adjudicates symptoms.

[0123] As another example, monitoring system 222 may determine a classification for the parametric data associated with the risk level of the health event, and create a training set of parametric data for reinforcement training of ML model 224 and/or personalization of ML model 224 for patient 4, e.g., to create a patient-specific version of ML model 224 (512). Monitoring system 222 may utilize any of the techniques described herein, e.g., with respect to FIG. 7, to collect classification data 232 for classifying the training set of parametric data.

[0124] Health monitor 96 executed by processing circuitry 80 of external device may implement portions of the techniques described with respect to FIGS. 6-8. For example, health monitor 96 may present surveys and collect answers from patient 4, present instructions to take medication to patient 4, and provide enable messaging between patient 4 and a clinician.

[0125] In some examples, in order to enable real-time patient management, health monitor 96 can follow a pre-determined protocol to automatically push patient actions based on specific, detected patterns of parametric data. For example, health monitor 96 may see a predetermined clinically significant degree of AF burden and recommend modifications to a patient’s anti coagulation medication. As discussed above, the actions may additionally or alternatively be pushed based on the risk level of the health event satisfying a criterion. In some examples, computing system 20 may provide an interface for a clinician via a web interface or user interface devices 204 to specify the parametric data features or risk level criterion that would trigger clinical action, e.g., AF duration

33

SUBSTITUTE SHEET (RULE 26) lasting longer than 1 hour or probability of stroke exceeding a threshold probability, and the clinical action that the patient would need to take, such as an up titration of anti coagulation medications. In some examples, health monitor 96 may provide a pro re nata (PRN) medication request. In some examples, health monitor 96 may have a communication tab and also a priority status that would require the action to be acknowledged before allowing patient 4 to move on to other features of health monitor 96, such as viewing parametric data of patient 4.

[0126] FIG. 9 is a flow diagram illustrating an example technique for outputting a suggestion to change patient behavior, in accordance with one or more techniques of this disclosure. FIG. 9 is described with respect to medical device system 2 of FIG. 1. However, the techniques of FIG. 9 may be performed by different components of medical device system 2 or by additional or alternative medical device systems.

[0127] Computing system 20 may receive parametric data of a patient 4 (602). In some examples, the parametric data is generated by one or more sensing devices (e.g., IMD 10 and/or sensor device 14) based on physiological signals of the patient 4 sensed by the one or more sensing devices. In some cases, computing system 20 may identify, based on the parametric data, one or more parameters. For example, computing system 20 may determine AF burden (AFB), day heart rate (DHR), activities of daily living (ADL), night heart rate (NHR), heart rate variability (HRV), or any combination thereof based on the parametric data collected by IMD 10 and/or sensor device 14. Computing system 20 is not limited to determining AFB, DHR, ADL, NHR, and HRV based on the parametric data. Computing system 20 may determine one or more other parameters based on the parametric data.

[0128] When computing system 20 receives the parametric data, computing system 20 may determine an AF burden of the patient 4 over a period of time (604). In some examples, the AF burden of patient 4 over the period of time may represent a time signal that indicates the AF burden of the patient 4 at a sequence of times during over the period of time. In some examples, the AF burden of the patient 4 over the period of time includes a pattern of increased AF burden. Computing system 20 may identify the pattern of increased AF burden. The pattern may, in some cases, include one or more occurrences of increased AF burden. An occurrence of increased AF burden may represent an event where AF burden increases above a threshold AF burden value. In some examples, an

34

SUBSTITUTE SHEET (RULE 26) occurrence of increased AF burden may represent an event where AF burden increases above a threshold AF burden value for more than a threshold amount of time.

[0129] Based on identifying the pattern of increased AF burden, computing system 20 may output a request to identify patient behaviors (606). The patient behaviors may be output for display by a user interface 86 of external device 12. Computing system 20 may output a set of behaviors as a list. The list may present each behavior of the set of behaviors alongside a user control that allows a user to select or deselect the respective behavior. In some examples, the external device 12 may receive an input selecting none of the behaviors. In some examples, the external device 12 may receive an input selecting one of the behaviors. In some examples, the external device 12 may receive an input selecting a combination of more than one of the behaviors. In some examples, the external device 12 may receive an input selecting all of the behaviors.

[0130] The set of behaviors output for display be external device 12 may represent behaviors that are likely to contribute to increased AF burden. These behaviors may include consuming foods and beverages that contain one or more substances (e.g., caffeine, sodium, and potassium). The behaviors may also include activity (e.g., exercise, or another kind of body movement). In some examples, computing system 20 may select the set of behaviors based on a time of day at which occurrences of increased AF burden for patient 4 are more likely to occur. For example, if a pattern of increased AF burden corresponding to patient 4 indicates that increased AF burden frequently occurs in the mornings, computing system 20 may select drinking caffeinated beverages as one of the set of behaviors. Computing system 20 may, in some cases, output the same set of behaviors without regard to the time of increased AF burden.

[0131] Computing system 20 may determine a suggestion to change patient behaviors to attenuate the pattern of increased AF burden (608). For example, when computing system 20 receives a user input indicating one or more behaviors, computing system 20 may output a suggestion to change at least one behavior to attenuate the pattern of increased AF burden in the future. Consuming caffeine, for example, represents a behavior that might contribute to increased AF burden. Computing system 20 may output a suggestion to decrease or eliminate caffeine consumption if the patient 4 indicates that they consumed caffeine during the period of time corresponding to the pattern of increased

35

SUBSTITUTE SHEET (RULE 26) AF burden. Computing system 20 may output, for display by the external device 12, the suggestion (610).

[0132] FIG. 10 is a flow diagram illustrating an example technique for monitoring AF burden following a suggestion to change patient behavior, in accordance with one or more techniques of this disclosure. FIG. 10 is described with respect to medical device system 2 of FIG. 1. However, the techniques of FIG. 10 may be performed by different components of medical device system 2 or by additional or alternative medical device systems. In some examples, the medical device system 2 may perform the techniques of FIG. 10 after performing the techniques of FIG. 9, but this is not required. Medical device system 2 may perform the techniques of FIG. 10 independent of the techniques of FIG. 9.

[0133] Computing system 20 may receive a response indicating that the patient 4 accepts a first suggestion to change patient behavior (612). In some examples, the first suggestion to change patient behavior represents the suggestion output for display by the external device 12 in the techniques of FIG. 9, but this is not required. The first suggestion may represent any suggestion presented to the patient 4 and accepted by the patient 4. In some examples, when computing system 20 outputs a suggestion to change patient behavior, the suggestion may on a user interface with a user control to accept the suggestion. By indicating that the suggestion is accepted, the patient 4 may indicate an intent to change behavior according to the suggestion.

[0134] Based on receiving the response, computing system 20 may determine an AF burden of the patient 4 over a period of time (614). In some examples, the period of time may occur after the patient 4 accepts the first suggestion to change patient behavior. That is, computing system 20 may determine the AF burden of patient 4 following the acceptance of the suggestion to determine whether the suggestion to change patient behavior effectively addressed increased AF burden.

[0135] Computing system 20 may determine whether a pattern of increased AF burden is present during a period of time (616). If the pattern of increased AF burden is not present during the period of time (“NO” at block 616), computing system 20 may determine that the first suggestion successfully attenuated increased AF burden (617). In some examples, computing system 20 identifies a pattern of increased AF burden prior to outputting the first suggestion to change behavior. Computing system 20 may determine that the first suggestion to change behavior was effective based on determining that the

36

SUBSTITUTE SHEET (RULE 26) pattern of increased AF burden is attenuated or nonexistent following the acceptance of the suggestion to change behavior.

[0136] If the pattern of increased AF burden is present during the period of time (“YES” at block 616), computing system 20 may determine a second suggestion to change one or more patient behaviors (618). Computing system 20 may determine that the first suggestion was unsuccessful in attenuating or eliminating the pattern of increased AF burden when the patient indicated an intent to adopt the first suggestion, but the pattern of increased AF burden is still present following the acceptance of the first suggestion. In some cases, computing system 20 may select the second suggestion based on the most likely cause of the pattern of increased AF burden. The first suggestion may have been the most likely cause, but based on determining that the first suggestion was effective, computing system 20 may select the second suggestion to include the next most likely cause other than the first suggestion. Computing system 20 may output the suggestion (620) for display by the user interface 86 of external device 12 (620).

[0137] FIG. 11 is a flow diagram illustrating an example technique for identifying a pattern of increased AF burden, in accordance with one or more techniques of this disclosure. FIG. 11 is described with respect to medical device system 2 of FIG. 1. However, the techniques of FIG. 11 may be performed by different components of medical device system 2 or by additional or alternative medical device systems.

[0138] Computing system 20 may determine, based on parametric data, the AF burden of patient 4 over a period of time. Computing system 20 may analyze the AF burden of patient 4 over the period of time in order to determine whether there is a pattern of increased AF burden. Patterns of increased AF burden may, in some cases, be timedependent. For example, increased AF burden may be more likely to occur for a patient at certain times of day due to one or more behaviors of the patient. Increased AF burden may indicate an increased likelihood of a health event for patient 4. Computing system 20 may identify one or more occurrences of increased AF burden over a period of time (630). In some examples, an occurrence of increased AF burden represents an event where the AF burden of the patient 4 increases above a threshold AF burden value. In some examples, an occurrence of increased AF burden represents an event where the AF burden of the patient 4 increases above a threshold AF burden value for more than a threshold amount of time.

37

SUBSTITUTE SHEET (RULE 26) [0139] Computing system 20 may determine a time of day corresponding to each occurrence of the one or more occurrences (632). In some examples, the one or more occurrences may occur more frequently at certain times of day. For example, for a first patient, the one or more occurrences may occur more frequently in the morning hours, and for a second patient, the one or more occurrences may occur more frequently in the evening hours. The first patient may drink coffee in the mornings, causing increased AF burden, and the second patient may exercise in the evenings, causing increased AF burden. Computing system 20 may determine the time of day corresponding to occurrences of increased AF burden in order to obtain pattern information.

[0140] Additionally, or alternatively, computing system 20 may determine a severity of each occurrence of the one or more occurrences of increase AF burden (634). The severity of an occurrence of increased AF burden may include a duration of the occurrence or a magnitude of the occurrence. The duration may represent an amount of time that the AF burden of the patient remains above an AF burden threshold. The magnitude may include a maximum AF burden of the occurrence, a summation of AF burden values that are greater than the AF burden threshold, or another computation reflecting a level of increased AF burden. Computing system 20 may identify a pattern of increased AF burden based on the time of day corresponding to each occurrence and the severity of each occurrence (636).

[0141] FIG. 12 is a flow diagram illustrating an example technique for determining a risk level of a health event based on the AF burden of a patient over a period of time, in accordance with one or more techniques of this disclosure. FIG. 12 is described with respect to medical device system 2 of FIG. 1. However, the techniques of FIG. 12 may be performed by different components of medical device system 2 or by additional or alternative medical device systems.

[0142] Computing system 20 may receive parametric data of patient 4 (702). In some examples, the parametric data may indicate a plurality of parameters of patient 4. The parametric data may be generated by one or more sensing devices (e.g., IMD 10 and/or sensor device 14) based on physiological signals of the patient sensed by the one or more sensing devices. In some examples, the parametric data may indicate AF burden, day heart rate, activities of daily living, night heart rate, heart rate variability, or any combination thereof.

38

SUBSTITUTE SHEET (RULE 26) [0143] Computing system 20 may determine an AF burden of patient 4 over a period of time based on the parametric data (704). Computing system 20 may apply the AF burden of patient 4 over the period of time to a model (706). In some examples, the model may output, based on the AF burden of patient 4, a risk level. The model may evaluate the AF burden data to determine whether the AF burden data indicates an increased risk of a health event. For example, computing system 20 may determine a risk level of a health event for patient 4 based on application of the AF burden to the model (708). In some examples, the model may determine the risk level based on a variability of AF burden, a magnitude of one or more occurrences of increased AF burden, a duration of one or more occurrences of increased AF burden, or any combination thereof.

[0144] FIG. 13 is a flow diagram illustrating an example technique for determining a risk level of a health event based on AF burden variability, in accordance with one or more techniques of this disclosure. FIG. 13 is described with respect to medical device system 2 of FIG. 1. However, the techniques of FIG. 13 may be performed by different components of medical device system 2 or by additional or alternative medical device systems.

[0145] Variability of a patient’s AF burden over a period of time may be an indicator of increased risk of a health event. In some examples, the variability of AF burden is a stronger indicator of increased risk of a health event than one or more other AF burden parameters (e.g., duration of increased AF burden occurrences, magnitude of increased AF burden occurrences). Consequently, it may be beneficial for computing system 20 to determine a variability of increased AF burden over a period of time in order to evaluate a risk level that the patient 4 will experience a health event.

[0146] Computing system 20 may receive an AF burden of patient 4 over a period of time (710). Computing system 20 may calculate an AF burden score corresponding to the period of time (712). In some examples, the AF burden score may represent a median AF burden or a median AF burden over the period of time. In some examples, the AF burden score may represent a sum of AF burden values over the period of time. The AF burden score corresponding to the period of time may quantify the AF burden over the entire period of time. For example, the AF burden score may be greater when there is a greater amount of AF burden over the period of time, and the AF burden score may be lower when there is a lower amount of AF burden over the period of time.

39

SUBSTITUTE SHEET (RULE 26) [0147] Computing system 20 may calculate an AF burden score corresponding to each time interval of a set of time intervals within the period of time (714). For example, the period of time may be broken up into the set of time intervals. The set of time intervals in succession may comprise the period of time. In some examples, the AF burden score may represent a median AF burden or a median AF burden over the respective time interval. In some examples, the AF burden score may represent a sum of AF burden values over the respective time interval. Computing system 20 may determine an AF score corresponding to each time interval of the set of time intervals so that the AF score for each time interval is comparable against the AF score for the entire period of time.

[0148] For example, computing system 20 may compare the AF burden score corresponding to each time interval of the set of time intervals with the AF burden score corresponding to the period of time (716). In some examples, computing system 20 may determine, for the AF score corresponding to each time interval of the set of time intervals, a difference between the AF burden score for the period of time and the AF score for the respective time interval. Computing system 20 may calculate a sum of the differences in order to determine an extent to which the AF burden scores for the time intervals differ from the baseline AF score for the period of time.

[0149] Computing system 20 may determine a risk level of the patient based on the comparison (718). For example, by comparing the AF burden score corresponding to each time interval of the set of time intervals with the AF burden score corresponding to the period of time, computing system 20 may determine an extent to which the AF burden of the patient 4 varies over time. Higher levels of variability may correspond to a higher risk level. Lower levels of variability may correspond to a lower risk level.

[0150] FIG. 14 is a flow diagram illustrating an example technique for determining a risk level of a health event based on one or more conditions specific to a patient, in accordance with one or more techniques of this disclosure. FIG. 14 is described with respect to medical device system 2 of FIG. 1. However, the techniques of FIG. 14 may be performed by different components of medical device system 2 or by additional or alternative medical device systems.

[0151] Computing system 20 may receive parametric data of patient 4 (802). In some examples, parametric data is generated by one or more sensing devices (e.g., IMD 10 and/or sensor device 14) based on physiological signals of patient 4 sensed by the one or

40

SUBSTITUTE SHEET (RULE 26) more sensing devices. Computing system 20 may determine a set of parameters of patient 4 based on the parametric data (804). These parameters may include, in some examples, AF burden, day heart rate, activities of daily living, night heart rate, heart rate variability, or any combination thereof, but these are not the only parameters that computing system 20 is configured to determine based on the parametric data. Computing system 20 may, in some cases, determine one or more parameters in addition to or alternatively to AF burden, day heart rate, activities of daily living, night heart rate, and heart rate variability. [0152] In some examples, computing system 20 may receive information indicating one or more conditions specific to the patient (806). For example, computing system 20 may receive history of AF, history of COPD, CHADS-VASc score, prior oral anticoagulant (prior oac), history of chronic kidney disease, history of ablation, history of sleep apnea, history of coronary artery disease, history of valvular heart disease, or any combination thereof corresponding to the patient 4. In some examples, computing system 20 may receive one or more conditions of patient 4 in addition to or alternatively to history of AF, history of COPD, CHADS-VASc score, prior oral anticoagulant (prior oac), history of chronic kidney disease, history of ablation, history of sleep apnea, history of coronary artery disease, and history of valvular heart disease.

[0153] Computing system 20 may apply the set of parameters to a model based on the one or more conditions (808). In some examples, to apply the set of parameters to the model, computing system 20 may assign a weight to each parameter of the set of parameters. Each parameter of the set of parameters may have a different amount of affect on a risk level for a health event. For example, AF burden may have a greater effect on the risk level than night heart rate. In this example, the computing system 20 may set a weight of AF burden to be higher than a weight of night heart rate. The one or more patient conditions may affect the weights applied to the one or more parameters. For example, if the patient has a history of ablation, this may affect the weights placed on one or more parameters. In some examples, if the patient has a history of beta blocking, this may change the weight placed on heart rate variability. Computing system 20 may determine a risk level of a health event for the patient 4 (810). The weights applied to the parameters may affect the risk level determined by the computing system 20.

[0154] FIG. 15 is a conceptual diagram illustrating a patient behavior inquiry screen 1000 for display on a user interface of a device, in accordance with one or more

41

SUBSTITUTE SHEET (RULE 26) techniques of this disclosure. As seen in FIG. 15, screen 1000 includes an introductory message 1010 that states “Please select any activities that you engage in between 7AM and 10AM. Screen 1000 includes a first patient behavior 1020, a first user control 1021, a second patient behavior 1022, a second user control 1023, a third patient behavior 1024, a third user control 1023, a fourth patient behavior 1026, a fourth user control 1027, a fifth patient behavior 1028, and a fifth user control 1029. Screen 1000 includes a user control 1030 for submitting selected patient behaviors.

[0155] The patient behaviors 1020, 1022, 1024, 1026, 1028, may represent behaviors that are likely to contribute to increased AF burden. The first patient behavior 1020 may comprise “consuming caffeinated beverages,” the second patient behavior 1022 may comprise “consuming foods or beverages that contain high levels of Sodium,” the third patient behavior 1024 may comprise “consuming foods or beverages that contain high levels of added sugars,” the fourth patient behavior 1026 may comprise “engaging in exercise,” and the fifth patient behavior 1028 may comprise “consuming foods or beverages that contain high levels of Potassium.” In the example of FIG. 15, the user control 1021 corresponding to the first patient behavior 1020 and the user control 1029 corresponding to the fifth patient behavior 1028 are selected, and the other user controls 1023, 1025, 1027 are deselected. This means that if user control 1030 is selected, the device will send information indicating that the patient indicated “consuming caffeinated beverages” and “consuming foods or beverages that contain high levels of Potassium” between 7AM and 10AM.

[0156] FIG. 16 is a conceptual diagram illustrating a first suggestion screen 1100 for display on a user interface of a device, in accordance with one or more techniques of this disclosure. As seen in FIG. 16, the first suggestion screen 1100 includes a first message 1110 that states “Please consider altering your morning routine in the following manner:,” and a second message 1120 that states “consume no more than 5 milligrams (mg) of Caffeine.” The first message 1110 and the second message 1120 may present a suggestion for the patient to limit caffeine consumption. If the patient accepts the suggestion by selecting the “accept” user control 1130, the device may send a message that the patient accepted the suggestion to computing system 20.

[0157] FIG. 17 is a conceptual diagram illustrating a second suggestion screen 1200 for display on a user interface of a device, in accordance with one or more techniques of

42

SUBSTITUTE SHEET (RULE 26) this disclosure. As seen in FIG. 17, the second suggestion screen 1200 includes a first message 1210 that states “Please consider altering your morning routine in the following manner:,” and a second message 1220 that states “Avoid consuming Potassium.” The first message 1210 and the second message 1220 may present a suggestion for the patient to limit potassium consumption. If the patient accepts the suggestion by selecting the “accept” user control 1230, the device may send a message that the patient accepted the suggestion to computing system 20.

[0158] FIG. 18 is a graph illustrating parametric data of a plurality of patient parameters over a time period around a stroke event (time 0), in accordance with one or more techniques of this disclosure. In the example of FIG. 18, the patient parameters include a patient activity parameter (Activities of Daily Living, related to an amount of patient motion exceeding a threshold during daytime hours), heart rate variability (HRV), night heart rate, day heart rate, and time in AF (or AF burden). As can be seen in the illustrated example, time in AF and the heart rate related parameters all increase, and patient activity decreases, in the days leading up to the stroke.

[0159] FIG. 19 is a graph illustrating timeseries values of moving averages of parametric data of a patient parameter, in accordance with one or more techniques of this disclosure. In the example illustrated by FIG. 19, the patient parameter is Activities of Daily Living, although similar techniques may be applied to any other patient parameter described herein. FIG. 19 illustrates a technique for quantifying a feature related to an excursion of a patient parameter from its baseline or trend, which may be indicative of an increased risk of the health event. In some examples, monitoring system 222 summarizes a trend with at least two simple moving averages (SMAs), and uses a comparison or offset of the two SMAs to capture a clinically significant change in the patient parameter. One SMA may be a shorter-term SMA and the other a longer-term SMA, e.g., that includes less recent values of the patient parameter than the shorter term SMA. Patient parameter values occurring within a predetermined number of days of the health event, e.g., stroke, may be identified. Under-sample controls may be 1 : 1 with cases, and all offsets and covariates may be evaluated in one model. Monitoring system 222 may compare goodness-of-fit for each variable (patient parameter) to determine relative importance of the variables.

43

SUBSTITUTE SHEET (RULE 26) [0160] FIG. 20 is a chart illustrating experimentally-determined statistical significances of a plurality of patient parameters in predicting stroke, in accordance with one or more techniques of this disclosure. The patient parameters in the example of FIG. 20 are AF burden (AFB), day heart rate (DHR), activities of daily living (ADL), night heart rate (NHR), and heart rate variability (HRV). The statistical significances illustrated in FIG. 20 were determined based on parametric data collected from a plurality of patients including patients that suffered a stroke. As illustrated in FIG. 20, AF burden was found to be a significantly better predictor of stroke than the other patient parameters.

[0161] The experimental analysis suggested that a change in AF burden occurs within a long-term trend (21+ days) prior to a stroke event. AF burden may be considered the leading predictor in the long-term. More particularly, a growing short-term trend in AF burden within a longer term trend may be predictive of stroke. The predictive ability of AF burden may be 4X greater when acute, shorter-term changes are compared to a longer- term trend.

[0162] FIG. 21 is another chart illustrating experimentally-determined statistical significances of a plurality of patient parameters in predicting stroke, in accordance with one or more techniques of this disclosure. FIG. 21 is similar to FIG. 20, but includes additional patient parameters. In particular, FIG. 21 includes history of AF, CHADS- VASc score, prior oral anticoagulant (prior oac), and history of chronic kidney disease. While FIG. 21 illustrates that prior stroke is 13X more significant of predictor of stroke than AF burden, AF burden is the leading predictor after CHADS-VASc.

[0163] FIGS. 22A-22D are charts illustrating experimentally-determined statistical significances of a plurality of patient parameters in predicting stroke for different patient populations, in accordance with one or more techniques of this disclosure. FIG. 22A illustrates the statistical significances of the plurality of patient parameters in predicting stroke for patients with prior AF ablation. FIG. 22B illustrates the statistical significances of the plurality of patient parameters in predicting stroke for patients with prior AF management. FIG. 22C illustrates the statistical significances of the plurality of patient parameters in predicting stroke for patients with prior stroke. FIG. 22D illustrates the statistical significances of the plurality of patient parameters in predicting stroke for patients in whom AF is suspected by not confirmed.

44

SUBSTITUTE SHEET (RULE 26) [0164] FIGS. 23 A-23D are charts illustrating experimentally-determined statistical significances of a plurality of patient parameters in predicting hospitalization (a subset of health care utilization) for different patient populations, in accordance with one or more techniques of this disclosure. FIG. 23 A illustrates the statistical significances of the plurality of patient parameters in predicting stroke for patients with prior AF ablation. FIG. 23B illustrates the statistical significances of the plurality of patient parameters in predicting stroke for patients with prior AF management. FIG. 23 C illustrates the statistical significances of the plurality of patient parameters in predicting stroke for patients with prior stroke. FIG. 23D illustrates the statistical significances of the plurality of patient parameters in predicting stroke for patients in whom AF is suspected by not confirmed.

[0165] FIG. 24 is a chart illustrating analysis of AF burden pattern features for predicting stroke and health care utilization (HCU), in accordance with one or more techniques of this disclosure. The analysis indicates that for both stroke and HCU, a spike in AF burden, in some cases paired with a low patient activity level, is predictive of the event occurring within a timeframe.

[0166] FIG. 25A and 25B are diagrams illustrating AF burden patterns in patients who experience stroke or a health care utilization event, respectively, for various patient populations, in accordance with one or more techniques of this disclosure. AF burden patterns such as those illustrated in FIGS. 25 A and 25B signal subclinical changes that indicate periods of heightened risk for stroke and HCU.

[0167] A retrospective cohort study of patients with ICMs, including the Reveal LINQ™ ICM, was performed to determine whether rules-based algorithms that examine change from baseline ICM-based parameters can be used to stratify risk of near-term HCU. The occurrence of HCU as a study end point was obtained from deidentified claims data. A patient was labeled as having an occurrence of HCU if their claims history included at least one encounter from an in- or outpatient hospital, emergency room, or ambulatory surgical center with a cardiovascular DRG or diagnosis code. The first occurrence of HCU was recorded if a patient had multiple utilizations.

[0168] ICM-based diagnostic parameters evaluated in the study included daily total AT/AF burden (milliseconds/day), total patient activity, e.g., time with supra-threshold patient motion (minutes/day), average ventricular rate (night and day), and HRV. Patients

45

SUBSTITUTE SHEET (RULE 26) with less than 21 days of daily follow-up after implant, or with a gap in follow-up greater than or equal to 30 days, were excluded from the cohort. Missing data resulting from a gap in daily follow-up was interpolated by forward-filling the last known value for each diagnostic parameter. Follow-up history was limited to two years unless there was an HCU, in which case follow-up ended the day prior to the event. Patients without any devicedetected time in AT/AF within the two-year follow-up period were excluded from the cohort.

[0169] To define diagnostic temporal patterns for the study, each parameter, at each patient follow-up date, was evaluated as a cumulative moving average (CMA) from the day after implant and as an SMA of different historical periods (1, 2, 3, 5, 8, 13, and 21 days) starting 21 days after implant. For the study, offset SMA _a _b denoted the difference between SMA _a and SMAb where the longer period SMA is subtracted from the shorter period SMA (i.e., a < b). An offset of period p with its respective CMA was denoted as SMAp c.

[0170] FIG. 26 is a graph illustrating detected AT/AF time (burden) over the course of a monitoring period, in accordance with one or more techniques of this disclosure. The vertical bars illustrate AF burden (AT/AF time) for sub-periods, in this case days, during which the patient experienced AT/AF. The graph of FIG. 26 further includes three trend lines illustrating, respectively, the CMA of AF burden 600, the 21 -day SMA of AF burden 602, and the difference between the 21 -day SMA and the CMA of AF burden 604.

[0171] For the study, the occurrence of HCU was treated as an unbalanced, binary, classification problem. A recursive partitioning & regression tree algorithm (RP ART) was used to predict which follow-up days had an occurrence of HCU using diagnostic parameters and moving average offsets as predictors. Random sampling methods for imbalanced learning were used within a bootstrapping routine to promote algorithm convergence and to improve classifier accuracy. HCU events were oversampled by labeling the five days prior to an occurrence as an event. For patients who experienced an HCU, follow-up ended on the day prior to the occurrence to prevent the use of device measurements taken on the same day the event happened, a situation that would introduce look ahead bias into the modeling. For each bootstrap iteration:

1. Patients were randomly partitioned into training (70%) and validation (30%) sets.

2. For the training set, non-labeled days were under sampled to equal the number of labeled days.

46

SUBSTITUTE SHEET (RULE 26) 3. A classification tree using 10-fold cross validation was fit on the balanced training set.

4. The model fit in Step 3 was pruned to its minimum cross validation error.

5. Split information from the model fit in Step 4 was saved.

6. The unbalanced validation set was classified using the model fit from Step 4.

7. Classification statistics for each terminal node from Step 6 were saved.

[0172] Each split for a terminal node was recorded as a 3 -tuple, [predictor name, comparison, index], along with its respective HCU rate and patient count for both training and validation sets. Each split was saved as a separate entry if a node had multiple splits. In such a case, the utilization rates and patient counts would be the same for all splits in each node.

[0173] A scatterplot of decision tree terminal nodes showing the relationship between labeled HCU rate and the percent of patients was used to identify patterns in the AF burden classification tree structure that would stratify healthcare event risk. The algorithm for defining these patterns was:

1. Visually identify areas in the scatterplot with a local maximum in patient percent.

2. If the area is unique to Time in AT/AF, define rectangular coordinates for event risk and patient percent that enclose the area.

3. If the area is not unique to Time in AT/AF, then i. Set the upper and lower boundary for patient percent equal to the local maximum ii. Subtract 0.01 from the lower boundary for patient percent. iii. Set the lower and upper boundaries for event rate to the respective locations where the scatterplot intersects with the lower patient percent boundary defined in the preceding step.

4. Select nodes within the rectangular area.

5. Group by the pair [predictor name, comparison],

6. Calculate the number of times each pair is selected, the number of times each pair is selected as a percent of all bootstrapped classification trees, and the mean of [index] values.

7. If the area is not unique to Time in AT/AF, repeat Steps 3.ii - 6 until the modal predictor is selected in at least 10% of all classification trees.

8. Rank order 3-tuples [predictor, comparison, mean index value] in descending order by selection rate.

9. Identify the elbow in selection rate (i.e. where the selection rate drops by approximately 50%).

10. Define an AF burden pattern as the 3-tuples having a selection rate above the elbow point identified in the preceding step.

[0174] Descriptive analyses and tests of equal proportions were performed to compare the odds ratio for AF burden patterns with clinically relevant thresholds for duration and quantity.

47

SUBSTITUTE SHEET (RULE 26) [0175] The bootstrapping routine was run 3,000 times to create an equal number of classification trees. FIG. 27 presents a scatterplot of 50,751 terminal nodes by labeled HCU rate and percent of patients for the balanced training data, in accordance with one or more techniques of this disclosure. A point on a plot represents a unique terminal node. A single node can be represented across diagnostic parameters when its definition includes multiples splits with a different parameter for each split (e.g., time in AT/AF > 1 hour & daily activity < 100 minutes & nighttime heart rate > 80 beats per minute). Three local maxima were identified and denoted as shaded areas A, B and C. Missing (A & C) or infrequent (B) nodes for daily activity and heart rate parameters suggest the areas are largely defined by Time in AT/AF. Area D is derived from the analysis of areas A, B & C and is defined later in the results.

Table 2: Top splits per terminal node distribution for the training data

SUBSTITUTE SHEET (RULE 26) [0176] Table 2 (above) presents a summary of the top five splits by area. Splits with a selection rate above their respective elbow point are in bold. Together, these highlighted splits define the AF burden pattern for a given area. Pattern A is defined by an AF burden CMA less than approximately 1 second. The pattern is present in all 3,000 decision trees and describes the follow-up period prior to the first detection of AT/AF (77% of occurrences) and the period of relative sinus rhythm recovery after device detected AT/AF (23% of occurrences). Pattern C is defined by an AF burden CMA greater than approximately 1 second and an AF burden 21 -day SMA that is approximately greater than its historical average. The pattern is present in 25% of all decision trees and describes a relative spike or increasing trend in daily AF burden. Pattern B is defined by an AF burden CMA greater than approximately 1 second, but unlike pattern C, it has a decreasing AF burden 21 -day SMA that is less than its historical average. The increasing 1 -day SMA (daily burden) relative to the 21 -day SMA suggests that pattern C signals a period of sporadic, below average burden, relative to the patient, that can occur after a period of elevated burden.

[0177] FIG. 28 presents an example graphical illustration of these patterns in AF burden data mapped for a single HCU patient, in accordance with one or more techniques of this disclosure. Labeled HCU rate and patient percent were calculated on the training data for AF burden quantity and duration thresholds. The quantity threshold was defined as daily AF burden greater than 5% (72 minutes); the duration threshold was defined as continuous AF greater than one hour. The log odds event rate was 0.369 and 0.386 and the patient percent was 12.9% and 7.6% for the respective thresholds. Table 2, Area D presents a summary of the top five splits in the terminal node scatterplot where the log odds event rate was greater than 0.369 and the percent of patients was greater than 12.9%. The top three splits define a partial substructure of pattern C where the CMA of daily activity drops below 76 minutes. When applied to a balanced training set, pattern D is selected 10.4% of the time and has a log odds ratio of 0.368, a value that is not statistically different from the other log odds ratios (Poisson regression, p > 0.5 for all threshold coefficients).

[0178] Atrial fibrillation (AF) may be associated with increased risk of healthcare utilization (HCU), which may be triggered by onset of AF or a change in AF burden. Change from baseline of AF burden or other parameters measured by insertable cardiac

49

SUBSTITUTE SHEET (RULE 26) monitors (ICMs) may be useful to predict near-term HCU. One or more ICM parameters can be used to estimate risk of near-term HCU.

[0179] AF burden (total hours per day of AT/AF) may be transformed into simple moving averages (SMAs) of different periods (1, 2, 3, 5, 8, 13, 21 days) for each followup (FU). Cumulative SMA may be calculated for the time between ICM implantation and FU. AF pattern may be defined as the comparison of an SMA period with its cumulative average. The same process may be applied to daily activity recorded by the ICM. HCU may be defined as any encounter from a hospital, emergency room, or ambulatory surgical center with a cardiovascular DRG or diagnosis code.

[0180] An AF burden pattern may reveal distinct groups: (A) no history of AF (reference); (B) below average burden; (C) above average burden; (D) above average burden with low level ICM-detected daily activity. Odds of HCU may be increased in all groups vs reference (B vs A OR 3.82; C vs A OR 8.25; D vs A OR 11.66), including a 33% (212/644) increase in HCU detection over nominal duration & quantity thresholds.

50

SUBSTITUTE SHEET (RULE 26)

Table 3

[0181] Table 3 includes AF burden thresholds for groups A, B, C, and D. Change- from-baseline analyses of ICM-detected AF and ICM-detected daily activity may be strongly associated with near-term HCU, especially high burden coupled with low activity. [0182] FIG. 29 presents a scatterplot of scored terminal nodes by labelled HCU rate and patient percent for the unbalanced validation set, in accordance with one or more techniques of this disclosure. The overall distribution is similar in shape to the training data (FIG. 27). Different shades of col or show different threshold patterns with the lightest shaded points representing nodes not covered by a pattern. AF burden patterns (A-C) provide broad coverage of the terminal node distribution with clear segmentation of event risk (B versus A, odds ratio (OR) 3.82, 95% CI 3.59-4.07; C versus A, OR 8.25, 95% CI 7.84- 8.69). Including a daily activity threshold (D) provides more specific coverage with the greatest risk for HCU among AF burden patterns (D versus A, OR 11.66, 95% CI 10.63- 12.79).

[0183] FIG. 30 presents a Venn diagram of AF burden threshold counts for the validation set. Table 4 (below) presents statistics for each threshold and their mutually exclusive subsets, in accordance with one or more techniques of this disclosure. Approximately 32% (6,594/20,858) of pattern D thresholds are mutually exclusive to quantity and duration thresholds and represent a 33% (212/644) increase in event capture rate. A test for odds ratio differences using Poisson regression showed a statistically significant coeffi cient for the intersection of all three thresholds (p < 0.10); the remaining coefficients were not statistically different (p > 0.10 for all coefficients). Approximately

51

SUBSTITUTE SHEET (RULE 26) 23% of patients experienced just the pattern D threshold at an expected rate of 18.2% of follow-ups, or 66 days per year.

[0184] In Table 4, Count indicates the number of times the threshold was met; Events, the number of labeled HCUs; Odds, the ratio of event count to threshold count divided by the group mean event rate for the validation set; Patients, the number of patients with at least one day meeting the threshold as a percent of total patients in the validation set; Follow-ups, the number of days meeting the threshold as a percent of total follow-up days for patients with at least one occurrence of the threshold. Note: counts are mutually exclusive per follow-up days, not by patient. A patient may experience different thresholds across follow-up days. Therefore, patient and follow-up percents will not sum to 100%.

52

SUBSTITUTE SHEET (RULE 26) [0185] The analysis of AF burden patterns in the study confirm the correlation between increased burden and risk and, more particularly, that a growing trend in AF burden (e.g., daily) over time is associated with a greater risk for HCU, especially when accompanied with a decline in daily activity. Patterns for AF burden amounts less than approximately 1-hour predict healthcare events on par with quantity and duration thresholds greater than 1-hour. AF burden patterns proved additional event capture that complements quantity and duration thresholds. AF burden as a risk factor for HCU is relative to a patient’s historical burden.

[0186] The study illustrates the value of AF burden and patient activity as parametric data from which features may be derived and then applied to an algorithm or model to determine a likelihood of an event, such as an HCU event, as described herein. The features derived from AF burden may include AF burden pattern features, such as a change, e.g., spike or increase, in AF burden relative to an overall AF burden trend. For example, AF burden pattern features may include one or more offsets between SMAs for different look-back periods and/or between an SMA for a look-back period and a CMA. As described herein, the model to which such features are applied may be machine learned or rules-based, e.g., involving decision trees and/or thresholds.

[0187] 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.

[0188] 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

53

SUBSTITUTE SHEET (RULE 26) 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).

[0189] 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), 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.

[0190] The following examples are a non-limiting list of clauses in accordance with one or more techniques of this disclosure.

[0191] Various examples have been described. These and other examples are within the scope of the following claims.

[0192] Example 1. A medical device system comprising: a memory; and processing circuitry in communication with the memory, wherein the processing circuitry is configured to: receive parametric data for a plurality of parameters of a patient, wherein the parametric data is generated by one or more sensing devices based on physiological signals of the patient sensed by the one or more sensing devices; determine, based on the parametric data, an atrial fibrillation (AF) burden of the patient over a period of time, wherein the AF burden of the patient over the period of time includes a pattern of increased AF burden; output, for display by a user device operated by the patient, a request to identify whether the patient engaged in each patient behavior of a set of patient behaviors during the period of time; determine, based on receiving a response indicating that the patient engaged in one or more patient behaviors of the set of patient behaviors, a suggestion to change at least a subset of the one or more patient behaviors to attenuate the pattern of increased AF burden; and output, for display by the user device operated by the patient, the suggestion.

[0193] Example 2. The medical device system of Example 1, wherein the period of time is a first period of time, wherein the suggestion is a first suggestion, and wherein the processing circuitry is further configured to: receive, from the user device, a response indicating that the patient accepts the suggestion to change at least the subset of

54

SUBSTITUTE SHEET (RULE 26) the one or more patient behaviors; determine, based on the parametric data, an AF burden of the patient over a second period of time, wherein the second period of time occurs after the response indicating that the patient accepts the suggestion to change; analyze the AF burden of the patient over the second period of time to determine whether the pattern of increased AF burden is present during the second period of time; determine, based on determining that the pattern of increased AF burden is present during the second period of time, a second suggestion to change at least the subset of the one or more patient behaviors; and output, for display by the user device operated by the patient, the second suggestion.

[0194] Example 3. The medical device system of any of Examples 1-2, wherein to output the request to identify whether the patient engaged in each patient behavior of the set of patient behaviors during the period of time, the processing circuitry is configured to output a list of the set of patient behaviors, wherein each patient behavior of the set of patient behaviors is associated with a user control that is configured to select or deselect the respective patient behavior.

[0195] Example 4. The medical device system of any of Examples 1-3, wherein to determine the suggestion to change at least the subset of the one or more patient behaviors, the processing circuitry is configured to: identify a likelihood that each patient behavior of the one or more patient behaviors contributed to the pattern of increased AF burden; and determine the suggestion to change at least the subset of the one or more patient behaviors based on the likelihood that each patient behavior of the one or more patient behaviors contributed to the pattern of increased AF burden.

[0196] Example 5. The medical device system of any of Examples 1-4, wherein the set of patient behaviors includes one or more of consumption of one or more foods, consumption of one or more beverages, and one or more patient movement activities.

[0197] Example 6. The medical device system of any of Examples 1-5, wherein the processing circuitry is further configured to identify, in the parametric data, the pattern of increased AF burden over the period of time, wherein to identify the pattern of increased AF burden, the processing circuitry is configured to: identify one or more occurrences of increased AF burden over the period of time, wherein each occurrence of the one or more occurrences comprises an event where the AF burden of the patient exceeds an AF burden threshold for greater than a threshold duration of time; determine a

55

SUBSTITUTE SHEET (RULE 26) time of day corresponding to each occurrence of the one or more occurrences; and determine that the one or more occurrences of increased AF burden occur at one or more times of day.

[0198] Example 7. The medical device system of Example 6, wherein the processing circuitry is further configured to select the set of patient behaviors to output to the user device based on the one or more times of day at which the one or more occurrences of increased AF burden are likely to occur.

[0199] Example 8. A medical device system comprising: a memory; and [0200] processing circuitry in communication with the memory, wherein the processing circuitry is configured to: receive parametric data for a plurality of parameters of a patient, wherein the parametric data is generated by one or more sensing devices based on physiological signals of the patient sensed by the one or more sensing devices; determine, based on the parametric data, an atrial fibrillation (AF) burden of the patient over a period of time; apply the AF burden of the patient over the period of time to a model; and determine a risk level of a health event for the patient based on the application of the AF burden of the patient over the period of time to the model.

[0201] Example 9. The medical device system of Example 8, wherein to apply the AF burden of the patient over the period of time to the model, the processing circuitry is configured to: calculate an AF burden score corresponding to the period of time; calculate an AF burden score corresponding to each time interval of a set of time intervals within the period of time; and compare the AF burden score corresponding to each time interval of the set of time intervals with the AF burden score corresponding to the period of time, and wherein the processing circuitry is configured to determine the risk level of the health event for the patient based on comparing the AF burden score corresponding to each time interval of the set of time intervals with the AF burden score corresponding to the period of time.

[0202] Example 10. The medical device system of Example 9, wherein to compare the AF burden score corresponding to each time interval of the set of time intervals with the AF burden score corresponding to the period of time, the processing circuitry is configured to: determine a difference between the AF burden score corresponding to each time interval of the set of time intervals and the AF burden score corresponding to the period of time; and determine, based on the difference between the

56

SUBSTITUTE SHEET (RULE 26) AF burden score corresponding to each time interval of the set of time intervals and the AF burden score corresponding to the period of time, an AF burden deviation score that indicates an extent to which the AF burden of the patient deviates from a baseline AF burden.

[0203] Example 11. The medical device system of Example 10, wherein to determine the AF burden deviation score, the processing circuitry is configured to calculate a sum of each difference between the AF burden score corresponding to each time interval of the set of time intervals and the AF burden score corresponding to the period of time.

[0204] Example 12. The medical device of any of Examples 9-11, wherein a duration of each time interval of the set of time intervals is 24 hours.

[0205] Example 13. The medical device system of any of Examples 8-12, wherein to apply the AF burden of the patient over the period of time to the model, the processing circuitry is configured to: identify a set of time intervals within the period of time; and determine an amount of time for each time interval of the set of time intervals during which the AF burden of the patient is greater than an AF burden threshold, and wherein the processing circuitry is configured to determine the risk level of the health event for the patient based on the amount of time for each time interval of the set of time intervals during which the AF burden of the patient is greater than the AF burden threshold.

[0206] Example 14. The medical device system of any of Examples 8-13, wherein to apply the AF burden of the patient over the period of time to the model, the processing circuitry is configured to: identify one or more occurrences over the period of time during which the AF burden of the patient is greater than an AF burden threshold; and determine a duration of each occurrence of the one or more occurrences, and wherein the processing circuitry is configured to determine the risk level of the health event for the patient based on the amount of time for each time interval of the set of time intervals during which the AF burden of the patient is greater than the AF burden threshold.

[0207] Example 15. The medical device system of any of Example 8-14, wherein to determine the risk level of the health event, the processing circuitry is configured to determine a probability of occurrence of the health event.

57

SUBSTITUTE SHEET (RULE 26) [0208] Example 16. The medical device system of any of Examples 8-15, wherein the risk level comprises a risk that the health event will occur within a predetermined time period.

[0209] Example 17. A medical device system comprising: a memory; and processing circuitry in communication with the memory, wherein the processing circuitry is configured to: receive parametric data for a plurality of parameters of a patient, wherein the parametric data is generated by one or more sensing devices based on physiological signals of the patient sensed by the one or more sensing devices; determine, based on the parametric data, a set of parameters of the patient over a period of time; receive information indicating one or more conditions specific to the patient; set a weight corresponding to each parameter of the set of parameters based on the one or more conditions specific to the patient; apply the set of parameters of the patient over the period of time to a model; and determine a risk level of a health event for the patient based on the application of the set of parameters over the period of time to the model.

[0210] Example 18. The medical device system of Example 17, wherein the one or more conditions specific to the patient include prior medical procedures performed on the patient.

[0211] Example 19. The medical device system of Example 18, wherein the one or more prior medical procedures include ablation.

[0212] Example 20. The medical device system of any of Examples 17-18, wherein the one or more conditions specific to the patient include one or more medications taken by the patient.

58

SUBSTITUTE SHEET (RULE 26)