WO2025196554A1

WO2025196554A1 - Configuration of medical system to review medical device transmissions

Info

Publication number: WO2025196554A1
Application number: PCT/IB2025/052295
Authority: WO
Inventors: Donald R. MUSGROVE; Robert I. WAXMAN; Eric A. Schilling; John C. Doerfler; Rodolphe Katra; Adam J. Black; Brandon D. Stoick; Joseph C. Green
Original assignee: Medtronic Inc
Current assignee: Medtronic Inc
Priority date: 2024-03-18
Filing date: 2025-03-03
Publication date: 2025-09-25
Anticipated expiration: 2026-09-18

Abstract

Techniques are described for facilitating review of medical device transmissions. As an example, a system configured for analyzing implantable medical device (IMD) transmissions, the system comprising: an IMD configured to: sense a physiological signal of a patient; and store physiological data as indicative of an episode based on the physiological signal; and processing circuitry configured to: perform a first review of the physiological data by at least comparing the physiological data to one or more previous transmissions; based on the comparison, determine whether to perform a second review of the physiological data to determine whether the physiological data is indicative of the episode; and based on a determination of the second review that the physiological data is indicative of the episode, send a transmission comprising the physiological data to a user.

Description

CONFIGURATION OF MEDICAL SYSTEM TO REVIEW MEDICAL DEVICE

TRANSMISSIONS

[0001] This application claims the benefit of U.S. Provisional Patent Application Serial No. 63/566,536, filed March 18, 2024, the entire content of which is incorporated herein by reference.

FIELD

[0002] This disclosure generally relates to medical devices and, more particularly, to patient monitoring devices.

BACKGROUND

[0003] A variety of implantable medical devices (IMD) have been clinically implanted or proposed for therapeutically treating or monitoring cardiac, neurological, and/or other conditions of a patient. IMDs may monitor physiological signals of the patient. For example, an IMD may monitor an electrocardiogram (ECG) of the patient to monitor, and in some cases treat arrhythmia conditions. 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 episodes based on the ECG, such as episodes of cardiac tachyarrhythmias. Some IMDs aid in controlling and managing heart rhythm. Such IMDs may transmit device data, e.g., episode data, to allow a user to review the data and investigate patient health. The data may be transmitted to a cloud computing system, which may process the data for analysis and/or presentation to the user.

SUMMARY

[0005] In some examples, users may be tasked with reviewing a high frequency and volume of data, which may hinder adequate review of medical device transmissions and/or place a significant burden on the users. Many transmissions may be unnecessary, e.g., may have no actionable findings, and may increase the burden of transmission analysis. Furthermore, due to the high volume of unnecessary transmissions, users may take longer to identify transmissions with actionable findings, thus delaying therapy and/or adjustments to therapy. [0006] In general, this disclosure describes techniques that may be implemented by a medical device system to review medical device transmissions. More specifically, this disclosure describes techniques that may advantageously reduce the volume and/or user burden associated by review of medical device transmissions. The techniques may be implemented in the medical device and/or other devices of the system, such as an edge computing device or cloud computing system.

[0007] For example, a system comprising an implantable medical device (IMD) may be configured to sense one or more physiological signals, e.g., an electrocardiogram (ECG) signal, of a patient. The IMD may determine whether data derived from the physiological signal(s) is indicative of a potential episode, e.g., whether ECG data is indicative of a potential episode. The IMD may store the physiological data for potential episodes, and later transmit this stored episode data, e.g., to a cloud computing system. In some examples, the IMD may be relatively sensitive to potential episodes. Consequently, the IMD may store and transmit data that does not in fact represent an episode.

[0008] According to the techniques of this disclosure, prior to transmitting the episode data, the IMD may perform a first review of the stored episode data by comparing the episode data to corresponding episode data from one or more previous transmissions. For example, the IMD may compare one or more features from the episode data to one or more corresponding features of the one or more previous transmissions. The previous transmission features may be considered a baseline or trend of the features and may be an average or other statistical representation of corresponding features from multiple previous transmissions.

[0009] If the first review comparison satisfies one or more similarity criteria, a second review of the episode data may be performed. The IMD may attempt to transmit the episode data to an external device/system, e.g., to an edge computing device and/or a cloud computing system. In some examples, the second review is device-based, e.g., if the IMD is unable to establish communication with or otherwise transmit episode data to an external device. In other examples, the second review is cloud-based or edge-based. The second review may be more rigorous than the first review. In some examples, the second review includes application of the episode data to a learning model. Based on the second review being indicative of the episode, the system may send or otherwise present the transmission data for the episode to a user. In some examples, e.g., as part of the second review, the system may also determine a current device state and/or a predicted future device state, e.g., the state of the IMD with respect to its performance in sensing physiological parameters and/or detecting episodes. In some examples, the system may additionally determine a predicted future patient state, such as a predicted adverse event, e.g., an arrhythmic episode or a heart failure event, such as a heart failure decompensation or a heart failure exacerbation. In some examples, the second analysis includes analysis of transmission data other than episode data, e.g., battery or other operational parameters of the IMD. The techniques of this disclosure may reduce the volume of unnecessary transmissions from the IMD, thereby reducing power consumption of the IMD, as well as unnecessary transmission review, thereby increasing efficiency of user analysis.

[0010] In some examples, the system may additionally or alternatively analyze IMD performance by continuously, e.g., on a periodic basis without human intervention, perform a first review of signal data. If the signal data is indicative of a sensing issue, e.g., oversensing, under-sensing, lead fracture, the system may send an alert to a user. Additionally or alternatively, the system may perform a second review of the signal data. In some examples, the second review of the signal data is more complex than the first review. In some examples, the first review is device-based, and the second review is cloud-based. In some examples, the system may initiate the second review regardless of the indication of the first review, e.g., the system may initiate the second review whenever the IMD initiates a transmission. The techniques of this disclosure may result in more prompt identification of sensing issues and may reduce the volume of unnecessary transmissions.

[0011] In some examples, the system may additionally or alternatively increase, decrease, or otherwise adapt the transmission frequency based on user input, such as clinician preferences, patient preferences, patient profile data, and previous transmissions, thereby adapting the transmission frequency to specific patient needs. In some examples, the system may additionally or alternatively adjust transmission content based on user input, such as clinician preferences, e.g., clinician preferences for a particular patient, or particular class or cohort of patients. For example, a clinician may only need a portion of a default transmission to identify episodes, sensing information, etc. The techniques of this disclosure may allow the clinician to adjust transmission content, which may decrease review time. [0012] In some examples, the system adjusts transmissions based on the requestor. For example, if a patient requests information, the system may output a relatively simple representation of the analysis, such as “device functioning normally” or “device functioning abnormally - see clinic,” and if a clinician requests information, the system may output a relatively complex representation of the analysis, which may comprise episode data and other indications.

[0013] As an example, a system configured for analyzing implantable medical device (IMD) transmissions comprises: an IMD configured to: sense a physiological signal of a patient; and store physiological data as indicative of an episode based on the physiological signal; and processing circuitry configured to: perform a first review of the physiological data by at least comparing the physiological data to one or more previous transmissions; based on the comparison, determine whether to perform a second review of the physiological data to determine whether the physiological data is indicative of the episode; and based on a determination of the second review that the physiological data is indicative of the episode, send a transmission comprising the physiological data to a user.

[0014] As another example, an implantable medical device (IMD) comprises: sensing circuitry configured to: sense a physiological signal of a patient; and processing circuitry configured to: store physiological data as indicative of an episode based on the physiological signal; perform a first review of the physiological data by at least comparing the physiological data to one or more previous transmissions; and based on the comparison, determine whether to perform a second review of the physiological data to determine whether the physiological data is indicative of the episode, wherein the transmission comprising the physiological data is sent to the user based on the second review being indicative of the physiological episode.

[0015] As another example, a system for analyzing implantable medical device (IMD) performance comprises: an IMD configured to: sense a signal of a patient; and processing circuitry configured to: determine one or more metrics based on the signal data; perform a first review of the signal data by at least comparing the one or more metrics to one or more corresponding thresholds; based on the comparison, determine whether the signal data is indicative of a sensing issue; responsive to one or more of the first review of the signal data being indicative of the sensing issue or determining to initiate a transmission, perform a second review of the signal data, wherein the second review is more complex than the first review; and based on a determination that the signal data is indicative of the sensing issue, present an indication to a user to adjust the IMD.

[0016] As another example, a method of analyzing implantable medical device (IMD) transmissions comprises: sensing, by sensing circuitry of an IMD, a physiological signal of a patient; and storing, by a memory of the IMD, physiological data indicative of an episode based on the physiological signal; performing, by processing circuitry of a system comprising the IMD, a first review of the physiological data by at least comparing the physiological data to one or more previous transmissions; based on the comparison, determining, by the processing circuitry, whether to perform a second review of the physiological data to determine whether the physiological data is indicative of the episode; and based on a determination of the second review that the physiological data is indicative of the episode, sending, by communication circuitry of the system, a transmission comprising the physiological data to a user.

[0017] As another example, a method comprises: sensing, by sensing circuitry of an implantable medical device (IMD), a physiological signal of a patient; storing, by processing circuitry of the IMD, physiological data as indicative of an episode based on the physiological signal; performing, by the processing circuitry, a first review of the physiological data by at least comparing the physiological data to one or more previous transmissions; and based on the comparison, determining, by the processing circuitry, whether to perform a second review of the physiological data to determine whether the physiological data is indicative of the episode, wherein the transmission comprising the physiological data is sent to the user based on the second review being indicative of the episode.

[0018] As another example, a method for analyzing implantable medical device (IMD) performance comprises: sensing, by sensing circuitry of an IMD, a signal of a patient; determining, by processing circuitry of a system comprising the IMD, one or more metrics based on the signal data; performing, by the processing circuitry, a first review of the signal data by at least comparing the one or more metrics to one or more corresponding thresholds; responsive to one or more of the first review of the signal data being indicative of the sensing issue or determining to initiate a transmission, performing, by the processing circuitry, a second review of the signal data, wherein the second review is more complex than the first review; and based on a determination that the signal data is indicative of the sensing issue, presenting, by the processing circuitry, an indication to a user to adjust the IMD.

[0019] As another example, a non-transitory computer-readable storage medium comprises instructions that, when executed by processing circuitry, cause the processing circuitry to: receive a physiological signal of a patient; store physiological data as indicative of an episode based on the physiological signal; perform a first review of the physiological data by at least comparing the physiological data to one or more previous transmissions; based on the comparison, determine whether to perform a second review of the physiological data to determine whether the physiological data is indicative of the episode; and based on a determination of the second review that the physiological data is indicative of the episode, send a transmission comprising the physiological data to a user. [0020] As another examples, a non-transitory computer-readable storage medium comprises instructions that, when executed by processing circuitry, cause the processing circuitry to: receive a physiological signal of a patient; store physiological data as indicative of an episode based on the physiological signal; perform a first review of the physiological data by at least comparing the physiological data to one or more previous transmissions; and based on the comparison, determine whether to perform a second review of the physiological data to determine whether the physiological data is indicative of the episode, wherein the transmission comprising the physiological data is sent to the user based on the second review being indicative of the episode.

[0021] As another example, a non-transitory computer-readable storage medium comprising instructions that, when executed by processing circuitry, cause the processing circuitry to: receive a signal of a patient; determine one or more metrics based on the signal data; perform a first review of the signal data by at least comparing the one or more metrics to one or more corresponding thresholds; based on the comparison, determine whether the signal data is indicative of a sensing issue; responsive to one or more of the first review of the signal data being indicative of the sensing issue or determining to initiate a transmission, perform a second review of the signal data, wherein the second review is more complex than the first review; and based on a determination that the signal data is indicative of the sensing issue, present an indication to a user to adjust the IMD. [0022] 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

[0023] FIG. 1 illustrates the environment of an example medical device system in conjunction with a patient, in accordance with one or more techniques of this disclosure. [0024] FIGS. 2 A and 2B are conceptual diagrams illustrating example implantable medical devices that operate in accordance with one or more techniques of this disclosure. [0025] FIG. 3 is a block diagram illustrating an example configuration of an implantable medical device that operates in accordance with one or more techniques of the present disclosure.

[0026] FIG. 4 is a block diagram illustrating an example configuration of the computing system of FIG. 1, in accordance with one or more techniques of this disclosure. [0027] FIG. 5 is a flow diagram illustrating an example operation for determining whether to send a transmission to a user, in accordance with one or more techniques of this disclosure.

[0028] FIG. 6 is a flow diagram illustrating an example operation for reviewing episode data and determining whether to send a transmission and/or an alert, in accordance with one or more techniques of this disclosure.

[0029] FIG. 7 is a flow diagram illustrating an example operation for monitoring signal data, in accordance with one or more techniques of this disclosure.

[0030] FIG. 8 is a flow diagram illustrating an example operation for adapting a transmission frequency for a user, in accordance with one or more techniques of this disclosure.

[0031] FIG. 9 is a diagram illustrating example relationships between patient and/or clinician profile information and transmission frequency, in accordance with one or more techniques of this disclosure.

[0032] FIG. 10 is a flow diagram illustrating an example operation for adapting transmission content based on user preferences, in accordance with one or more techniques of this disclosure. [0033] FIG. 11 is a conceptual diagram illustrating an example screen for displaying a notification of a sensing issue to a user, in accordance with one or more techniques of this disclosure.

[0034] FIG. 12 is a conceptual diagram illustrating an example screen for displaying a notification of a cardiac event to a user, in accordance with one or more techniques of this disclosure.

[0035] FIG. 13 is a conceptual diagram illustrating an example machine learning model configured to determine whether to send a transmission.

[0036] FIG. 14 is a conceptual diagram illustrating an example training process for a machine learning model in accordance with examples of the current disclosure.

[0037] FIG. 15 is a flow diagram illustrating an example operation for updating rules for a machine learning model.

[0038] Like reference characters refer to like elements throughout the figures and description.

DETAILED DESCRIPTION

[0039] A variety of types of implantable and external devices are configured to monitor health based on sensed electrocardiograms (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, rings, necklaces, hearing aids, a wearable cardiac monitor or automated external defibrillator (AED), clothing, car seats, or bed linens. Such external devices may facilitate relatively longer- term monitoring of patient health during normal daily activities.

[0040] Implantable medical devices (IMDs) also sense and monitor ECGs and other physiological signals and detect health events such as episodes of arrhythmia, cardiac arrest, myocardial infarction, stroke, and seizure. Example IMDs include pacemakers and implantable cardioverter-defibrillators, which may be coupled to intravascular or extravascular leads, as well as pacemakers with housings configured for implantation within the heart, which may be leadless. Some IMDs do not provide therapy, such as implantable patient monitors. One example of such an IMD is the Reveal LINQ™ or LINQ II™ insertable cardiac monitors (ICMs), available from Medtronic, Inc., which may be inserted subcutaneously. Such IMDs may facilitate relatively longer-term continuous monitoring of patients during normal daily activities, and may periodically or on demand transmit collected data, e.g., episode data for detected arrhythmia episodes or other health episodes, to a remote patient monitoring system, such as the Medtronic CareLink™ Network via a home monitoring system or a smart phone application.

[0041] In some examples, the transmitted data indicative of an episode may not comprise true episodic data. The transmission may be unnecessary, e.g., the transmission may have no actionable findings. In some examples, users analyze the transmissions manually after the system initially detects a potential episode. The user may receive a relatively large volume of transmissions, many of which may be unnecessary transmissions. In some examples, IMDs of a system may have sensing issues, such as oversensing, under-sensing, lead placement issues, lead fracture, etc. The techniques of this disclosure are directed to adapting and automating transmission review to reduce the amount of unnecessary transmission data for human review.

[0042] The techniques of this disclosure may provide one or more technical and clinical advantages. For example, the techniques of this disclosure may be implemented by a system including an IMD that can continuously (e.g., on a periodic basis without human intervention) sense physiological signals while subcutaneously implanted in a patient over months or years to effectively detect potential episodes with high sensitivity, while the system may perform multiple, e.g., 2, reviews of potential episodes to determine whether to a transmission of the episode data will ultimately be reviewed by the user. By performing reviews of the episode data and/or other transmission data, the techniques of this disclosure may decrease IMD power source consumption and/or user burden by decreasing a number of unnecessary transmissions.

[0043] Additionally, the techniques of this disclosure may enable the system to identify the presence of sensing issues and enable a user to respond to such sensing issues. By identifying the presence of sensing issues before user analysis of transmissions, the techniques of this disclosure may facilitate faster and more efficient identification of sensing issues, thereby enabling the user to respond to the sensing issues more quickly, which may improve patient outcomes.

[0044] The techniques of this disclosure may additionally facilitate the review of transmissions by identifying and preventing unnecessary transmissions, which may allow the user to identify actionable findings in other transmissions more efficiently and decrease user burden. Additionally, by adapting transmissions based on, for example clinician preferences, patient preferences, patient profile data, and/or historical patient data, the techniques of this disclosure may result in patient and clinician-specific monitoring, which may decrease user frustration and stress. Additionally, implementing patient-specific monitoring may result in faster issue identification, which may improve patient outcomes.

[0045] FIG. l is a conceptual drawing illustrating an example of a medical device system 2 for collecting, reviewing, and transmitting signal data, e.g., physiological data, in accordance with the 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 Reveal LINQ™ or LINQ II™ insertable cardiac monitor (ICM). Although described primarily in the context of examples in which the medical device that collects episode data 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.

[0046] External device 12 is configured for wireless communication with IMD 10. External device 12 may be configured to communicate with computing system 8 via network 16. In some examples, external device 12 may provide a user interface and allow a user to interact with IMD 10. Computing system 8 may comprise external devices configured to allow a user to interact with IMD 10, or data collected from IMD 10, via network 16.

[0047] External device 12 may be used to retrieve data from IMD 10 and may transmit the data to computing system 8 via network 16. The retrieved data may include episode data collected by IMD 10 and other physiological signals recorded by IMD 10. The episode data may include ECG segments recorded by IMD 10, e.g., due to IMD 10 determining that an episode of arrhythmia or another malady occurred during the segment, or in response to a request to record the segment from patient 4 or another user.

[0048] In some examples, computing system 8 includes one or more handheld external devices, computer workstations, servers or other networked external devices. In some examples, computing system 8 may include one or more devices, including processing circuitry and storage devices, that implement a monitoring system 14. Computing system 8 may comprise a cloud computing system. Computing system 8, network 16, and monitoring system 14 may be implemented by the Medtronic CareLink™ Network or other patient monitoring system, in some examples.

[0049] Monitoring system 14 may analyze episode data received from medical devices, including IMD 10, and direct the episode data to reviewers. Monitoring system 14 may implement machine learning models for analysis of episode data. The machine learning models may include neural networks, deep learning models, convolutional neural networks, or other types of predictive analytics systems.

[0050] Network 16 may include one or more external 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 16 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 16 may provide external devices, such as computing system 8 and IMD 10, access to the Internet, and may provide a communication framework that allows the external devices to communicate with one another. In some examples, network 16 may be a private network that provides a communication framework that allows computing system 8, IMD 10, and/or external device 12 to communicate with one another but isolates one or more of computing system 8, IMD 10, or external device 12 from devices external to network 16 for security purposes. In some examples, the communications between computing system 8, IMD 10, and external device 12 are encrypted.

[0051] Computing system 8 is an example of a computing system configured to receive episode data stored by a medical device of a patient for a potential episode detected by the medical device. Computing system 8 may be managed by a manufacturer of IMD 10 to, for example, provide cloud storage and analysis of collected data, maintenance and software services, or other networked functionality for their devices and users thereof. In the example illustrated by FIG. 1, computing system 8 implements a monitoring system 14. As will be described in greater detail below, monitoring system 14 facilitates detection of episodes of patient 4 and potential sensing issues of IMD 10, and the responses of system 2 to such episodes and sensing issues.

[0052] External device 12 may transmit data, including physiological data retrieved from IMD 10, to computing system 8 via network 16. The physiological data may include episode data, e.g., cardiac data regarding episodes of arrhythmia or other cardiac episodes detected by IMD 10, and other physiological signals or data recorded by IMD 10 and/or external device(s) 12. In some examples, data included in a transmission comprises one or more of episode data or other sensed physiological data, therapy data, and operational parameter data of IMD 10. Monitoring system 14 may also retrieve data regarding patient 4 from one or more sources of electronic health records (EHR) via network 16. EHR may include data regarding historical (e.g., baseline) transmission data, previous health events and treatments, disease states, comorbidities, demographics, height, weight, and body mass index (BMI), as examples, of patients including patient 4. Monitoring system 14 may use data from EHR to configure algorithms implemented by IMD 10, external device 12, and or monitoring system 14 to detect episodes and/or sensing issues for patient 4. In some examples, monitoring system 14 provides data from EHR to external device 12 and/or IMD 10 for storage therein and use as part of their algorithms for detecting episodes and/or sensing issues.

[0053] FIG. 2A is a perspective drawing illustrating an IMD 10A, which may be an example configuration of IMD 10 of FIG. 1 as an ICM. In the example shown in FIG. 2 A, IMD 10A may be embodied as a monitoring device having housing 212, proximal electrode 216A and distal electrode 216B. Housing 212 may further comprise first major surface 214, second major surface 218, proximal end 220, and distal end 222. Housing 212 encloses electronic circuitry located inside the IMD 10A and protects the circuitry contained therein from body fluids. Housing 212 may be hermetically sealed and configured for subcutaneous implantation. Electrical feedthroughs provide electrical connection of electrodes 216A and 216B. [0054] In the example shown in FIG. 2A, IMD 10A is defined by a length /., a width W and thickness or depth D and is in the form of an elongated rectangular prism wherein the length L is much larger than the width W, which in turn is larger than the depth D. In one example, the geometry of the IMD 10A - in particular a width W greater than the depth D - is selected to allow IMD 10A to be inserted under the skin of the patient using a minimally invasive procedure and to remain in the desired orientation during insertion. For example, the device shown in FIG. 2A includes radial asymmetries (notably, the rectangular shape) along the longitudinal axis that maintains the device in the proper orientation following insertion. For example, the spacing between proximal electrode 216A and distal electrode 216B may range from 5 millimeters (mm) to 55 mm, 30 mm to 55 mm, 35 mm to 55 mm, and from 40 mm to 55 mm and may be any range or individual spacing from 5 mm to 60 mm. In addition, IMD 10A may have a length L that ranges from 30 mm to about 70 mm. In other examples, the length L may range from 5 mm to 60 mm, 40 mm to 60 mm, 45 mm to 60 mm and may be any length or range of lengths between about 30 mm and about 70 mm. In addition, the width W of major surface 214 may range from 3 mm to 15, mm, from 3 mm to 10 mm, or from 5 mm to 15 mm, and may be any single or range of widths between 3 mm and 15 mm. The thickness of depth D of IMD 10A may range from 2 mm to 15 mm, from 2 mm to 9 mm, from 2 mm to 5 mm, from 5 mm to 15 mm, and may be any single or range of depths between 2 mm and 15 mm. In addition, IMD 10A according to an example of the present disclosure has a geometry and size designed for ease of implant and patient comfort. Examples of IMD 10A described in this disclosure may have a volume of three cubic centimeters (cm) or less, 1.5 cubic cm or less or any volume between three and 1.5 cubic centimeters.

[0055] In the example shown in FIG. 2A, once inserted within the patient, the first major surface 214 faces outward, toward the skin of the patient while the second major surface 218 is located opposite the first major surface 214. In addition, in the example shown in FIG. 2 A, proximal end 220 and distal end 222 are rounded to reduce discomfort and irritation to surrounding tissue once inserted under the skin of the patient. IMD 10A, including instrument and method for inserting IMD 10A is described, for example, in U.S. Patent Publication No. 2014/0276928, incorporated herein by reference in its entirety.

[0056] Proximal electrode 216A is at or proximate to proximal end 220, and distal electrode 216B is at or proximate to distal end 222. Proximal electrode 216A and distal electrode 216B are used to sense ECG signals thoracically outside the ribcage, which may be sub-muscularly or subcutaneously. ECG signals may be stored in a memory of IMD 10 A, and data may be transmitted via integrated antenna 230 A to another device, which may be another implantable device or an external device, such as external device 12. In some example, electrodes 216A and 216B may additionally or alternatively be used for sensing any bio-potential signal of interest, which may be, for example, an electroencephalogram (EEG), electromyogram (EMG), or a nerve signal, or for measuring impedance, from any implanted location.

[0057] In the example shown in FIG. 2 A, proximal electrode 216A is at or in close proximity to the proximal end 220 and distal electrode 216B is at or in close proximity to distal end 222. In this example, distal electrode 216B is not limited to a flattened, outward facing surface, but may extend from first major surface 214 around rounded edges 224 and/or end surface 226 and onto the second major surface 218 so that the electrode 216B has a three-dimensional curved configuration. In some examples, electrode 216B is an uninsulated portion of a metallic, e.g., titanium, part of housing 212.

[0058] In the example shown in FIG. 2 A, proximal electrode 216A is located on first major surface 214 and is substantially flat, and outward facing. However, in other examples proximal electrode 216A may utilize the three-dimensional curved configuration of distal electrode 216B, providing a three-dimensional proximal electrode (not shown in this example). Similarly, in other examples distal electrode 216B may utilize a substantially flat, outward facing electrode located on first major surface 214 similar to that shown with respect to proximal electrode 216A.

[0059] The various electrode configurations allow for configurations in which proximal electrode 216A and distal electrode 216B are located on both first major surface 214 and second major surface 218. In other configurations, such as that shown in FIG.

2A, only one of proximal electrode 216A and distal electrode 216B is located on both major surfaces 214 and 218, and in still other configurations both proximal electrode 216A and distal electrode 216B are located on one of the first major surface 214 or the second major surface 218 (e.g., proximal electrode 216A located on first major surface 214 while distal electrode 216B is located on second major surface 218). In another example, IMD 10A may include electrodes on both major surface 214 and 218 at or near the proximal and distal ends of the device, such that a total of four electrodes are included on IMD 10A. Electrodes 216A and 216B may be formed of a plurality of different types of biocompatible conductive material, e.g., stainless steel, titanium, platinum, iridium, or alloys thereof, and may utilize one or more coatings such as titanium nitride or fractal titanium nitride.

[0060] In the example shown in FIG. 2A, proximal end 220 includes a header assembly 228 that includes one or more of proximal electrode 216A, integrated antenna 230A, anti-migration projections 232, and/or suture hole 234. Integrated antenna 230A is located on the same major surface (i.e., first major surface 214) as proximal electrode 216A and is also included as part of header assembly 228. Integrated antenna 230A allows IMD 10A to transmit and/or receive data. In other examples, integrated antenna 230 A may be formed on the opposite major surface as proximal electrode 216A or may be incorporated within the housing 212 of IMD 10A. In the example shown in FIG. 2A, antimigration projections 232 are located adjacent to integrated antenna 230A and protrude away from first major surface 214 to prevent longitudinal movement of the device. In the example shown in FIG. 2A, anti-migration projections 232 include a plurality (e.g., nine) small bumps or protrusions extending away from first major surface 214. As discussed above, in other examples anti -migration projections 232 may be located on the opposite major surface as proximal electrode 216A and/or integrated antenna 230A. In addition, in the example shown in FIG. 2A, header assembly 228 includes suture hole 234, which provides another means of securing IMD 10A to the patient to prevent movement following insertion. In the example shown, suture hole 234 is located adjacent to proximal electrode 216A. In one example, header assembly 228 is a molded header assembly made from a polymeric or plastic material, which may be integrated or separable from the main portion of IMD 10 A.

[0061] FIG. 2B is a perspective drawing illustrating another IMD 10B, which may be another example configuration of IMD 10 from FIG. 1 as an ICM. IMD 10B of FIG. 2B may be configured substantially similarly to IMD lOA of FIG. 2A, with differences between them discussed herein.

[0062] IMD 10B may include a leadless, subcutaneously-implantable monitoring device, e.g., an ICM. IMD 10B includes housing having a base 240 and an insulative cover 242. Proximal electrode 216C and distal electrode 216D may be formed or placed on an outer surface of cover 242. Various circuitries and components of IMD 10B may be formed or placed on an inner surface of cover 242, or within base 240. In some examples, a battery or other power source of IMD 10B may be included within base 240. In the illustrated example, antenna 230B is formed or placed on the outer surface of cover 242 but may be formed or placed on the inner surface in some examples. In some examples, insulative cover 242 may be positioned over an open base 240 such that base 240 and cover 242 enclose the circuitries and other components and protect them from fluids such as body fluids. The housing including base 270 and insulative cover 272 may be hermetically sealed and configured for subcutaneous implantation.

[0063] Circuitries and components may be formed on the inner side of insulative cover 242, such as by using flip-chip technology. Insulative cover 242 may be flipped onto a base 240. When flipped and placed onto base 240, the components of IMD 10B formed on the inner side of insulative cover 242 may be positioned in a gap 244 defined by base 240. Electrodes 216C and 216D and antenna 230B may be electrically connected to circuitry formed on the inner side of insulative cover 242 through one or more vias (not shown) formed through insulative cover 242. Insulative cover 242 may be formed of sapphire (i.e., corundum), glass, parylene, and/or any other suitable insulating material. Base 240 may be formed from titanium or any other suitable material (e.g., a biocompatible material). Electrodes 216C and 216D may be formed from any of stainless steel, titanium, platinum, iridium, or alloys thereof. In addition, electrodes 216C and 216D 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.

[0064] In the example shown in FIG. 2B, the housing of IMD 10B defines a length /., a width W and thickness or depth D and is in the form of an elongated rectangular prism wherein the length L is much larger than the width W, which in turn is larger than the depth D, similar to IMD 10A of FIG. 2 A. For example, the spacing between proximal electrode 216C and distal electrode 216D may range from 5 mm to 50 mm, from 30 mm to 50 mm, from 35 mm to 45 mm, and may be any single spacing or range of spacings from 5 mm to 50 mm, such as approximately 40 mm. In addition, IMD 10B may have a length L that ranges from 5 mm to about 70 mm. In other examples, the length L may range from 30 mm to 70 mm, 40 mm to 60 mm, 45 mm to 55 mm, and may be any single length or range of lengths from 5 mm to 50 mm, such as approximately 45 mm. In addition, the width may range from 3 mm to 15 mm, 5 mm to 15 mm, 5 mm to 10 mm, and may be any single width or range of widths from 3 mm to 15 mm, such as approximately 8 mm. The thickness or depth D of IMD 10B may range from 2 mm to 15 mm, from 5 mm to 15 mm, or from 3 mm to 5 mm, and may be any single depth or range of depths between 2 mm and 15 mm, such as approximately 4 mm. IMD 10B may have a volume of three cubic centimeters (cm) or less, or 1.5 cubic cm or less, such as approximately 1.4 cubic cm.

[0065] In the example shown in FIG. 2B, once inserted subcutaneously within the patient, outer surface of cover 242 faces outward, toward the skin of the patient. In addition, as shown in FIG. 2B, proximal end 246 and distal end 248 are rounded to reduce discomfort and irritation to surrounding tissue once inserted under the skin of the patient. In addition, edges of IMD 10B may be rounded.

[0066] FIG. 3 is a block diagram illustrating an example configuration of IMD 10 of FIG. 1. As shown in FIG. 3, IMD 10 includes processing circuitry 350, memory 352, sensing circuitry 354 coupled to electrodes 356A and 356B (hereinafter, “electrodes 356”) and one or more sensor(s) 358, and communication circuitry 360.

[0067] Processing circuitry 350 may include fixed function circuitry and/or programmable processing circuitry. Processing circuitry 350 may include any one or more of a microprocessor, a controller, a graphics processing unit (GPU), a tensor processing unit (TPU), 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 350 may include multiple components, such as any combination of one or more microprocessors, one or more controllers, one or more GPUs, one or more TPUs, 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 350 herein may be embodied as software, firmware, hardware, or any combination thereof. In some examples, memory 352 includes computer-readable instructions that, when executed by processing circuitry 350, cause IMD 10 and processing circuitry 350 to perform various functions attributed herein to IMD 10 and processing circuitry 350. Memory 352 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. [0068] Sensing circuitry 354 may monitor signals from electrodes 356 in order to, for example, monitor electrical activity of a heart of patient 4 and produce ECG data for patient 4. In some examples, processing circuitry 350 may identify features of the sensed ECG, such as heart rate, heart rate variability, T-wave alternans, intra-beat intervals (e.g., QT intervals), and/or ECG morphologic features, to detect an episode of cardiac arrhythmia of patient 4. Processing circuitry 350 may store the digitized ECG and features of the ECG used to detect the episode in memory 352 as physiological data 382 for the detected episode.

[0069] In some examples, IMD 10 includes one or more sensors 358, such as one or more accelerometers, gyroscopes, microphones, optical sensors, temperature sensors, pressure sensors, and/or chemical sensors. In some examples, sensing circuitry 354 may include one or more filters and amplifiers for filtering and amplifying signals received from one or more of electrodes 356 and/or sensors 358. In some examples, sensing circuitry 354 and/or processing circuitry 350 may include a rectifier, filter and/or amplifier, a sense amplifier, comparator, and/or analog-to-digital converter. Processing circuitry 350 may determine physiological data 382, e.g., values of physiological parameters of patient 4, based on signals from sensors 358, which may be stored in memory 352. Patient parameters determined from signals from sensors 358 may include oxygen saturation, glucose level, stress hormone level, heart sounds, body motion, body posture, or blood pressure.

[0070] Memory 352 may store applications 370 executable by processing circuitry 350, and data 380. Applications 370 may include an event surveillance application 372. Processing circuitry 350 may execute event surveillance application 372 to detect potential episodes, e.g., episodes, and/or sensing issues of patient 4 based on a combination of one or more of the types of data described herein, which may be stored as physiological data 382 and/or operational data 388, respectively. In some examples, physiological data 382 can include episode data, e.g., when stored in response to detecting a potential episode. In some examples, physiological data 382 may additionally include physiological data sensed by other devices, e.g., external device(s) 12, and received via communication circuitry 360. In some examples, event surveillance application 372 may be configured with an analysis engine 374. Analysis engine 374 may apply rules 386 to physiological data 382. Rules 386 may include one or more models, algorithms, decision trees, and/or thresholds. In some cases, rules 386 may be developed based on machine learning, e.g., may include one or more machine learning models.

[0071] As examples, event surveillance application 372 may detect a potential episode of SCA, a ventricular fibrillation, a ventricular tachycardia, supra-ventricular tachycardia (e.g., conducted atrial fibrillation), atrial fibrillation or tachycardia, ventricular asystole, a myocardial infarction based on an ECG and/or other patient parameter data indicating the electrical or mechanical activity of the heart of patient 4. In some examples, event surveillance application 372 may detect stroke. In some examples, sensing circuitry 354 may detect brain activity data, e.g., an electroencephalogram (EEG) via electrodes 356, and event surveillance application 372 may detect stroke or a seizure. In some examples, event surveillance application 372 detects whether the patient has fallen based on data from an accelerometer alone, or in combination with other physiological data. In some examples, event surveillance application 372 may additionally detect potential device function issues, such as sensing issues, e.g., oversensing, under-sensing, lead fracture, or loss of capture, and/or battery depletion.

[0072] In some examples, e.g., for a first review following the detection of the potential episode, processing circuitry 350 may be configured to compare physiological data 382, e.g., features of physiological data 382, to baseline transmission data 384 to determine whether to proceed with a transmission of the data, e.g., whether an episode occurred or whether there is a potential sensing issue. Baseline transmission data 384 can comprise feature information extracted from the data of one or more previous transmissions, e.g., including data derived from previously sensed signal(s) for previously identified episodes. Example feature information may include values of physiological parameters derived from previously-sensed physiological signals, such as heart rate, heart rate variability, arrhythmia metrics, patient activity metrics, or perfusion/edema, or outputs from a machine learning model when previous baseline data was input into the model. Additionally, or alternatively, baseline transmission data 384 can comprise unprocessed data, e.g., previously-sensed physiological signal data. In some examples, the comparison requires less energy expenditure by IMD 10 than a transmission.

[0073] When processing circuitry 350 confirms physiological data 382 is indicative of an episode and/or a potential sensing issue during the first review, processing circuitry 350 may initiate a second review. In some examples, processing circuitry 350 may control communication circuitry 360 to transmit physiological data 382, and optionally, operational data 388, e.g., to external device 12, for cloud-based or edge-based processing. If communication circuitry 360 fails to transmit physiological data 382, e.g., due to connectivity issues, processing circuitry 350 may perform a second review of physiological data 382 using event surveillance application 372, which may implement one or more machine learning models. In some examples, the second review may be more rigorous than the first review.

[0074] In some examples, in response to the first review being indicative of an episode and/or a sensing issue, processing circuitry 350 transmits, via communication circuitry 360, physiological data 382 to external device(s) 12 (FIG. 1). This transmission may be included in a message indicating the episode and/or sensing issue, as described herein. Transmission of the message may occur as quickly as possible. Communication circuitry 360 may include any suitable hardware, firmware, software, or any combination thereof for wirelessly communicating with another device, such as external device(s) 12.

[0075] FIG. 4 is a block diagram illustrating an example configuration of computing system 8, in accordance with one or more techniques of this disclosure. In the illustrated example, computing system 8 includes processing circuitry 402 for executing applications 424 that include monitoring system 450 or any other applications described herein.

Computing system 8 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., input devices 404, communication circuitry 406, user interface devices 410, or output devices 412; and in some examples components such as storage device(s) 408 may not be colocated or in the same chassis as other components). In some examples, computing system 8 may be a cloud computing system distributed across a plurality of devices. [0076] In the example of FIG. 4, computing system 8 includes processing circuitry 402, one or more input devices 404, communication circuitry 406, one or more storage device(s) 408, user interface (UI) device(s) 410, and one or more output devices 412. Computing system 8, in some examples, further includes one or more application(s) 424 such as monitoring system 450, and operating system 416 that are executable by computing system 8. Each of components 402, 404, 406, 408, 410, and 412 are coupled (physically, communicatively, and/or operatively) for inter-component communications. In some examples, communication channels 414 may include a system bus, a network connection, an inter-process communication data structure, or any other method for communicating data. As one example, components 402, 404, 406, 408, 410, and 412 may be coupled by one or more communication channels 414.

[0077] Processing circuitry 402, in one example, is configured to implement functionality and/or process instructions for execution within computing system 8. For example, processing circuitry 402 may be capable of processing instructions stored in storage device(s) 408. Examples of processing circuitry 402 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.

[0078] One or more storage device(s) 408 may be configured to store information within computing system 8 during operation. Storage device(s) 408, in some examples, is described as a computer-readable storage medium. In some examples, storage device(s) 408 is a temporary memory, meaning that a primary purpose of storage device(s) 408 is not long-term storage. Storage device(s) 408, in some examples, is described as a volatile memory, meaning that storage device(s) 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(s) 408 is used to store program instructions for execution by processing circuitry 402. Storage device(s) 408, in one example, is used by software or applications 424 running on computing system 8 to temporarily store information during program execution.

[0079] Storage device(s) 408, in some examples, also include one or more computer- readable storage media. Storage device(s) 408 may be configured to store larger amounts of information than volatile memory. Storage device(s) 408 may further be configured for long-term storage of information. In some examples, storage device(s) 408 include nonvolatile 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). [0080] Computing system 8, in some examples, also includes communication circuitry 406 to communicate with other devices and systems, such as IMD 10 and external device 12 of FIG. 1, as well as other networked client external devices of various users. Communication circuitry 406 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 and Wi-Fi radios.

[0081] Computing system 8, in one example, also includes one or more user interface devices 410. User interface devices 410, in some examples, are configured to receive input from a user through tactile, audio, or video feedback. Examples of user interface devices(s) 410 include 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. In some examples, a presence-sensitive display includes a touch- sensitive screen.

[0082] One or more output device(s) 412 may also be included in computing system 8. Output device(s) 412, in some examples, is configured to provide output to a user using tactile, audio, or video stimuli. Output device(s) 412, in one example, includes a presencesensitive display, 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. Additional examples of output device(s) 412 include 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.

[0083] Computing system 8 may include operating system 416. Operating system 416, in some examples, controls the operation of components of computing system 8. For example, operating system 416, in one example, facilitates the communication of one or more applications 424 and monitoring system 450 with processing circuitry 402, communication circuitry 406, storage device(s) 408, input devices 404, user interface devices 410, and output devices 412.

[0084] Applications 424 may also include program instructions and/or data that are executable by computing system 8. Example application(s) 424 executable by computing system 8 may include monitoring system 450. 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.

[0085] In accordance with the techniques of the disclosure, computing system 8 receives episode data and/or signal issue data, e.g., physiological data 382 and, optionally, operational data 388, for episodes and/or issues stored by medical devices, such as IMD 10, via communication circuitry 406, e.g., to perform the second review of physiological data 382, and optionally to review operational data 388 to predict a future device state, e.g., a sensing issue and/or a pacing or other therapy issue. In examples in which predicting a future device state comprises predicted a sensing issue and/or a therapy issue, operational data 388 may include device-reported sensing and therapy (e.g., pacing) trends over time. Processing circuitry 402 may store the physiological data 382, and optionally, operational data 388, in storage device(s) 408. The episode data and/or issue data may have been collected by IMD 10 in response to IMD 10 detecting arrhythmias, sensing issues, and/or user input directing the storage of episode data and/or sensing issue data. In some examples, the processing circuitry 402 may additionally determine a predicted future patient state, such as a predicted adverse event, e.g., an arrhythmic episode, a heart failure event/decompensation, or a heart failure exacerbation based on a second review of data received from IMD 10.

[0086] Monitoring system 450, as implemented by computing system 8 including processing circuitry 402 and storage device(s) 408, controls the review and annotation of the episodes, and generation of reports of the episodes subsequent to the annotation for clinician review. Monitoring system 450 may utilize input devices 404, output devices 412, and/or communication circuitry 406 to direct episode data and/or sensing issue data to one or more human reviewers, e.g., via one or more graphical user interfaces presented on output devices 412 or other client external devices.

[0087] Processing circuitry 402 may apply machine learning models 452 and apply the episode data and/or sensing issue data, e.g., physiological data 382, as inputs to the one or more machine learning models 452. Machine learning models 452 may be configured to output values indicative of the probability that the physiological data 382 includes an episode or not or the probabilities that physiological data 382 includes episodes of certain types that the machine learning models are configured to detect, as examples. In some examples, processing circuitry 402 may additionally apply machine learning models 452 to operational data 388 (alone or in combination with physiological data 382) to predict a future device state and/or output values indicative of the probability that the data represents sensing issues or not, as examples. Processing circuitry 402 may apply configurable thresholds to the probability values to annotate the episode and/or sensing issue as including one or more cardiac episode types, e.g., by providing an indication of an arrhythmia type or other classification if the probability of the classification exceeds a threshold, or sensing issue types, e.g., by providing an indication of suspected issues, e.g., lead issues, oversensing issues, or undersensing issues.

[0088] Machine learning models 452 may also be configured to identify features within physiological data 382, such as depolarizations, and determine whether physiological data 382 is indicative of an episode. Machine learning models 452 may be trained on training episode data sets having known classifications as determined by human reviewers. Additionally or alternatively, machine learning models 452 may be trained on ECG or other physiological signal data sensed and stored by IMD 10 for reasons other than detection of an episode, e.g., presenting/scheduled rhythm data. Machine learning models 452 may include, as examples, neural networks, such as deep neural networks, which may include convolutional neural networks, multi-layer perceptrons, transformers, recurrent neural networks, and/or echo state networks, as examples.

[0089] Monitoring system 450 determines, e.g., during the second review, whether physiological data 382 and, optionally, operational data 388, is indicative of an episode and/or sensing issue. Based on the determination, monitoring system 450 may be configured to select to transmit physiological data 382 and/or operational data 388.

[0090] In some examples, the criteria for reviewing for episodes and/or sensing issues may be user-configurable to present episodes and/or issues of interest, e.g., according to the monitoring requirements or monitoring reasons specified for the clinician, clinic, or patient, with a high degree of confidence of correct classification, and to provide efficient. In some examples, the criteria may customizable, e.g., patient specific.

[0091] FIG. 5 is a flow diagram illustrating an example operation for determining whether to send a transmission and/or an alert to a user, in accordance with one or more techniques of this disclosure. Event surveillance 372 of IMD 10 may initially detect a potential episode and cause processing circuitry 350 to store the episode data as physiological data 382 (500). Processing circuitry 350 may additionally store operational data 388. In some examples, event surveillance 372 may be configured to be more sensitive during initial detection relative to subsequent reviews. Processing circuitry 350 performs a first review of physiological data 382 (501). The first review may comprise comparing baseline transmission data 384 to physiological data 382, e.g., as described in FIG. 3. In some examples the first review may require less energy, e.g., battery power, than transmitting physiological data 382, e.g., to external device 12. Processing circuitry 350 determines whether the one or more criterion for further review, e.g., the second review, are satisfied, e.g., whether physiological data 382 and baseline transmission data 384 meet a difference threshold based on the first review (502). If the criterion is not satisfied (“NO” of 502), the process ends, and processing circuitry 350 may not initiate a transmission. If the criterion is satisfied (“YES” of 502), processing circuitry 350 determines to initiate the second review. In some examples, computing system 8 may perform the second review (504). In other examples, processing circuitry 350 may perform the second review, e.g., if IMD 10 cannot establish a connection to transmit physiological data 382. Processing circuitry 350 of IMD 10 or processing circuitry 402 of computing system 8 may implement machine learning to perform the second review, e.g., as described in FIGS. 3 and 4 herein. Processing circuitry 402 or processing circuitry 350 determines whether, based on the second review, physiological data 382 is indicative of an episode, e.g., an arrhythmia, and/or a sensing issue, e.g., oversensing, under-sensing, or lead issues (506). If physiological data 382 is indicative of an episode and/or a sensing issue (“YES” of 506), processing circuitry 402 or processing circuitry 350 sends one or more of a transmission of physiological data 382 and/or operational data 388 to a user, as well as any annotations or other information identified in the review process, or an alert to seek medical attention to the user (508). The alert may be audible, visual, or tactile. If physiological data 382 is not indicative of an episode and/or a sensing issue (“NO” of 506), the process ends.

[0092] In some examples, processing circuitry 402 and/or processing circuitry 350 may be configured to receive user input comprising user preferences, e.g., via user interface device(s) 410 of computing system 8. Based on the user preferences, processing circuitry 402 and/or processing circuitry 350 may adapt the first review and/or the second review, e.g., to increase user-specificity. [0093] FIG. 6 is a flow diagram illustrating an example operation for reviewing potential cardiac event data and determining whether to send a transmission and/or an alert, in accordance with one or more techniques of this disclosure. In some examples, FIG. 6 may comprise a specific example of FIG. 5. Event surveillance 372 of IMD 10 screens physiological data to detect a potential episode and/or sensing issue (600). Event surveillance 372 may be configured to be more sensitive at step 600 than the reviews. Processing circuitry 350 compares physiological data 382 to previous transmissions, e.g., baseline transmission data 384 (602). In some examples, baseline transmission data 384 comprises a template with feature, i.e., “signature,” information. In some examples, the comparison requires less energy than a transmission. Based on the comparison, processing circuitry 350 determines whether to attempt to initiate a transmission to a device, e.g., external device 12 for cloud-based review, e.g., via computing system 8 (603). If processing circuitry 350 determines not to initiate a transmission to external device 12 (“NO” of 603), the screening process starts again, and IMD 10 may not send a transmission to external device 12. If processing circuitry 350 determines to initiate a transmission to external device 12 (“YES” of 603), processing circuitry 350 controls communication circuitry 360 of IMD 10 (FIG. 3) to attempt to establish a remote connection (604). If communication circuitry 360 successfully establishes a remote connection meeting a connection criterion (“YES” of 606), processing circuitry, e.g., processing circuitry 402 of computing system 8, performs an automated cloud-based review of physiological data 382, which may be similar to the second review of FIG. 5 and may comprise implementing one or more machine learning models (610). In some examples, processing circuitry 402 determines whether remote connection satisfies a connection criterion by determining, for example, whether the remote connection has been established or whether the remote connection has sufficient quality. In some examples, based on the review, processing circuitry 402 predicts a current or future device state of IMD 10, e.g., sensing issues, such as current or impending lead fracture, oversensing, or under-sensing. In some examples, processing circuitry 402 predicts the current or future device state of IMD 10 based on operational data 388, physiological data 382, or a combination of operational data 388 and physiological data 382 (612). Based on the review, processing circuitry 402 determines whether to send a transmission and/or an alert to the user (614). If processing circuitry 402 determines to send the transmission and/or the alert to the user (“YES” of 614), processing circuitry 402 sends the transmission and/or the alert. If processing circuitry 402 determines not to send the transmission and/or the alert to the user (“NO” of 614), processing circuitry 402 initiates documentation of a summary report, e.g., for future analysis (616). If communication circuitry 360 fails to establish a remote connection satisfying the connection criterion (“NO” of 606), processing circuitry 350 performs a device-based review, e.g., IMD 10-based review, of physiological data 382 (608). In some examples, processing circuitry 402 determines the remote connection does not satisfy the connection criterion when circuitry 360 fails to establish the remote connection. In some examples, processing circuitry 402 determines the remote connection does not satisfy the connection criterion when the remote connection does not have sufficient quality. In some examples, the IMD 10-based review may be similar to the second review of FIG. 5 and may implement one or more machine learning models. If processing circuitry 350 determines to initiate an alert (“YES” of 614), e.g., based on the IMD 10-based review being indicative of an episode, processing circuitry 350 may control communication circuitry 360 to alert the patient, e.g., to seek medical attention (618). If processing circuitry 350 determines not to initiate an alert (“NO” of 614), processing circuitry 350 initiates a documentation of a summary report (616).

[0094] FIG. 7 is a flow diagram illustrating an example operation for monitoring signal data, in accordance with one or more techniques of this disclosure. Signal data may comprise one or more of presenting rhythm data, pacing data, or sensing data and may be stored in memory 352 as data 380. In the example of FIG. 7, a device, e.g., IMD 10, collects presenting rhythm data, pacing data, and sensing data (704). In some examples, IMD 10 may collect a subset of the data types. In some examples, the sensing data includes data based on signals sensed via electrodes X and Y and/or sensors 358, such as accelerometer data. Processing circuitry 350 may be configured to initiate regularly scheduled transmissions, e.g., 3 a.m. daily. If processing circuitry 350 determines it is time for a regularly scheduled transmission (“YES” of 706), processing circuitry 350 creates and sends a transmission, e.g., to external device 12, based on the data (720). Processing circuitry 402 of computing system 8 performs an analysis of the data to check for sensing issues (724). Based on the analysis, processing circuitry 402 determines a likelihood of a sensing issue (726). If the likelihood meets a likelihood threshold (“YES” of 728), processing circuitry 402 controls communication circuitry 406 to send an alert to a clinician (718). The clinician may update the programming of IMD 10 or take another action, e.g., contact the patient to schedule a clinic visit, to address the sensing issue (716). In some examples, processing circuitry 402 or processing circuitry 350 may be configured to provide recommended updates for the programming of IMD 10. The clinician may approve, adjust, or reject the recommended updates. If the likelihood does not meet a likelihood threshold (“NO” of 728), the analysis ends, and IMD 10 continues to collect data. If processing circuitry 350 determines it is not time for a regularly scheduled transmission (“NO” of 706), processing circuitry 350 initiates a device-based analysis of the data for sensing issues (708). In some examples, the device-based analysis may be less complex than the computing system based analysis, e.g., to conserve IMD 10 battery life. Based on the analysis, processing circuitry 350 determines a likelihood of a sensing issue (710). If the likelihood meets a likelihood threshold (“YES” of 712), processing circuitry 350 controls communication circuitry 360 to create and send an alert message to a clinician (718). The clinician may update programming of IMD 10 or take another action, e.g., contact the patient to schedule a clinic visit to address the sensing issue (716). In some examples, processing circuitry 402 or processing circuitry 350 may be configured to provide recommended updates for the programming of IMD 10. The clinician may approve, adjust, or reject the recommended updates. If the likelihood does not meet a likelihood threshold (“NO” of 728), the analysis ends, and IMD 10 continues to collect data. By continuously monitoring the data, e.g., rather than only checking for sensing issues at transmission times, the techniques of this disclosure may advantageously facilitate faster identification of sensing issues and remedial action. The techniques may additionally decrease the number of unnecessary transmissions, e.g., by identifying and addressing oversensing and under-sensing.

[0095] FIG. 8 is a flow diagram illustrating an example operation for adapting a transmission frequency for a user, in accordance with one or more techniques of this disclosure. In some examples, the user, e.g., the clinician, may be able to adjust a transmission frequency based on patient information, patient data, clinician preferences, and/or patient preferences. Processing circuitry, e.g., of computing system 8, IMD 10, or another device of system 2 sets a default transmission frequency (800). Processing circuitry 402 of computing system 8 prompts the clinician to select to allow automated adaptive transmission scheduling (802). Processing circuitry 402 receives information and selections from the clinician, e.g., via user interface device(s) 410 (FIG. 4), indicating which factors of a plurality of factors are allowed to impact the adaptive transmission schedule of the patient (804). Based on the clinician selections, processing circuitry 402 updates the transmission frequency (806).

[0096] FIG. 9 is a diagram illustrating example relationships between patient and/or clinician profile information and preferences and transmission frequency, in accordance with one or more techniques of this disclosure. Factors 900 comprise a plurality of factors that may impact transmission frequency. The clinician may input information regarding each of the plurality of factors and make selections for which factor(s) of the plurality of factors can affect transmission frequency. Outputs 902 comprise a plurality of outputs, e.g., to increase transmission frequency from default or to decrease transmission frequency from default, corresponding to each of the plurality of factors. In some examples, the clinician may additionally select a degree of change for each of the plurality of outputs. For example, if the clinician is relatively concerned by a patient comorbidity, the clinician may select to increase the transmission frequency by a relatively large degree. In some examples, some factors may have a higher priority than others.

[0097] In some examples, processing circuitry 402 determines a hierarchy for the importance of each of the factors. The hierarchy may be patient-specific or based on a pool of patients. The clinician may adjust the hierarchy, e.g., to meet clinic preferences or to increase patient-specificity. In other examples, the clinician determines the hierarchy with no input from processing circuitry 402.

[0098] FIG. 10 is a flow diagram illustrating an example operation for adapting transmission content based on user preferences, in accordance with one or more techniques of this disclosure. In some examples, the user, e.g., the clinician or the patient, may request a transmission, e.g., via user interface device(s) 410 or external device 12. Processing circuitry 350 of IMD 10 receives the transmission request or detects a potential episode (1002). Processing circuitry 350 determines whether further analysis is needed, e.g., based on whether physiological data 382 is confirmed as indicative of a potential episode, in accordance with user preferences (1003). If processing circuitry 350 determines not to perform further analysis (“NO” of 1003), the process ends. If processing circuitry 350 determines to perform further analysis (“YES” of 1003), processing circuitry 350 determines whether to transmit physiological data 382 for cloud-based review or to perform device-based review, e.g., to conserve battery power (1004). If processing circuitry determines to transmit physiological data 382 for cloud-based review (“YES” of 1004), processing circuitry 350 controls communication circuitry 360 to establish a remote connection. Responsive to communication circuitry 360 successfully establishing the remote connection, processing circuitry 350 controls communication circuitry 360 to transmit physiological data 382 for automated cloud-based review (1010). If processing circuitry determines not to transmit physiological data 382 for cloud-based review (“NO” of 1004), processing circuitry 350 performs a device-based review (1008). Processing circuitry 360 transmits data to the user for adequate review as determined based on the on- device or cloud-based review and the user preferences (1012).

[0099] The user, e.g., the patient or the clinician may input user preferences, e.g., via user interface device(s) 410. In some examples, the user preferences comprise a selection of a monitoring type. For example, monitoring types may include a relatively high monitoring and data presentation setting, a moderate monitoring and data presentation setting, and a relatively low monitoring and data presentation setting. In some examples, the patient may be able to select from a subset of the monitoring types, e.g., the moderate and low monitoring and data presentation settings, e.g., to prevent patient confusion. [00100] FIG. 11 is a conceptual diagram illustrating an example screen 1100, e.g., of user interface device(s) 410, for displaying a notification of a sensing issue to a user, e.g., the clinician or the patient, in accordance with one or more techniques of this disclosure. Example screen 1100 includes box 1102. Box 1102 comprises a warning indicative of suspected sensing issue box 1104. In this example, the suspected sensing issue comprises a lead issue, e.g., lead fracture. In other examples, the sensing issue may comprise an oversensing issue, an under-sensing issue, etc. In some examples, the user may select sensing issue box 1104 for further information. In the example of a suspected lead fracture, the information may comprise lead information, e.g., operational data 388, and/or physiological data 382 indicative of the lead issue. In the examples of oversensing and under-sensing issues, the information may comprise operational data 388 and/or physiological data 382 indicative of the oversensing or under-sensing issue and a suggested adjustment to system 2, e.g., IMD 10, programming. The information may additionally comprise a likelihood or confidence that the detecting sensing issue is a true sensing issue. In some examples, example screen 1100 may additionally include a graphical visualization of sensing and pacing (or other therapy) trend data (not depicted), e.g., to provide an indication to the clinician regarding the cause of the warning of box 1102.

[0100] FIG. 12 is a conceptual diagram illustrating an example screen 1200, e.g., of user interface device(s) 410, for displaying a notification of a cardiac event to a user, e.g., the clinician or the patient, in accordance with one or more techniques of this disclosure. Screen 1200 comprises episode indication box 1202 and data box 1204. Episode indication box 1202 comprises a summary of findings associated with a transmission, e.g., a patient name, a monitoring type, and a warning of the potential episode. The clinician may be able to select data box 1204 for further For example, the clinician may be able to click data box 1204 to view physiological data 382, which may include a depiction of a rhythm strip corresponding to the potential episode. In some examples, box 1204 includes specific features of the rhythm strip contributing to the potential episode warning, and other information determined during review, such as a likelihood or confidence that the transmission comprises episodic data.

[0101] FIG. 13 is a conceptual diagram illustrating an example machine learning model 1300 configured to determine whether to send a transmission and/or an alert, in accordance with one or more techniques of this disclosure. Machine learning model 1300 is an example of a set of rules, e.g., a set of rules implemented by machine learning models 452 of computing system 8 in wireless communication with IMD 10, or as a set of rules 386 implemented by analysis engine 374 of IMD 10, as discussed above. Machine learning model 1300 is an example of a deep learning model, or deep learning algorithm, trained to determine whether to send a transmission and/or alert based on reviews of physiological data 382. One or more of IMD 10, external device 12, or a computing system 8 may train, store, and/or utilize machine learning model 1300, but other devices may apply inputs associated with a particular patient to machine learning model 1300 in other examples. As discussed above, other types of machine learning and deep learning models or algorithms may be utilized in other examples. For examples, a convolutional neural network model of ResNet-18 may be used. Some non-limiting examples of models that may be used for transfer learning include AlexNet, VGGNet, GoogleNet, ResNet50, DenseNet, transformer models such as bidirectional encoder representations from transformers (BERT) and generative pre-trained transformers (GPT), etc. Some non-limiting examples of machine learning techniques include Support Vector Machines, K-Nearest Neighbor algorithm, and Multi-layer Perceptron.

[0102] As shown in the example of FIG. 13, machine learning model 1300 may include three layers. These three layers include input layer 1302, hidden layers 1304, and output layer 1306. Output layer 1306 comprises the output from the transfer function 1305 of output layer 1306. Input layer 1302 represents each of the input values XI through X4 provided to machine learning model 1300. The number of inputs may be less than or greater than 4, including much greater than 4, e.g., hundreds or thousands. In some examples, the input values may any of the of values input into a machine learning model, as described above. In some examples, input values may include samples of an ECG signal. In addition, in some examples input values of machine learning model 1300 may include additional data, such as data relating to one or more additional parameters of patient 4.

[0103] Each of the input values for each node in the input layer 1302 is provided to each node of hidden layer 1304. In the example of FIG. 13, hidden layers 1304 include two layers, one layer having four nodes and the other layer having three nodes, but fewer or greater number of nodes may be used in other examples. Each input from input layer 1302 is multiplied by a weight and then summed at each node of hidden layers 1304. During training of machine learning model 1300, the weights for each input are adjusted to establish the relationship between the inputs, e.g., physiological data 382, to determining whether a particular set of inputs represents an episode and/or a sensing issue. In some examples, one hidden layer may be incorporated into machine learning model 1300, or three or more hidden layers may be incorporated into machine learning model 1300, where each layer includes the same or different number of nodes.

[0104] The result of each node within hidden layers 1304 is applied to the transfer function of output layer 1306. The transfer function may be linear or non-linear, and in some examples may depend on the number of layers within machine learning model 1300. Example non-linear transfer functions may be a sigmoid function or a rectifier function. The output 1307 of the transfer function may be a classification that indicates whether the particular ECG segment or other input set represents an episode and/or a sensing issue and/or a likelihood or confidence level indicative of an extent to which the input data set represents an episode and/or a sensing issue.

[0105] By applying the ECG signal data and/or other patient parameter data to a machine learning model, such as machine learning model 1300, processing circuitry, such as processing circuitry 402 of computing system 8, is able to determine whether a patient is experiencing or will soon experience an episode or sensing issue with great accuracy, specificity, and sensitivity.

[0106] The architecture of model 1300 is but one example, and other examples may be utilized in implementing the techniques of this disclosure. For example, a machine learning model may include different types of layers, such as pooling layers. As another example, a machine learning model may include features not illustrated in the example of FIG. 13, such as skip connections and weight sharing.

[0107] FIG. 14 is a conceptual diagram illustrating an example training process for a machine learning model 1400 being trained using supervised and/or reinforcement learning techniques, in accordance with one or more techniques of this disclosure. Machine learning model 1400 may be substantially similar to or the same as machine learning model 1300 (FIG. 13). Machine learning model 1400 may be implemented using any number of models for supervised and/or reinforcement learning, such as but not limited to, an artificial neural network, a decision tree, a naive Bayes network, a support vector machine, or a k-nearest neighbor model. In other examples, machine learning model 1400 may be implemented using any number of models for unsupervised learning. In some examples, processing circuitry one or more of IMD 10, external device 12, and/or computing system 8 initially trains the machine learning model 1400 based on training set data 1402 including numerous instances of input data corresponding to episodes, nonepisodes, sensing issues, and non-sensing issues, e.g., as labeled by an expert. A prediction or classification by the machine learning model 1400 may be compared 1404 to the target output 1403, e.g., as determined based on the label. Based on an error signal representing the comparison, the processing circuitry implementing a learning/training function 1405 may send or apply a modification to weights of machine learning model 1400 or otherwise modify/update the machine learning model 1400. For example, one or more of IMD 10, external device 12, and/or computing system 8 may, for each training instance in the training set 1402, modify machine learning model 1400 to change an episode and/or sensing issue status and/or a confidence associate with the status generated by the machine learning model 1400 in response to data applied to the machine learning model 1400.

[0108] FIG. 15 is a flow diagram illustrating an example operation for updating rules for a machine learning model, in accordance with one or more techniques of this disclosure. Processing circuitry 350 of IMD 10 or processing circuitry 402 of computing system 8, alone or in combination, detects an episode and/or sensing issue based on physiological data and sends a transmission (1500). The user provides feedback, e.g., via user interface device(s) 410 of computing system 8, for the episode and/or sensing issue, e.g., true or false. Processing circuitry 402 receives the feedback (1502). Based on the feedback for the episode and/or sensing issue and physiological data 382, processing circuitry 402 determines to update rules, e.g., rules implemented by machine learning model(s) 452 and/or rules 386 implemented by analysis engine 374 (1504).

[0109] Example 1. A system configured for analyzing implantable medical device (IMD) transmissions, the system comprising: an IMD configured to: sense a physiological signal of a patient; and store physiological data as indicative of an episode based on the physiological signal; and processing circuitry configured to: perform a first review of the physiological data by at least comparing the physiological data to one or more previous transmissions; based on the comparison, determine whether to perform a second review of the physiological to determine whether the physiological data is indicative of the episode; and based on a determination of the second review that the physiological data is indicative of the episode, send a transmission comprising the physiological data to a user.

[0110] Example 2. The system of example 1, wherein the physiological data comprises cardiac data.

[0111] Example 3. The system of any one or more of examples 1-2, wherein the processing circuitry comprises processing circuitry of the IMD that performs the first review.

[0112] Example 4. The system of example 3, wherein, based on the comparison, the processing circuitry of the IMD is configured to: establish a remote connection with a computing system; and transmit the physiological data to the computing system, wherein the processing circuitry comprises processing circuitry of the computing system configured to perform the second review of the physiological data. [0113] Example 5. The system of example 4, wherein when the remote connection does not satisfy a connection criterion, the processing circuitry of the IMD is configured to perform the second review of the physiological data.

[0114] Example 6. The system of any one or more of examples 1-5, wherein when the second review results in the determination that the physiological data is indicative of the episode, the patient is advised to seek medical attention.

[0115] Example 7. The system of any one or more of examples 1-6, wherein to perform the second review the processing circuitry is configured to apply the physiological data to a machine learning model.

[0116] Example 8. The system of any one or more of examples 1-7, wherein the user comprises one or more of a patient, a caregiver, a clinician, or an emergency responder.

[0117] Example 9. The system of any one or more of claims 1-8, wherein the processing circuitry is further configured to: determine a predicted future state, wherein the predicted future state comprises one or more of: a predicted future device state, wherein the predicted future device state comprises potential issues with one or more of pacing, sensing, or leads; or a predicted future patient state; and transmit the predicted future state to the user.

[0118] Example 10. The system of any of examples 1-9, wherein the processing circuitry is configured to: based on the second review, determine the physiological data is not indicative of the episode; and based on the physiological data not being indicative of the episode, do not transmit the physiological data to the user.

[0119] Example 11. The system of any of examples 1-10, wherein the processing circuitry is configured to: receive a user preference; and based on the user preference, adapt one or more of the first or second review.

[0120] Example 12. The system of any of examples 1-11, wherein to compare the physiological data to one or more previous transmissions, the processing circuitry is configured to: determine one or more features of the one or more previous transmissions; determine one or more features of the physiological data; and compare features of the physiological data to the features of the previous transmissions.

[0121] Example 13. An implantable medical device (IMD) comprising: sensing circuitry configured to: sense a physiological signal of a patient; and processing circuitry configured to: store physiological data as indicative of an episode based on the physiological signal; perform a first review of the physiological data by at least comparing the physiological data to one or more previous transmissions; and based on the comparison, determine whether to: establish a remote connection with a computing system; and transmit the physiological data to the computing system, for the computing system to perform a second review of the physiological data to determine whether the physiological data is indicative of the episode.

[0122] Example 14. The IMD of example 13, wherein the physiological data comprises cardiac data.

[0123] Example 15. The IMD of any one or more of examples 13-14, wherein the computing system comprises processing circuitry configured to: perform the second review of the physiological data.

[0124] Example 16. The IMD of any one or more of examples 13-15, wherein when the remote connection does not satisfy a connection criterion, the processing circuitry of the IMD is configured to perform the second review of the physiological data. [0125] Example 17. The IMD of any one or more of examples 13-16, wherein when the second review results in the determination that the physiological data is indicative of a episode, the patient is advised to seek medical attention.

[0126] Example 18. The IMD of any one or more of examples 13-17, wherein to perform the second review the processing circuitry is configured to apply the physiological data to a machine learning model.

[0127] Example 19. The IMD of any one or more of examples 13-18, wherein the user comprises one or more of a patient, a caregiver, a clinician, or an emergency responder.

[0128] Example 20. A system for analyzing implantable medical device (IMD) performance, the system comprising: an IMD configured to: sense a signal of a patient; and processing circuitry configured to: determine one or more metrics based on the signal data; perform a first review of the signal data by at least comparing the one or more metrics to one or more corresponding thresholds; based on the comparison, determine whether the signal data is indicative of a sensing issue; responsive to one or more of the first review of the signal data being indicative of the sensing issue or determining to initiate a transmission, perform a second review of the signal data, wherein the second review is more complex than the first review; and based on a determination that the signal data is indicative of the sensing issue, present an indication to a user to adjust the IMD. [0129] Example 21. The system of example 20, wherein the potential sensing issue comprises under-sensing, oversensing, or lead fracture.

[0130] Example 22. The system of any one or more of examples 20-21, wherein the first review is performed on the IMD, and the second review is cloud-based.

[0131] Example 23. The system of any of examples 20-22, wherein the one or more corresponding thresholds are based on baseline data or trend data.

[0132] Example 24. The system of any one or more of examples 20-23, wherein to perform one or more of the first review or the second review, the processing circuitry is configured to apply the signal data to a machine learning model.

[0133] Example 25. A method of analyzing implantable medical device (IMD) transmissions, the method comprising: sensing, by sensing circuitry of an IMD, a physiological signal of a patient; and storing, by a memory of the IMD, physiological data indicative of an episode based on the physiological signal; performing, by processing circuitry of a system comprising the IMD, a first review of the physiological data by at least comparing the physiological data to one or more previous transmissions; based on the comparison, determining, by the processing circuitry, whether to perform a second review of the physiological data to determine whether the physiological data is indicative of the episode; and based on a determination of the second review that the physiological data is indicative of the episode, sending, by communication circuitry of the system, a transmission comprising the physiological data to a user.

[0134] Example 26. The method of example 25, wherein the physiological data comprises cardiac data.

[0135] Example 27. The method of any one or more of examples 25-26, wherein the processing circuitry that performs the first review comprises processing circuitry of the IMD.

[0136] Example 28. The method of example 27, further comprising: based on the comparison, establishing, by the processing circuitry of the IMD, a remote connection with a computing system; and transmitting, by the processing circuitry, the physiological data to the computing system, wherein the processing circuitry comprises processing circuitry of the computing system configured to perform the second review of the physiological data.

[0137] Example 29. The method of example 28, further comprising: based on the remote connection not satisfying a connection criterion, performing, by the processing circuitry of the IMD, the second review of the physiological data.

[0138] Example 30. The method of any one or more of examples 25-29, wherein when the second review results in the determination that the physiological data is indicative of the episode, the patient is advised to seek medical attention.

[0139] Example 31. The method of any one or more of examples 25-30, wherein performing one or more of the first review or the second review comprising applying, by the processing circuitry, the physiological data to a machine learning model.

[0140] Example 32. The method of any one or more of examples 25-31, wherein the user comprises one or more of a patient, a caregiver, a clinician, or an emergency responder.

[0141] Example 33. The method of any one or more of examples 25-32, further comprising: determining, by the processing circuitry, a predicted future state, wherein the predicted future device state comprises one or more of: a predicted future device state, wherein the predicted future device state comprises potential issues with one or more of pacing, sensing, or leads; or a predicted future patient state; and transmitting, by the processing circuitry, the predicted future state to the user.

[0142] Example 34. The method of any one or more of examples 25-33, further comprising: based on the second review, determining, by the processing circuitry, the physiological data is not indicative of the episode; and based on the physiological data not being indicative of the episode, by the processing circuitry, not transmitting the physiological data to the user.

[0143] Example 35. The method of any one or more of examples 25-34, further comprising; receive, by the processing circuitry, a user preference; and based on the user preference, adapting, by the processing circuitry, one or more of the first or second review. [0144] Example 36. The method of any of examples 25-35, wherein comparing the physiological data to one or more previous transmissions comprises: determining, by the processing circuitry, one or more features of the one or more previous transmissions; determining, by the processing circuitry, one or more features of the physiological data; and comparing, by the processing circuitry, features of the physiological data to the features of the previous transmissions.

[0145] Example 37. A method comprising: sensing, by sensing circuitry of an implantable medical device (IMD), a physiological signal of a patient; storing, by processing circuitry of the IMD, physiological data as indicative of an episode based on the physiological signal; performing, by the processing circuitry, a first review of the physiological data by at least comparing the physiological data to one or more previous transmissions; and based on the comparison, determining, by the processing circuitry, whether to perform a second review of the physiological data to determine whether the physiological data is indicative of the episode, wherein the transmission comprising the physiological data is sent to the user based on the second review being indicative of the episode.

[0146] Example 38. The method of example 37, wherein the physiological data comprises cardiac data.

[0147] Example 39. The method of any one or more of examples 37-38, further comprising: performing, by processing circuitry of the computing system, the second review of the physiological data.

[0148] Example 40. The method of any one or more of examples 37-39, further comprising: based on the remote connection not satisfying a connection criterion, performing, by the processing circuitry of the IMD, the second review of the physiological data.

[0149] Example 41. The method of any one or more of examples 37-40, wherein when the second review results in the determination that the physiological data is indicative of the episode, the patient is advised to seek medical attention.

[0150] Example 42. The method of any one or more of examples 37-41, wherein performing one or more of the first review or the second review comprising applying, by the processing circuitry, the physiological data to a machine learning model.

[0151] Example 43. The method of any one or more of examples 37-42, wherein the user comprises one or more of a patient, a caregiver, a clinician, or an emergency responder.

[0152] Example 44. A method for analyzing implantable medical device (IMD) performance, the method comprising: sensing, by sensing circuitry of an IMD, a signal of a patient; determining, by processing circuitry of a system comprising the IMD, one or more metrics based on the signal data; performing, by the processing circuitry, a first review of the signal data by at least comparing the one or more metrics to one or more corresponding thresholds; responsive to one or more of the first review of the signal data being indicative of the sensing issue or determining to initiate a transmission, performing, by the processing circuitry, a second review of the signal data, wherein the second review is more complex than the first review; and based on a determination that the signal data is indicative of the sensing issue, presenting, by the processing circuitry, an indication to a user to adjust the IMD.

[0153] Example 45. The method of example 44, wherein the potential sensing issue comprises under-sensing or oversensing.

[0154] Example 46. The method of any one or more of examples 44-45, wherein the first review is performed on the IMD, and the second review is cloud-based.

[0155] Example 47. The system of any of examples 44-46, wherein the one or more corresponding thresholds are based on baseline data or trend data.

[0156] Example 48. The method of any one or more of examples 44-47, wherein performing one or more of the first review or the second review comprising applying, by the processing circuitry, the signal data to a machine learning model.

[0157] Example 49. A non-transitory computer-readable storage medium comprising instructions that, when executed by processing circuitry, cause the processing circuitry to: receive a physiological signal of a patient; store physiological data as indicative of an episode based on the physiological signal; perform a first review of the physiological data by at least comparing the physiological data to one or more previous transmissions; based on the comparison, determine whether to perform a second review of the physiological data to determine whether the physiological data is indicative of the episode; and based on a determination of the second review that the physiological data is indicative of the episode, send a transmission comprising the physiological data to a user. [0158] Example 50. A non-transitory computer-readable storage medium comprising instructions that, when executed by processing circuitry, cause the processing circuitry to: receive a physiological signal of a patient; store physiological data as indicative of an episode based on the physiological signal; perform a first review of the physiological data by at least comparing the physiological data to one or more previous transmissions; and based on the comparison, determine whether to: establish a remote connection with a computing system; and transmit the physiological data to the computing system, for the computing system to perform a second review of the physiological data to determine whether the physiological data is indicative of the episode.

[0159] Example 51. A non-transitory computer-readable storage medium comprising instructions that, when executed by processing circuitry, cause the processing circuitry to: receive a signal of a patient; determine one or more metrics based on the signal data; perform a first review of the signal data by at least comparing the one or more metrics to one or more corresponding thresholds; based on the comparison, determine whether the signal data is indicative of a sensing issue; responsive to one or more of the first review of the signal data being indicative of the sensing issue or determining to initiate a transmission, perform a second review of the signal data, wherein the second review is more complex than the first review; and based on a determination that the signal data is indicative of the sensing issue, present an indication to a user to adjust the IMD. [0160] Various examples have been described. These and other examples are within the scope of the following claims.

Claims

WHAT IS CLAIMED IS:

1. A system configured for analyzing implantable medical device (IMD) transmissions, the system comprising: an IMD configured to: sense a physiological signal of a patient; and store physiological data as indicative of an episode based on the physiological signal; and processing circuitry configured to: perform a first review of the physiological data by at least comparing the physiological data to one or more previous transmissions; based on the comparison, determine whether to perform a second review of the physiological data to determine whether the physiological data is indicative of the episode; and based on a determination of the second review that the physiological data is indicative of the episode, send a transmission comprising the physiological data to a user.

2. The system of claim 1, wherein the physiological data comprises cardiac data.

3. The system of any one or more of claims 1-2, wherein the processing circuitry comprises processing circuitry of the IMD that performs the first review.

4. The system of claim 3, wherein, based on the comparison, the processing circuitry of the IMD is configured to: establish a remote connection with a computing system; and transmit the physiological data to the computing system, wherein the processing circuitry comprises processing circuitry of the computing system configured to perform the second review of the physiological data.

5. The system of claim 4, wherein when the remote connection does not satisfy a connection criterion, the processing circuitry of the IMD is configured to perform the second review of the physiological data.

6. The system of any one or more of claims 1-5, wherein when the second review results in the determination that the physiological data is indicative of the episode, the patient is advised to seek medical attention.

7. The system of any one or more of claims 1-6, wherein to perform the second review the processing circuitry is configured to apply the physiological data to a machine learning model.

8. The system of any one or more of claims 1-7, wherein the user comprises one or more of a patient, a caregiver, a clinician, or an emergency responder.

9. The system of any one or more of claims 1-8, wherein the processing circuitry is further configured to: determine a predicted future state, wherein the predicted future state comprises one or more of: a predicted future device state, wherein the predicted future device state comprises potential issues with one or more of pacing, sensing, or leads; or a predicted future patient state; and transmit the predicted future state to the user.

10. The system of any of claims 1-9, wherein the processing circuitry is configured to: based on the second review, determine the physiological data is not indicative of the episode; and based on the physiological data not being indicative of the episode, do not transmit the physiological data to the user.

11. The system of any of claims 1-10, wherein the processing circuitry is configured to: receive a user preference; and based on the user preference, adapt one or more of the first or second review.

12. The system of any of claims 1-11, wherein to compare the cardiac data to one or more previous transmissions, the processing circuitry is configured to: determine one or more features of the one or more previous transmissions; determine one or more features of the physiological data; and compare features of the physiological data to the features of the previous transmissions.

13. An implantable medical device (IMD) comprising: sensing circuitry configured to: sense a physiological signal of a patient; and processing circuitry configured to: store physiological data as indicative of an episode based on the physiological signal; perform a first review of the physiological data by at least comparing the physiological data to one or more previous transmissions; and based on the comparison, determine whether to: establish a remote connection with a computing system; and transmit the physiological data to the computing system, for the computing system to perform a second review of the physiological data to determine whether the physiological data is indicative of the episode.

14. The IMD of claim 13, wherein the computing system comprises processing circuitry configured to: perform the second review of the physiological data.

15. A non-transitory computer-readable storage medium comprising instructions that, when executed by processing circuitry, cause the processing circuitry to: receive a physiological signal of a patient; store physiological data as indicative of an episode based on the physiological signal; perform a first review of the physiological data by at least comparing the physiological data to one or more previous transmissions; based on the comparison, determine whether to perform a second review of the physiological data to determine whether the physiological data is indicative of the episode; and based on a determination of the second review that the physiological data is indicative of the episode, send a transmission comprising the physiological data to a user.