[go: up one dir, main page]

WO2025224670A1 - Surveillance de l'état glycémique sur la base d'un signal cardiaque étiqueté - Google Patents

Surveillance de l'état glycémique sur la base d'un signal cardiaque étiqueté

Info

Publication number
WO2025224670A1
WO2025224670A1 PCT/IB2025/054282 IB2025054282W WO2025224670A1 WO 2025224670 A1 WO2025224670 A1 WO 2025224670A1 IB 2025054282 W IB2025054282 W IB 2025054282W WO 2025224670 A1 WO2025224670 A1 WO 2025224670A1
Authority
WO
WIPO (PCT)
Prior art keywords
cardiac
patient
processing circuitry
cardiac signals
signals
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/IB2025/054282
Other languages
English (en)
Inventor
Niranjan Chakravarthy
Rodolphe Katra
Sean R. LANDMAN
Tyler Stigen
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Medtronic Inc
Original Assignee
Medtronic Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Medtronic Inc filed Critical Medtronic Inc
Publication of WO2025224670A1 publication Critical patent/WO2025224670A1/fr
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment

Definitions

  • This disclosure generally relates to medical devices and, more particularly, to patient monitoring devices.
  • a variety of medical devices have been proposed for therapeutically treating or monitoring cardiac, neurological, and/or other conditions of a patient.
  • Medical devices may monitor physiological signals of the patient.
  • a medical device may monitor a cardiac signal, e.g., an electrocardiogram (ECG) signal or a cardiac electrogram (EGM) signal, of the patient to monitor a patient condition.
  • ECG electrocardiogram
  • EMM cardiac electrogram
  • using these signals such devices facilitate monitoring and evaluating patient health over a number of months or years, outside of a clinic setting.
  • the disclosure describes techniques for facilitating monitoring of patient cardiac episodes and glycemic state by monitoring a physiological signal of the patient, such as a cardiac signal, e.g., a cardiac electrogram (EGM) signal or an electrocardiogram (ECG) signal.
  • a cardiac signal e.g., a cardiac electrogram (EGM) signal or an electrocardiogram (ECG) signal.
  • ECG electrocardiogram
  • the example techniques for monitoring patient cardiac episodes and glycemic state include continuously monitoring the cardiac signal and storing, i.e., capturing, segments of the cardiac signal based on the segments of the cardiac signal satisfying one or more criterion.
  • a medical device of a system monitoring the cardiac signals may be configured to capture cardiac signals at a regular interval to capture baseline cardiac signals.
  • the medical device may be configured to capture cardiac signals in response to patient input to capture patient-activated cardiac signals.
  • the medical device may additionally be configured to capture cardiac signals in response to detection of a cardiac episode, such as asystole, bradycardia, atrial fibrillation (AF), atrial tachycardia, ST-segment deviation, QT interval prolongation, ventricular tachycardia, etc.
  • the system may be configured to determine a glycemic state of the patient based on the cardiac signals. However, not all cardiac signals may be conducive for determining the glycemic state, and use of all cardiac signals to determine the glycemic state may lead to erroneous glycemic state determination.
  • the system may tag a cardiac signal based on the reason or stimulus for capture, e.g., a cardiac signal captured at the regular interval is tagged as a baseline cardiac signal, a cardiac signal captured in response to patient input is tagged as a patient-activated cardiac signal, and a cardiac signal captured in response to detection of a cardiac episode may be tagged as, for example, an atrial fibrillation (AF) cardiac signal or a ventricular tachycardia (VT) cardiac signal.
  • AF atrial fibrillation
  • VT ventricular tachycardia
  • the system may additionally or alternatively tag the cardiac signal based on the time of capture.
  • the system may filter the cardiac signals based on the tag assigned to each captured cardiac signal before estimating the patient glycemic state. For instance, the system may remove cardiac signals having a tag corresponding to cardiac signals associated with a patient status that is not conducive to determining the glycemic state (e.g., cardiac signals associated with the patient status of VT or asystole).
  • the system may include, as a subset of cardiac signals, having a tag corresponding to cardiac signals associated with a patient status that is conducive of determining the glycemic state (e.g., cardiac signals associated with the baseline cardiac signals, patient status of atrial fibrillation (AF), or patient activated cardiac signal).
  • the system may utilize the subset of cardiac signals to determine an overall glycemic state of the patient.
  • a system comprises: one or more memories configured to: store a plurality of cardiac signals of a patient; and processing circuitry configured to: receive a respective assigned tag associated with one or more of the cardiac signals, wherein the respective assigned tag is indicative of a patient status associated with a corresponding cardiac signal of the one or more cardiac signals; based on the respective assigned tag indicative of the patient status meeting one or more criterion, filter the one or more cardiac signals to generate a subset of cardiac signals; determine an overall glycemic state of the patient based on the subset of cardiac signals; and output an indication to a user indicative of the overall glycemic state of the patient.
  • a method comprises: storing, via one or more memories a medical device system, a plurality of cardiac signals of a patient; receiving, by processing circuitry of the medical device system, a respective assigned tag associated with one or more of the cardiac signals, wherein the respective assigned tag is indicative of a patient status associated with a corresponding cardiac signal of the one or more cardiac signals; filtering, by the processing circuitry, the one or more cardiac signals to generate a subset of cardiac signals based on the respective assigned tag indicative of the patient status meeting one or more criterion; determining, by the processing circuitry, an overall glycemic state of the patient based on the subset of cardiac signals; and outputting, by the processing circuitry, an indication to a user indicative of the overall glycemic state of the patient.
  • a non-transitory computer-readable medium stores instructions that, when executed by processing circuitry, cause the processing circuitry to: receive a respective assigned tag associated with one or more cardiac signals of a plurality of cardiac signals of a patient, wherein the respective assigned tag is indicative of a patient status associated with a corresponding cardiac signal of the one or more cardiac signals; based on the respective assigned tag indicative of the patient status meeting one or more criterion, filter the one or more cardiac signals to generate a subset of cardiac signals; determine an overall glycemic state of the patient based on the subset of cardiac signals; and output an indication to a user indicative of the overall glycemic state of the patient.
  • 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.
  • 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.
  • FIG. 3 is a block diagram illustrating an example configuration of a medical device that operates in accordance with one or more techniques of the present disclosure.
  • 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.
  • FIG. 5 is a flow diagram illustrating an example operation for determining a glycemic state of a patient, in accordance with one or more techniques of this disclosure.
  • FIG. 6 is a flow diagram illustrating an example operation for determining a tag-based glycemic state of a patient, in accordance with one or more techniques of this disclosure.
  • FIG. 7 is a flow diagram illustrating an example operation for adjusting a frequency of cardiac signal capture, in accordance with one or more techniques of this disclosure.
  • FIG. 8 is a conceptual diagram illustrating an example machine learning model configured to determine a glycemic state of a patient, in accordance with one or more techniques of this disclosure.
  • FIG. 9 is a conceptual diagram illustrating an example training process for a machine learning model in accordance with examples of the current disclosure.
  • a variety of types of implantable and external devices are configured to monitor health based on sensed cardiac signals, e.g., electrocardiograms (ECGs) or cardiac electrograms (EGMs), and, in some cases, other physiological signals.
  • ECGs electrocardiograms
  • EGMs cardiac electrograms
  • External devices that may be used to non-invasively sense and monitor cardiac signals and other physiological signals include wearable devices with electrodes configured to contact the skin of the patient, such as watches, patches, 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.
  • Implantable medical devices also sense and monitor cardiac signals 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 LINQTM or LINQ IITM 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 CareLinkTM Network via a home monitoring system or a smart phone application.
  • collected data e.g., episode data for detected arrhythmia episodes or other health episodes
  • a remote patient monitoring system such as the Medtronic CareLinkTM Network via a home monitoring system or a smart phone application.
  • This disclosure relates to techniques for monitoring patient cardiac signals, e.g., ECG signals or cardiac EGM signals, to facilitate monitoring of cardiac episodes and/or glycemic state of a patient.
  • Devices may be configured to detect episodes based on the cardiac signal, such as fibrillations or arrhythmias.
  • cardiac signals can be used to estimate the glycemic state of a patient.
  • glycemic state e.g., amount of glucose in a bloodstream
  • cardiac signals can be used to estimate the glycemic state of a patient.
  • patients with certain cardiac conditions experience or have an increased risk of experiencing one or more comorbid conditions, such as diabetes.
  • patients with diabetes experience or have an increased risk of experiencing certain cardiac conditions.
  • the techniques of this disclosure may facilitate identification of changes in patient conditions, such as the onset of comorbid conditions, which may improve patient outcomes.
  • the techniques further include determining one or more tag- based glycemic states, e.g., a baseline glycemic state, a patient-activated patient state, or an episode glycemic state, such as an AF glycemic state.
  • tag-based glycemic states e.g., a baseline glycemic state, a patient-activated patient state, or an episode glycemic state, such as an AF glycemic state.
  • the techniques further include determining one or more trends in patient glycemic state.
  • the techniques of this disclosure may facilitate identification of changes in patient condition.
  • the techniques of this disclosure may allow a patient or user to address the change in patient condition, which may improve patient outcomes.
  • the techniques of this disclosure may implement a machine learning model.
  • the techniques may improve an accuracy of glycemic state determination. Additionally, by implementing a machine learning model, the techniques may decrease clinician review time.
  • 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.
  • the example techniques may be used with a medical device 10, which may be in wireless communication with an external device 12.
  • medical device 10 is an implantable medical device (IMD) implanted outside of a thoracic cavity of patient 4 (e.g., subcutaneously in the pectoral location illustrated in FIG. 1).
  • Medical device 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.
  • Medical device 10 includes a plurality of electrodes (not shown in FIG.
  • medical device 10 takes the form of the Reveal LINQTM or LINQ IITM insertable cardiac monitor (ICM).
  • ICM Reveal LINQTM or LINQ IITM insertable cardiac monitor
  • External device 12 is configured for wireless communication with medical device 10.
  • External device 12 may be configured to communicate with computing system 8 via network 16.
  • external device 12 may provide a user interface and allow a user to interact with medical device 10.
  • Computing system 8 may comprise external devices configured to allow a user to interact with medical device 10, or data collected from medical device 10, via network 16.
  • External device 12 may be used to retrieve data from medical device 10 and may transmit the data to computing system 8 via network 16.
  • the retrieved data may include cardiac signals collected by medical device 10 and/or other physiological signals recorded by medical device 10, such as a respiration signal, a photoplethysmography (PPG) signal, a multi -frequency impedance cardiography signal, or a heart sounds signal.
  • the episode data may include cardiac segments recorded by medical device 10, e.g., on a regular schedule, due to medical device 10 determining that an episode of arrhythmia or another malady occurred during the segment, and/or in response to a request to record the segment from patient 4 or another user.
  • medical device 10 may be configured for wireless communication with computing system 8 via network 16, i.e., medical device 10 may perform one or more of the operations described herein as being performed by external device 12.
  • computing system 8 includes one or more handheld external devices, computer workstations, servers or other networked external devices.
  • computing system 8 may include one or more devices, including processing circuitry and storage devices, which may be distributed across multiple locations and/or multiple servers.
  • Computing system 8 may comprise a cloud computing system.
  • Computing system 8 and network 16 may be implemented by the Medtronic CareLinkTM Network or other patient monitoring system, in some examples.
  • Computing system 8 may implement a monitoring system (not shown) that may analyze episode data received from medical devices, including medical device 10, and direct the episode data to reviewers.
  • Computing system 8 may implement one or more 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.
  • 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 medical device 10, access to the Internet, and may provide a communication framework that allows the external devices to communicate with one another.
  • network 16 may be a private network that provides a communication framework that allows computing system 8, medical device 10, and/or external device 12 to communicate with one another but isolates one or more of computing system 8, medical device 10, or external device 12 from devices external to network 16 for security purposes.
  • the communications between computing system 8, medical device 10, and external device 12 are encrypted.
  • Computing system 8 is an example of a computing system configured to receive cardiac data stored by a medical device, e.g., medical device 10, of a patient, e.g., patient 4.
  • Computing system 8 may be managed by a manufacturer of medical device 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.
  • External device 12 may transmit data, including cardiac signals and/or other physiological signals retrieved from medical device 10, to computing system 8 via network 16.
  • the cardiac signals and/or other physiological signals may include, for example, baseline cardiac signals, episode cardiac signals, e.g., AF cardiac signals or ventricular tachycardia cardiac signals, patient-activated cardiac signals, respiration signals, PPG signals, multi -frequency impedance cardiography signals, heart sounds signals, and other physiological signals or data recorded by IMD 10 and/or external device(s) 12.
  • Computing system 8 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 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.
  • Computing system 8 may use data from EHR to configure algorithms implemented by medical device 10, external device 12, and/or computing system 8 to determine glycemic state of the patient and/or monitor a cardiac condition of patient 4.
  • computing system 8 provides data from EHR to external device 12 and/or medical device 10 for storage therein and use as part of their algorithms for detecting episodes and/or determining glycemic state.
  • this disclosure describes example techniques of determining an overall glycemic state of the patient based on a subset of cardiac signals from the plurality of cardiac signals that medical device 10 stored.
  • the example techniques may be performed using any combination of the components illustrated in FIG. 1. In examples where fewer components than those illustrated in FIG. 1 are used to determine the overall glycemic state, the remaining components may not be necessary.
  • medical device 10 may sense a plurality of cardiac signals. However, rather than using medical device 10, it may be possible for external device 12 (e.g., such as where external device 12 is a watch) to sense the plurality of cardiac signals. In such an example, medical device 10 may not be needed.
  • processing circuitry of medical device 10 may be configured to assign respective tags to one or more of the cardiac signals, where each respective assigned tag is indicative of a patient status associate with the corresponding cardiac signal. Medical device 10 may then transmit the tags and cardiac signals to computing system 8 through external device 12 via network 16. However, in some examples, external device 12 may assign respective tags, rather than medical device 10, or computing system 8 may assign respective tags, rather than external device 12 or medical device 10.
  • processing circuitry of medical device 10 or external device 12 may filter the cardiac signals based on the assigned tags to generate a subset of cardiac signals that are conducive to glycemic state determination, and removing cardiac signals that are not conducive to glycemic state determination.
  • Computing system 8 may be configured to determine the overall glycemic state of the patient based on the subset of cardiac signals. For instance, computing system 8 may execute a trained machine learning model, and the input to the trained machine learning model may be the subset of cardiac signals (e.g., features of the subset of cardiac signals). However, it may be possible for external device 12 to determine the overall glycemic state. In some examples, medical device 10 may be configured to determine the overall glycemic state.
  • the example techniques described in this disclosure may be performed by one or any combination of devices and systems illustrated in FIG. 1.
  • the processing circuitry may be located within one of the illustrated components (e.g., computing system 8) or may be distributed across the components.
  • the processing circuitry may be considered as having different portions, where a first portion is located within medical device, a second portion is located within computing system 8, etc.
  • a first portion of the processing circuitry within medical device 10 may assign the tags and/or filter the cardiac signals to generate the subset of cardiac signals
  • a second portion of the processing circuitry within computing system 8 may determine the overall glycemic state.
  • FIG. 2A is a perspective drawing illustrating an IMD 10A, which may be an example configuration of medical device 10 of FIG. 1 as an ICM.
  • 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.
  • 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.
  • 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.
  • 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.
  • 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.
  • 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.
  • 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.
  • 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.
  • 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.
  • 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 No. 11,311,312, incorporated herein by reference in its entirety.
  • 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 cardiac signals thoracically outside the ribcage, which may be implanted sub-muscularly or subcutaneously, cardiac 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.
  • 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.
  • EEG electroencephalogram
  • EMG electromyogram
  • nerve signal or for measuring impedance, from any implanted location.
  • 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.
  • 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.
  • electrode 216B is an uninsulated portion of a metallic, e.g., titanium, part of housing 212.
  • proximal electrode 216A is located on first major surface 214 and is substantially flat, and outward facing.
  • 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).
  • 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.
  • proximal electrode 216A and distal electrode 216B are located on both first major surface 214 and second major surface 218.
  • proximal electrode 216A and distal electrode 216B are 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).
  • 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.
  • 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.
  • 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.
  • 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.
  • anti-migration projections 232 include a plurality (e.g., nine) small bumps or protrusions extending away from first major surface 214.
  • anti -migration projections 232 may be located on the opposite major surface as proximal electrode 216A and/or integrated antenna 230A.
  • header assembly 228 includes suture hole 234, which provides another means of securing IMD 10A to the patient to prevent movement following insertion.
  • 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.
  • FIG. 2B is a perspective drawing illustrating another IMD 10B, which may be another example configuration of medical device 10 from FIG. 1 as an ICM.
  • IMD 10B of FIG. 2B may be configured substantially similarly to IMD 10A of FIG. 2A, with differences between them discussed herein.
  • 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.
  • a battery or other power source of IMD 10B may be included within base 240.
  • 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.
  • 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.
  • 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.
  • a material such as titanium nitride or fractal titanium nitride, although other suitable materials and coatings for such electrodes may be used.
  • 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.
  • 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.
  • IMD 10B may have a length L that ranges from 5 mm to about 70 mm.
  • 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.
  • 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.
  • outer surface of cover 242 faces outward, toward the skin of the patient.
  • 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.
  • edges of IMD 10B may be rounded.
  • FIG. 3 is a block diagram illustrating an example configuration of medical device 10 from FIG. 1 that operates in accordance with one or more techniques of the present disclosure.
  • medical device 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.
  • 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.
  • 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.
  • 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.
  • RAM random-access memory
  • ROM read-only memory
  • NVRAM non-volatile RAM
  • EEPROM electrically-erasable programmable ROM
  • flash memory or any other digital media.
  • 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 cardiac data for patient 4.
  • cardiac data, cardiac signal data, and cardiac signals are used interchangeably in this disclosure.
  • processing circuitry 350 may identify features of the sensed cardiac signal, such as heart rate, heart rate variability, T- wave alternans, intra-beat intervals (e.g., QT intervals), and/or cardiac morphologic features, to detect a cardiac episode and/or determine a glycemic state of patient 4.
  • Processing circuitry 350 may store the digitized cardiac signal and/or features of the cardiac signal used to detect the episode and/or to determine the glycemic state in memory 352 as physiological data 388.
  • medical device 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.
  • 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.
  • 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 388, 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.
  • 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 episodes and/or collect data to determine glycemic state 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 388.
  • physiological data 388 can include episode data, e.g., when stored in response to detecting a cardiac episode.
  • physiological data 388 may additionally include physiological data sensed by other devices, e.g., external device(s) 12, and received via communication circuitry 360.
  • event surveillance application 372 may be configured with an analysis engine (not shown).
  • the analysis engine may apply one or more rules such as models, algorithms, decision trees, and/or thresholds to physiological data 388, e.g., to determine glycemic state.
  • the rules may be developed based on machine learning, e.g., may include one or more machine learning models.
  • the rules including the one or more machine learning models may be patient specific.
  • the machine learning models are programmable based on patient settings that can be tailored for a specific patient.
  • event surveillance application 372 may detect a potential episode of sudden cardiac arrest (SC A), a ventricular fibrillation, a ventricular tachycardia, supraventricular tachycardia (e.g., conducted atrial fibrillation), atrial fibrillation or tachycardia, ventricular asystole, ST-segment deviation, QT interval prolongation, a myocardial infarction based on a cardiac signal and/or other patient parameter data indicating the electrical or mechanical activity of the heart of patient 4.
  • SC A sudden cardiac arrest
  • a ventricular fibrillation e.g., a ventricular tachycardia
  • supraventricular tachycardia e.g., conducted atrial fibrillation
  • atrial fibrillation or tachycardia e.g., ventricular asystole
  • ST-segment deviation e.g., QT interval prolongation
  • myocardial infarction based on a cardiac signal and/or other patient parameter data
  • processing circuitry 350 may be configured to assign a tag to each captured cardiac signal of physiological data 388 based on a patient status associated with physiological data 388.
  • the tags may identify each captured data segment as one or more of baseline cardiac data, patient-activated cardiac data, and/or cardiac episode cardiac data, e.g., AF cardiac data or ventricular tachycardia cardiac data.
  • event surveillance application 372 may generate information that indicates whether a captured cardiac signal was captured when the patient was experiencing a cardiac episode like ventricular tachycardia (VT), asystole, ST-segment deviation, QT interval prolongation, or atrial fibrillation (AF).
  • the tags may identify each captured data segment based on activity level, e.g., low activity, moderate activity, or high activity.
  • the captured cardiac signals of physiological data 388 may be main datapoints to determine glycemic state of patient 4, and the tags may be metadata, which processing circuitry 350 may use to perform filtering, or conditional processing.
  • the patient status associated with a cardiac signal may indicate whether a patient is having a cardiac episode or not.
  • medical device 10 may capture the cardiac signal in response to detection patient activated event (e.g., request from patient 4), and the patient activated event is an example of the patient status since patient 4 may have experienced a condition and requested capture of a cardiac signal.
  • medical device 10 may capture the cardiac signal as part of a baseline cardiac measurement.
  • medical device 10 may be configured to periodically capture cardiac measurement regardless of whether patient 4 is experiencing any condition.
  • the baseline cardiac measurement may be a patient status in that the patient status is normal.
  • medical device 10 may capture a cardiac signal in response to event surveillance application 372 detecting of a cardiac event like ventricular tachycardia (VT), asystole, atrial tachycardia, ST-segment deviation, QT interval prolongation, or atrial fibrillation (AF), or after a cardiac signal is captured, event surveillance application 372 may determine the cardiac signal is indicative of VT, asystole, or AF, etc. In such examples, the patient status may be the cardiac episode patient 4 is experiencing.
  • VT ventricular tachycardia
  • VT ventricular tachycardia
  • atrial tachycardia egment deviation
  • QT interval prolongation a atrial fibrillation
  • AF atrial fibrillation
  • processing circuitry 350 using application(s) 370 or some other technique may assign respective tags to one or more of the cardiac signals.
  • the respective assigned tags may be indicative of a patient status associated with a corresponding cardiac signal of the one or more cardiac signals.
  • processing circuitry 350 may assign a first cardiac signal (e.g., segment) the tag of baseline (e.g., assuming that first cardiac signal was captured as part of baseline measurements).
  • Processing circuitry 350 may assign a second cardiac signal (e.g., segment) the tag of VT (e.g., assuming that the second cardiac signal was captured when patient 4 experienced VT), and so forth.
  • a second cardiac signal e.g., segment
  • the tag of VT e.g., assuming that the second cardiac signal was captured when patient 4 experienced VT
  • processing circuitry 350 may filter the one or more cardiac signals to generate a subset of cardiac signals. For example, processing circuitry 350 may compare the tags of physiological data 388, where physiological data 388 is an example of cardiac signals, to filter parameters 386, where filter parameters 386 are an example of the one or more criterion, to determine whether to filter the data for the glycemic state determination. In some examples, it may be advantageous to filter, for example, VT cardiac signal data from the other captured cardiac signal data of physiological data 388 to improve accuracy of the glycemic state determination.
  • Some cardiac episodes such as ventricular tachycardia or other ventricular arrhythmia, can cause changes in cardiac signal features and/or morphology that may lead to inaccurate glycemic state determinations.
  • the techniques of this disclosure may advantageously improve the accuracy of the glycemic state determination.
  • filter parameters 386 may define one or more criterion.
  • the one or more criteria may indicate that cardiac signals having a first type of tags should be removed (e.g., filtered out) for glycemic state determination, and may indicate that cardiac signals having a second type of tags should be included for glycemic state determination. For instance, cardiac signals having the respective assigned tags of baseline, AF, or patient activated should be included for glycemic state determination, but cardiac signals having the respective assigned tags of VT or asystole should be removed.
  • cardiac signals including VT episodes should be removed because during VT, the increased frequency of ventricular activity can cause other features of the cardiac signal, e.g., P-waves and T-waves, to be indecipherable or obscured from the ventricular activity features associated with VT. Additionally, the QRS complex can widen, and R-wave to R- wave intervals can shorten. In examples of monomorphic VT, the cardiac signal can become relatively sinusoidal in shape, and in examples of polymorphic VT, the cardiac signal can include disorganized morphology changes. Due to these changes in the cardiac signal caused by VT, VT signal data can lead to inaccurate glycemic state determinations.
  • processing circuitry 350 may control communication circuitry 360 to transmit physiological data 388 and any associated tags, e.g., to external device 12, for cloud-based or edge-based processing. However, in some examples, processing circuitry 350 may control communication circuitry 360 to transmit physiological data 388 that has not been filtered out. That is, if processing circuitry 350 performs filtering, based on the respective assigned tag indicative of the patient status meeting one or more criterion defined by filter parameters 386, then processing circuitry 350 may cause communication circuitry 360 to transmit the subset of cardiac signals that are generated from the filtering.
  • Processing circuitry 350 may transmit physiological data 388 and/or the subset of cardiac signals generated from the filtering on a regular transmission schedule, e.g., every 5 minutes or hourly, and/or based on a number of patient-activated recordings or a frequency of cardiac events.
  • medical device 10 may be configured to store up to, e.g., 3 patient-activated cardiac signal segments per day, and, e.g., up to 30 cardiac episodes per day, per cardiac episode type.
  • processing circuitry 350 may transmit physiological data 388 and/or the subset of cardiac signals less frequently, e.g., daily, weekly, or monthly, to, e.g., screen for changes in patient health.
  • 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. Processing circuitry 350 may determine to control communication circuitry 360 to send a transmission on a regular schedule, e.g., hourly, daily, or weekly, or on a need-based or patient-requested basis.
  • a regular schedule e.g., hourly, daily, or weekly, or on a need-based or patient-requested basis.
  • medical device 10 may be configured to sense the cardiac signals and store the cardiac signals as physiological data 388. However, the assigning of tags and filtering, and determining of the glycemic state of the patient 4, may be performed on another device. As another example, medical device 10 may be configured to sense the cardiac signals and store the cardiac signals as physiological data 388, and assign tags to the cardiac signals, where the respective assigned tag is indicative of a patient status associated with a corresponding cardiac signal. However, the filtering and determining of the glycemic state of the patient 4, may be performed on another device.
  • medical device 10 may be configured to sense the cardiac signals and store the cardiac signals as physiological data 388, assign tags to the cardiac signals, where the respective assigned tag is indicative of a patient status associated with a corresponding cardiac signal, and filter the one or more cardiac signals to generate a subset of cardiac signals.
  • the determining of the glycemic state of the patient 4 may be performed on another device.
  • medical device 10 may be configured to sense the cardiac signals and store the cardiac signals as physiological data 388, assign tags to the cardiac signals, where the respective assigned tag is indicative of a patient status associated with a corresponding cardiac signal, filter the one or more cardiac signals to generate a subset of cardiac signals, and determine the overall glycemic state of the patient based on the subset of cardiac signals.
  • FIG. 4 is a block diagram illustrating an example configuration of computing system 8 of FIG. 1, in accordance with one or more techniques of this disclosure.
  • computing system 8 includes processing circuitry 402 for executing applications 424.
  • 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 or processing circuitry 402 may not be co-located or in the same chassis as other components).
  • computing system 8 may be a cloud computing system distributed across a plurality of devices.
  • 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, 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.
  • communication channels 414 may include a system bus, a network connection, an interprocess communication data structure, or any other method for communicating data.
  • components 402, 404, 406, 408, 410, and 412 may be coupled by one or more communication channels 414.
  • Processing circuitry 402 in one example, is configured to implement functionality and/or process instructions for execution within computing system 8.
  • 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.
  • 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.
  • 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.
  • RAM random access memories
  • DRAM dynamic random access memories
  • SRAM static random access memories
  • 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.
  • 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.
  • 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).
  • Computing system 8 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.
  • network interfaces may include 3G and Wi-Fi radios.
  • Computing system 8 also includes one or more user interface devices 410.
  • User interface devices 410 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.
  • 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 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 liquid crystal display (LCD), or any other type of device that can generate intelligible output to a user.
  • a presencesensitive display for converting a signal into an appropriate form understandable to humans or machines.
  • Additional examples of output device(s) 412 include a speaker, a liquid crystal display (LCD), or any other type of device that can generate intelligible output to a user.
  • LCD liquid crystal display
  • Computing system 8 may include operating system 416.
  • Operating system 416 controls the operation of components of computing system 8.
  • operating system 416 in one example, facilitates the communication of one or more applications 424 with processing circuitry 402, communication circuitry 406, storage device(s) 408, input devices 404, user interface devices 410, and output devices 412.
  • Applications 424 may also include program instructions and/or data that are executable by computing system 8. Applications 424 may implement machine learning model(s) 452. Applications 424 may include other additional applications not shown which may alternatively or additionally be included to provide other functionality described herein and are not depicted for the sake of simplicity.
  • computing system 8 receives physiological data, e.g., cardiac signal data and, possibly, associated tags of physiological data 388, stored by medical devices, such as medical device 10, via communication circuitry 406, e.g., to determine the glycemic state of patient 4.
  • Processing circuitry 402 may store the physiological data 388, in storage device(s) 408.
  • the physiological data may have been collected by medical device 10 in response to device 10 detecting cardiac episodes or based on a regular schedule or patient request.
  • computing system 8 may receive the associated tags of physiological data 388 that computing system 8 uses for filtering to generate a subset of cardiac signals used for determining the overall glycemic state.
  • the associated tags may not be needed. For instance, if medical device 10 performs the filtering, then computing system 8 may receive the subset of cardiac signals that are used for determining the glycemic state.
  • the tag information may be available, but may not be needed, or may be removed. For instance, since the subset of cardiac signals that are conducive for determining glycemic state are what computing system 8 receives, further tag information may not be needed.
  • Machine learning model(s) 452 controls the determination of glycemic state, and generation of reports for user, e.g., patient 4 or clinician review.
  • Applications 424 may utilize input devices 404, output devices 412, and/or communication circuitry 406 to output glycemic state information to one or more users, e.g., via one or more graphical user interfaces presented on output devices 412 or other client external devices.
  • Processing circuitry 402 may determine one or more trends in glycemic state.
  • processing circuitry 402 may implement machine learning model(s) 452 to determine the one or more trends. For example, processing circuitry 402 may determine a change in glycemic state over a period of time, e.g., weeks or months. In some examples, changes in glycemic state over a period of time may be indicative of a change in patient condition, e.g., an onset of diabetes. Processing circuitry 402 may additionally, or alternatively, determine one or more tag-based glycemic states of patient 4, e.g., a glycemic state corresponding to one or more cardiac episode types, e.g., AF. In some examples, it may be advantageous to determine how glycemic state changes during cardiac episodes. For example, there may be a diagnostic benefit in determining what the glycemic state of patient 4 was during one or more AF episodes versus what the glycemic state of patient 4 based on baseline cardiac signal collection.
  • a diagnostic benefit in determining what the glycemic state
  • 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.
  • 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.
  • FIG. 5 is a flow diagram illustrating an example operation for determining a glycemic state of a patient, in accordance with one or more techniques of this disclosure.
  • sensing circuitry e.g., sensing circuitry 354 of FIG. 3, may sense a plurality of physiological signals, e.g., cardiac signals, respiration signals, PPG signals, multi-frequency impedance cardiography signals, and/or heart sounds signals, of patient 4.
  • Memory 352 of medical device 10 and/or storage device(s) 408 stores the plurality of cardiac signals (502).
  • processing circuitry of system 2 For each cardiac signal of the plurality of cardiac signals, processing circuitry of system 2, e.g., any of processing circuitry 350 of medical device 10, processing circuitry 402 of computing system 8, or processing circuitry of external device 12, receives a respective assigned tag associated with one or more of the cardiac signals.
  • the tags may be indicative of a patient status associated with each cardiac signal, i.e., the tags may comprise a baseline tag, a patient-activated tag, and cardiac episode tags, such as an AF tag, an asystole tag, an atrial tachycardia tag, and/or a ventricular tachycardia tag.
  • Processing circuitry filters cardiac signals of the plurality of cardiac signals based on the one or more respective tags assigned to each of the cardiac signals to generate a subset of cardiac signals (506). In other words, processing circuitry may determine to maintain a subset of the cardiac signals of the plurality of cardiac signals for determining a glycemic state of patient 4. As an example, processing circuitry may filter cardiac signals with tags indicative of a patient status of a ventricular tachycardia or other ventricular arrhythmia. Processing circuitry may determine an overall glycemic state of patient 4 based on the subset of the cardiac signals, i.e., remaining cardiac signals of the plurality of cardiac signals (508).
  • processing circuitry determines the overall glycemic state of patient 4 on a regular schedule, e.g., hourly, daily, or weekly, on a need-based or user-requested basis, or a combination thereof.
  • Processing circuitry controls communication circuitry, e.g., communication circuitry 360 of medical device 10, communication circuitry 406 of computing system 8, or communication circuitry of external device 12, to output an indication to a user, e.g., patient 4 and/or the clinician, of the glycemic state over the period of time, e.g., via a user interface of external device 12 and/or user interface device(s) 410 of computing system 8 (510).
  • processing circuitry may additionally determine one or more glycemic state trends (512).
  • processing circuitry may determine glycemic state trends over, for example, weeks or months, which may be indicative of a change in patient 4’s condition.
  • tags may include tags indicative of a patient activity level during signal data capture.
  • Processing circuitry of system 2 may filter respiration signals with tags indicative of a high patient activity level.
  • Processing circuitry may determine the overall glycemic state of patient 4 based on data associated with tags indicative of, e.g., low patient activity and moderate patient activity.
  • FIG. 6 is a flow diagram illustrating an example operation for determining a tag-based glycemic state of a patient, in accordance with one or more techniques of this disclosure.
  • processing circuitry of system 2 determines one or more tag-based glycemic states of patient 4 (602).
  • processing circuitry may determine a baseline glycemic state of patient 4 and/or an AF glycemic state of patient 4.
  • Processing circuitry controls communication circuitry, e.g., communication circuitry 360 of medical device 10, communication circuitry 406 of computing system 8, or communication circuitry of external device 12, to output an indication of the one or more tag-based glycemic states of patient 4 to the user, e.g., patient 4 or the clinician (604).
  • FIG. 7 is a flow diagram illustrating an example operation for adjusting a frequency of cardiac signal capture, in accordance with one or more techniques of this disclosure. Based on one or more glycemic state determinations of the patient, processing circuitry, e.g., processing circuitry 350 of medical device 10, processing circuitry 402 of computing system 8, or processing circuitry of external device 12 may determine a risk of diabetes of the patient (702).
  • processing circuitry may control communication circuitry, e.g., communication circuitry 360 of medical device 10, communication circuitry 406 of computing system 8, or communication circuitry of external device 12, to output an indication of the risk of diabetes to a user, e.g., via user interface device(s) 410, e.g., concurrently with the indication of glycemic state in step 508 of FIG. 5 or step 602 of FIG. 6.
  • processing circuitry may adjust a frequency of baseline cardiac signal capture (704). For example, processing circuitry may determine to increase a frequency of periodic cardiac signal capture, e.g., if patient 4 is at a relatively high risk of diabetes.
  • the techniques of this disclosure may allow higher risk patients to be monitored more frequently, which may improve accuracy of glycemic state and patient condition detection.
  • processing circuitry may determine to decrease the frequency of the period cardiac signal capture, e.g., if patient 4 is at a relatively low risk of diabetes.
  • the techniques of this disclosure may advantageously increase device longevity.
  • FIG. 8 is a conceptual diagram illustrating an example machine learning model 800 configured to determine a glycemic state of a patient, in accordance with one or more techniques of this disclosure.
  • Machine learning model 800 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 medical device 10, or as a set of rules implemented by medical device 10, as discussed above.
  • Machine learning model 800 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 388.
  • One or more of medical device 10, external device 12, or a computing system 8 may train, store, and/or utilize machine learning model 800, but other devices may apply inputs associated with a particular patient to machine learning model 800 in other examples.
  • machine learning and deep learning models or algorithms may be utilized in other examples.
  • a convolutional neural network model of ResNet-18 may be used.
  • 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 pretrained transformers (GPT), etc.
  • Some non-limiting examples of machine learning techniques include Support Vector Machines, K-Nearest Neighbor algorithm, and Multilayer Perceptron.
  • machine learning model 800 may include three layers. These three layers include input layer 802, hidden layers 804, and output layer 806. Output layer 806 comprises the output from the transfer function 805 of output layer 806. Input layer 802 represents each of the input values XI through X4 provided to machine learning model 800. 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 a cardiac signal. In addition, in some examples input values of machine learning model 800 may include additional data, such as data relating to one or more additional parameters of patient 4.
  • Each of the input values for each node in the input layer 802 is provided to each node of hidden layer 804.
  • hidden layers 804 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 802 is multiplied by a weight and then summed at each node of hidden layers 804.
  • the weights for each input are adjusted to establish the relationship between the inputs, e.g., physiological data 388, to determine glycemic state of patient 4.
  • machine learning model 800 may be trained to establish patient-specific relationships between physiological data 388 to determine patient 4’s glycemic state.
  • one hidden layer may be incorporated into machine learning model 800, or three or more hidden layers may be incorporated into machine learning model 800, where each layer includes the same or different number of nodes.
  • the result of each node within hidden layers 804 is applied to the transfer function of output layer 806.
  • the transfer function may be linear or non-linear, and in some examples may depend on the number of layers within machine learning model 800.
  • Example non-linear transfer functions may be a sigmoid function or a rectifier function.
  • the output 807 of the transfer function may be a classification that indicates whether the particular cardiac segment or other input set is indicative of hyperglycemia, hypoglycemia, or a normal glycemic state.
  • processing circuitry By applying the cardiac signal data and/or other patient parameter data to a machine learning model, such as machine learning model 800, processing circuitry, such as processing circuitry 402 of computing system 8, is able to determine a glycemic state of patient 4.
  • model 800 is but one example, and other examples may be utilized in implementing the techniques of this disclosure.
  • a machine learning model may include different types of layers, such as pooling layers.
  • a machine learning model may include features not illustrated in the example of FIG. 8, such as skip connections and weight sharing.
  • FIG. 9 is a conceptual diagram illustrating an example training process for a machine learning model 900 being trained using supervised and/or reinforcement learning techniques, in accordance with examples of the current disclosure.
  • Machine learning model 900 may be substantially similar to or the same as machine learning model 800 (FIG. 8).
  • Machine learning model 900 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 900 may be implemented using any number of models for unsupervised learning.
  • processing circuitry one or more of medical device 10, external device 12, and/or computing system 8 initially trains the machine learning model 900 based on training set data 902 including numerous instances of input data corresponding to a plurality of glycemic states, e.g., as labeled by an expert.
  • a prediction or classification by the machine learning model 900 may be compared 906 to the target output 904, e.g., as determined based on the label.
  • the processing circuitry implementing a leaming/training function 908 may send or apply a modification to weights of machine learning model 900 or otherwise modify/update the machine learning model 900.
  • one or more of medical device 10, external device 12, and/or computing system 8 may, for each training instance in the training set 902, modify machine learning model 900 to change a glycemic state determination generated by the machine learning model 900 in response to data applied to the machine learning model 900.
  • Example 1 A system comprising: one or more memories configured to: store a plurality of cardiac signals of a patient; and processing circuitry configured to: receive a respective assigned tag associated with one or more of the cardiac signals, wherein the respective assigned tag is indicative of a patient status associated with a corresponding cardiac signal of the one or more cardiac signals; based on the respective assigned tag indicative of the patient status meeting one or more criterion, filter the one or more cardiac signals to generate a subset of cardiac signals; determine an overall glycemic state of the patient based on the subset of cardiac signals; and output an indication to a user indicative of the overall glycemic state of the patient.
  • Example 2 The system of example 1, wherein the plurality of cardiac signals comprises one or more of: a baseline cardiac signal, wherein the baseline cardiac signal comprises a periodically captured cardiac signal; a patient-activated cardiac signal, wherein the patient-activated cardiac signal comprises a cardiac signal captured responsive to patient input; or a cardiac event cardiac signal, wherein the cardiac event cardiac signal comprises a cardiac signal captured responsive to a cardiac event.
  • Example s The system of example 2, wherein the cardiac event comprises one or more of: a bradycardia event, an atrial fibrillation event, an asystole event, a ventricular arrhythmia event, an atrial tachycardia event, an ST-segment deviation episode, a QT interval prolongation event, or a patient activated event.
  • the cardiac event comprises one or more of: a bradycardia event, an atrial fibrillation event, an asystole event, a ventricular arrhythmia event, an atrial tachycardia event, an ST-segment deviation episode, a QT interval prolongation event, or a patient activated event.
  • Example 4 The system of example 3, wherein the ventricular arrhythmia event comprises a ventricular tachycardia event.
  • Example 5 The system of any one or more of examples 1-4, wherein the patient status is based on cardiac event information associated with the cardiac signal.
  • Example 6 The system of any one or more of examples 1-5, wherein to filter the one or more cardiac signals, the processing circuitry is configured to: remove cardiac signals having the respective assigned tag indicative of ventricular tachycardia or asystole; and include, in the subset of cardiac signals, cardiac signals having respective assigned tag indicative of baseline cardiac signal, atrial fibrillation, or patient activated cardiac signal.
  • Example 7 Example 7.
  • processing circuitry is further configured to: for the respective assigned tag, determine a tag-based glycemic state, wherein the tag-based glycemic state is associated with the patient status; and output the tag-based glycemic state to the user.
  • Example 8 The system of any one or more of examples 1-7, wherein to determine the overall glycemic state, the processing circuitry is configured to: input the subset of cardiac signals into a machine learning model; and determine the overall glycemic state based on an output from the machine learning model.
  • Example 9 The system of example 8, wherein the processing circuitry is configured to: for each cardiac signal of the subset of cardiac signals, determine one or more features, wherein to input the subset of cardiac signals, the processing circuitry is configured to input the one or more features into the machine learning model.
  • Example 10 The system of any one or more of examples 1-9, further comprising a medical device, wherein a first portion of the processing circuitry comprises processing circuitry of the medical device, and wherein the first portion of the processing circuitry is configured to filter the one or more cardiac signals to generate the subset of cardiac signals.
  • Example 11 The system of example 10, wherein the first portion of the processing circuitry is configured to: transmit the subset of cardiac signals to a computing system, wherein the computing system comprises a second portion of the processing circuitry, and wherein the second portion of the processing circuitry is configured to determine the overall glycemic state.
  • Example 12 The system of any of examples 10 or 11, wherein at least one of the first portion of the processing circuitry or the second portion of the processing circuitry is configured to assign the respective tag to corresponding cardiac signals of the one or more cardiac signals.
  • Example 13 The system of any one or more of examples 1-12, wherein the determination of the overall glycemic state is cloud-based.
  • Example 14 The system of any one or more of examples 1-13, wherein the processing circuitry is further configured to determine one or more trends in the patient glycemic state.
  • Example 15 The system of any one or more of examples 1-14, wherein the processing circuitry is further configured to: based on the glycemic state of the patient, output a risk of diabetes for the patient.
  • Example 16 The system of example 15, wherein the processing circuitry is further configured to: based on the risk of diabetes for the patient, adjust one or more of the one or more morphology thresholds, a time threshold, or a frequency of periodic cardiac signal capture.
  • Example 17 A method comprising: storing, via one or more memories a medical device system, a plurality of cardiac signals of a patient; receiving, by processing circuitry of the medical device system, a respective assigned tag associated with one or more of the cardiac signals, wherein the respective assigned tag is indicative of a patient status associated with a corresponding cardiac signal of the one or more cardiac signals; filtering, by the processing circuitry, the one or more cardiac signals to generate a subset of cardiac signals based on the respective assigned tag indicative of the patient status meeting one or more criterion; determining, by the processing circuitry, an overall glycemic state of the patient based on the subset of cardiac signals; and outputting, by the processing circuitry, an indication to a user indicative of the overall glycemic state of the patient.
  • Example 18 The method of example 17, wherein the plurality of cardiac signals comprises one or more of: a baseline cardiac signal, wherein the baseline cardiac signal comprises a periodically captured cardiac signal; a patient-activated cardiac signal, wherein the patient-activated cardiac signal comprises a cardiac signal captured responsive to patient input; or a cardiac event cardiac signal, wherein the cardiac event cardiac signal comprises a cardiac signal captured responsive to a cardiac event.
  • Example 19 The method of example 18, wherein the cardiac event comprises one or more of: a bradycardia event, an atrial fibrillation event, an asystole event, a ventricular arrhythmia event, an atrial tachycardia event, an ST-segment deviation event, a QT interval prolongation event, or a patient activated event.
  • the cardiac event comprises one or more of: a bradycardia event, an atrial fibrillation event, an asystole event, a ventricular arrhythmia event, an atrial tachycardia event, an ST-segment deviation event, a QT interval prolongation event, or a patient activated event.
  • Example 20 The method of example 19, wherein the ventricular arrhythmia event comprises a ventricular tachycardia event.
  • Example 21 The method of any one or more of examples 17-20, wherein the patient status is based on cardiac event information associated with the cardiac signal.
  • Example 22 The method of any one or more of examples 17-21, wherein filtering the one or more cardiac signals comprises: removing, by the processing circuitry, cardiac signals having the respective assigned tag indicative of ventricular tachycardia or asystole; including, in the subset of signals, by the processing circuitry, cardiac signals having respective assigned tag indicative of baseline cardiac signal, atrial fibrillation, or patient activated cardiac signal.
  • Example 23 The method of any one or more of examples 17-22, further comprising: for the respective assigned tag, determining, by the processing circuitry, a tag- based glycemic state, wherein the tag-based glycemic state is associated with the patient status; and outputting, by the processing circuitry, the tag-based glycemic state to the user.
  • Example 24 The method of any one or more of examples 17-23, wherein determining the overall glycemic state comprises: inputting, by the processing circuitry, the subset of cardiac signals into a machine learning model; and determining, by the processing circuitry, the overall glycemic state based on an output from the machine learning model.
  • Example 25 The method of example 24, further comprising: for each cardiac signal of the subset of cardiac signals, determining, by the processing circuitry, one or more features, wherein to input the subset of cardiac signals, the processing circuitry is configured to input the one or more features into a machine learning model.
  • Example 26 The method of any one or more of examples 17-25, wherein a first portion of the processing circuitry of the medical device system comprises processing circuitry of a medical device, and wherein the first portion of the processing circuitry is configured to filter the one or more cardiac signals to generate the subset of cardiac signals.
  • Example 27 The method of example 26, further comprising: transmitting, by the first portion of the processing circuitry, the subset of cardiac signals to a computing system, wherein the computing system comprises a second portion of the processing circuitry, and wherein the second portion of the processing circuitry is configured to determine the overall glycemic state.
  • Example 28 The method of any of examples 26 or 27, wherein at least one of the first portion of the processing circuitry or the second portion of the processing circuitry is configured to assign the respective tag to corresponding cardiac signals of the one or more cardiac signals.
  • Example 29 The method of any one or more of examples 17-28, wherein the determination of the overall glycemic state is cloud-based.
  • Example 30 The method of any one or more of examples 17-29, wherein the processing circuitry is further configured to determine one or more trends in the patient glycemic state.
  • Example 31 The method of any one or more of examples 17-30, further comprising: based on the glycemic state of the patient, outputting, by the processing circuitry, a risk of diabetes for the patient.
  • Example 32 The system of example 31, further comprising: based on the risk of diabetes for the patient, adjusting, by the processing circuitry, one or more of the one or more morphology thresholds, a time threshold, or a frequency of periodic cardiac signal capture.
  • Example 33 A non-transitory computer-readable medium storing instructions that, when executed by processing circuitry, cause the processing circuitry to: receive a respective assigned tag associated with one or more cardiac signals of a plurality of cardiac signals of a patient, wherein the respective assigned tag is indicative of a patient status associated with a corresponding cardiac signal of the one or more cardiac signals; based on the respective assigned tag indicative of the patient status meeting one or more criterion, filter the one or more cardiac signals to generate a subset of cardiac signals; determine an overall glycemic state of the patient based on the subset of cardiac signals; and output an indication to a user indicative of the overall glycemic state of the patient. [0130] Various examples have been described. These and other examples are within the scope of the following claims.

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Biomedical Technology (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Pathology (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)

Abstract

L'invention concerne un système qui comprend : une ou plusieurs mémoires configurées : pour stocker une pluralité de signaux cardiaques d'un patient ; et un ensemble de circuits de traitement configuré : pour recevoir une étiquette attribuée respective associée à un ou plusieurs des signaux cardiaques, l'étiquette attribuée respective indiquant un état de patient associé à un signal cardiaque correspondant du ou des signaux cardiaques ; sur la base de l'étiquette attribuée respective indiquant l'état du patient satisfaisant à un ou plusieurs critères, pour filtrer le ou les signaux cardiaques pour générer un sous-ensemble de signaux cardiaques ; pour déterminer un état glycémique global du patient sur la base du sous-ensemble de signaux cardiaques ; et pour délivrer à un utilisateur une indication indiquant l'état glycémique global du patient.
PCT/IB2025/054282 2024-04-24 2025-04-24 Surveillance de l'état glycémique sur la base d'un signal cardiaque étiqueté Pending WO2025224670A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US202463638098P 2024-04-24 2024-04-24
US63/638,098 2024-04-24

Publications (1)

Publication Number Publication Date
WO2025224670A1 true WO2025224670A1 (fr) 2025-10-30

Family

ID=95825314

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/IB2025/054282 Pending WO2025224670A1 (fr) 2024-04-24 2025-04-24 Surveillance de l'état glycémique sur la base d'un signal cardiaque étiqueté

Country Status (1)

Country Link
WO (1) WO2025224670A1 (fr)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11311312B2 (en) 2013-03-15 2022-04-26 Medtronic, Inc. Subcutaneous delivery tool
US20230034970A1 (en) * 2021-07-28 2023-02-02 Medtronic, Inc. Filter-based arrhythmia detection

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11311312B2 (en) 2013-03-15 2022-04-26 Medtronic, Inc. Subcutaneous delivery tool
US20230034970A1 (en) * 2021-07-28 2023-02-02 Medtronic, Inc. Filter-based arrhythmia detection

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
PORUMB MIHAELA ET AL: "Precision Medicine and Artificial Intelligence: A Pilot Study on Deep Learning for Hypoglycemic Events Detection based on ECG", SCIENTIFIC REPORTS, vol. 10, no. 1, 13 January 2020 (2020-01-13), US, pages 1 - 16, XP093169996, ISSN: 2045-2322, Retrieved from the Internet <URL:https://www.nature.com/articles/s41598-019-56927-5> DOI: 10.1038/s41598-019-56927-5 *

Similar Documents

Publication Publication Date Title
US12308121B2 (en) Machine learning based depolarization identification and arrhythmia localization visualization
US20230329624A1 (en) Visualization of arrhythmia detection by machine learning
US12257060B2 (en) Methods and systems for predicting arrhythmia risk utilizing machine learning models
WO2022265841A1 (fr) Conditions de contournement d&#39;algorithme de décision
WO2025224670A1 (fr) Surveillance de l&#39;état glycémique sur la base d&#39;un signal cardiaque étiqueté
WO2025224669A1 (fr) État glycémique courant basé sur un signal cardiaque
US20240138743A1 (en) Premature ventricular contraction (pvc) detection using an artificial intelligence model
WO2025196554A1 (fr) Configuration de système médical pour examiner les transmissions de dispositif médical
US20220398470A1 (en) Adjudication algorithm bypass conditions
WO2025224686A1 (fr) Systèmes de détermination d&#39;éligibilité de patient pour des soins auto-administrés avec des anticoagulants oraux
WO2025224544A1 (fr) Fonctionnement d&#39;un système de dispositif médical pour identifier des échantillons de données cardiaques particuliers associés à un événement cardiaque
WO2024224194A1 (fr) Système médical conçu pour utiliser une séparation de source pour identifier des paramètres de patient à partir de signaux reçus de multiples dispositifs médicaux
WO2024249414A1 (fr) Fonctionnement d&#39;un système de dispositif médical implantable pour déterminer la probabilité de récurrence de fibrillation auriculaire
WO2025210417A1 (fr) Système médical pour la détermination d&#39;un score de risque pour prédire la survenue d&#39;arythmies et/ou d&#39;arrêt cardiaque soudain
WO2024050307A1 (fr) Surveillance de fraction d&#39;éjection et de dysfonctionnement du ventricule gauche basé sur un électrocardiogramme
WO2025177087A1 (fr) Système de dispositif médical configuré pour un dépistage préalable d&#39;un patient par rapport à un dispositif de thérapie et pour configurer le dispositif de thérapie pour le patient
WO2025088408A1 (fr) Fonctionnement d&#39;un système de dispositif médical pour déterminer des positions de fenêtre d&#39;un signal de battement de bruit cardiaque pour extraire des caractéristiques de bruit cardiaque
WO2024182052A1 (fr) Identification de fraction d&#39;éjection au moyen d&#39;un électrocardiogramme à dérivation unique détecté par un dispositif médical
WO2024049563A1 (fr) Identification de fraction d&#39;éjection au moyen d&#39;un électrogramme cardiaque à dérivation unique détecté par un dispositif médical
WO2025159861A1 (fr) Système médical configuré pour la discrimination d&#39;événements cardiaques à l&#39;aide d&#39;un apprentissage d&#39;ensemble et d&#39;une comparaison de morphologie
WO2024246636A1 (fr) Utilisation d&#39;un modèle d&#39;apprentissage automatique pré-entraîné avec des données d&#39;apprentissage non étiquetées pour générer des informations correspondant à des données cardiaques détectées par un dispositif médical
EP4510931A1 (fr) Tolérance d&#39;exercice utilisant un moniteur cardiaque implantable ou pouvant être porté
CN117479981A (zh) 判定算法绕过条件

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 25727482

Country of ref document: EP

Kind code of ref document: A1