System and method for clustering physiological events

Abstract

Systems and methods for managing physiological events generated by a medical device in a patient are discussed. An example system includes a controller circuit to receive information regarding a plurality of physiological events detected by a medical device in a patient, generate a respective feature set for each of the physiological events using the received information, and clustering the physiological events into different event groups using values of temporal or morphological features of the generated feature set. Each event group includes a respective set of physiological events. The controller circuit may identify, from the at least one group of events, a representative event representing a physiological event in the group of events, and output, to the user or process, the representative event and an indication that the representative event has been determined and represents a set of physiological events in the group of events.

Description

[0001] Priority claim

[0002] This application claims priority to U.S. Provisional Patent Application Serial No. 63 / 359,333, filed on July 8, 2022, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This document relates generally to patient management systems, and more particularly to systems, devices, and methods for automatically clustering a patient's physiological events to facilitate event review and adjudication by a clinician. Background Art

[0004] Implantable medical devices (IMDs) have been used to monitor the health status or disease state of patients and deliver treatment. For example, implantable cardioverter defibrillators (ICDs) can be used to monitor certain abnormal heart rhythms (or arrhythmias) and deliver electrical energy to the heart to correct abnormal heart rhythms. One of the most common arrhythmias is atrial fibrillation (AF), in which chaotic electrical impulses originating from the atrium or near the atrium cause irregular conduction to the ventricles, and cause inappropriately fast and irregular heart rates. AF may be paroxysmal, which can last from a few minutes to a few days, and then stop on its own. Persistent AF can last for more than a week, and usually requires drugs or other treatments to return to normal sinus rhythm. If treatment cannot restore normal heart rhythm, AF is permanent. Some IMDs can be used to monitor chronic heart disease (such as worsening of heart failure (WHF)), which can be characterized by cardiac asynchrony within or between ventricles. IMDs can provide cardiac stimulation therapy, such as cardiac resynchronization therapy (CRT), to correct cardiac asynchrony.

[0005] Some IMDs can record physiological data of the onset of an event and generate a patient alarm notification when a specific medical event (such as an arrhythmia event, a WHF event, or other physiological event) is detected. Some IMDs can record the onset of a patient-triggered medical event and record physiological data in response to the patient trigger. The recorded physiological data and alarm notification can be provided to a healthcare professional to signal the patient's health status. Through the notification, the healthcare provider can choose to review the recorded physiological data associated with the onset of the event, adjudicate the physiological event detected by the device (e.g., determine the presence or possible cause of the physiological event), or evaluate whether the treatment has produced the expected treatment outcome.

[0006] Patient management systems can monitor patients with IMDs that are interconnected to the patient management system via a data communications network. Such patient management systems can allow healthcare providers to follow up with patients remotely, or to periodically assess device functionality. Summary of the invention

[0007] Patient management system can store and manage a large amount of alarm notifications corresponding to the physiological events detected and reported by mobile medical equipment (AMD). For example, when managing the AMD patient queue in the clinic, the patient management system can often receive the alarm notifications of various arrhythmia attacks or worsening heart failure (WHF) events detected by implantable cardiac devices (such as cardiac monitors, pacemakers, implantable defibrillators or cardiac resynchronization therapy equipment). Some AMD can record the onset of patient triggers, such as when the patient shows certain signs or symptoms, or experiences the precursor events (such as arrhythmia, syncope or WHF events) indicating medical events. The physiological data associated with the onset of the physiological events detected by the device or the patient triggers can be sent to the patient management system, and checked by a clinician, for example, in order to adjudicate the physiological events detected by the device, arrange patient follow-up or reprogram AMD etc.

[0008] With a large number of AMDs connected to a patient management system, checking physiological events detected by the device (e.g., arrhythmia attacks) may require a large amount of time, clinical, technical, and human resources, which may be expensive for medical institutions. When an AMD is detected, physiological events with the same or similar potential causes (e.g., arrhythmia attacks of a specific type) can repeatedly trigger alarm notifications. For example, a patient with a history of atrial fibrillation (AF) may experience frequent AF attacks detected by an implantable medical device, whether properly detected (i.e., true positive or TP detection) or inappropriately detected (i.e., false positive or FP detection). TP detection of excess AF attacks may reflect highly frequent AF events, or be caused by the device being overly sensitive to noise or by temporary stabilization of the heart rate during potential long-term and persistent AF attacks. Repeated FP detection of AF attacks can be attributed to premature ventricular beats (PVCs), premature atrial beats (PACs), or atrioventricular conduction abnormalities, such as Wenckebach's atrioventricular block and other causes.

[0009] Excessive event onsets (TP-detected or FP-detected) and repeated alarm notifications increase clinician workload and healthcare costs. For example, since event onsets can be regularly reviewed by clinicians or other human experts, excessive event onsets increase the human burden of reviewing and / or adjudicating such onsets. In addition, storing such a large number of device-detected physiological events (e.g., sensor data and onset summaries) may occupy a large amount of device computing and storage resources.

[0010] Embodiments of the systems, devices, and methods discussed in this document can advantageously identify and cluster physiological events with similar attributes and improve the functionality of physiological event management systems, including prioritizing storage, display (e.g., for user review and adjudication), or transmission of physiological event data between devices (e.g., from an implantable device to an external device). An exemplary system includes a controller circuit for receiving information about a plurality of physiological events detected by a medical device in a patient, generating a corresponding feature set for each of the plurality of physiological events, and clustering the physiological events into different event groups using values ​​of temporal or morphological features of the feature set. Each event group includes a corresponding set of physiological events. The controller circuit can determine a representative event from at least one event group that represents the physiological events of the event group. A user or process can be provided with an indication that the representative event has been determined and represents a set of physiological events in the event group. The representative event can be automatically displayed and adjudicated by the user, while other physiological events in the same event group can be hidden to avoid display, and can be assigned the same adjudication as the representative event by default unless requested by the user or can only be displayed and / or adjudicated on demand.

[0011] Example 1 is a system for managing multiple physiological events detected by a medical device in a patient's body, the system comprising: a controller circuit configured to: receive information about multiple physiological events; for each of the multiple physiological events, generate a corresponding feature set using the received information, the feature set including time or morphological features with corresponding values; cluster the multiple physiological events into different event groups using the values ​​of the time or morphological features of the generated feature set, the different event groups each including a corresponding set of physiological events; determine a representative event representing the set of physiological events in at least one of the different event groups; and output the representative event and an indication that the representative event has been determined and represents the set of physiological events in at least one event group to a user or a system process.

[0012] In Example 2, the subject matter described in Example 1 optionally includes, wherein the controller circuit is configured to: initiate automatic display of information about the determined representative event on a user interface; hide information about a set of physiological events in at least one event group to avoid display on the user interface; and initiate on-demand display of information about one or more physiological events in a set of physiological events in at least one event group in response to a user command via the user interface.

[0013] In Example 3, the subject matter described in Example 2 optionally includes, wherein the user command includes a user selecting a physiological event from a set of physiological events in at least one event group, and wherein the controller circuit is configured to display information about the selected physiological event on a user interface in response to the user selection.

[0014] In Example 4, the subject matter described in any one or more of Examples 2-3 optionally includes a user interface configured to receive a ruling of a representative event from a user, wherein the controller circuit is configured to assign the received ruling of the representative event to each physiological event in a set of physiological events in at least one event group.

[0015] In Example 5, the subject matter according to any one or more of Examples 1-4 optionally includes wherein the controller circuit is configured to prioritize storage of information about the determined representative event over storage of information about a set of physiological events in at least one event group in the storage device.

[0016] In Example 6, the subject matter of any one or more of Examples 1-5 optionally includes wherein the controller circuit is configured to prioritize transmission of information about determined representative events between different devices over transmission of information about a set of physiological events in at least one event group.

[0017] In Example 7, the subject matter described in accordance with any one or more of Examples 1-6 optionally includes wherein the multiple physiological events include an arrhythmia episode detected from the patient, and the corresponding feature set generated includes at least one of: heart rate distribution features; arrhythmia duration; morphological features; or the time of day when the multiple physiological events are detected.

[0018] In Example 8, the subject matter according to any one or more of Examples 1-7 optionally includes that, in order to determine a representative event, the controller circuit is configured to: determine the centroid of the physiological event set of at least one event group in the feature space using a feature set generated correspondingly from at least a portion of the physiological event set; and determine the representative event of at least one event group as the physiological event closest to the determined centroid.

[0019] In Example 9, the subject matter according to any one or more of Examples 1-8 optionally includes that, in order to cluster multiple physiological events, the controller circuit is configured to: initialize cluster centers using a feature set of one of the multiple physiological events; iteratively update the cluster centers using the central tendency of the feature set correspondingly generated from the physiological events in the event group until a convergence criterion or an iteration stopping criterion is met; and assign the physiological events to cluster event groups based on a similarity measure between the physiological events and the iteratively updated cluster centers.

[0020] In Example 10, the subject matter described in Example 9 optionally includes wherein the controller circuit is configured to: calculate a corresponding similarity measure between the representative event and each physiological event in a set of physiological events in at least one event group; select a subset of events from the set of physiological events in at least one event group, each event subset having a corresponding similarity measure below a similarity threshold; and output an indication to a user or system process that the representative event represents the selected subset of events.

[0021] In Example 11, the subject matter described according to any one or more of Examples 1-10 optionally includes, wherein the controller circuit is configured to: calculate a corresponding similarity measure between each of the received multiple physiological events and the user-specified physiological event using a feature set generated accordingly from the received multiple physiological events and the user-specified physiological event; determine a set of physiological events in at least one event group whose corresponding similarity measures exceed a similarity threshold; and determine the user-specified physiological event as a representative event of at least one event group.

[0022] In Example 12, the subject matter described in Example 11 optionally includes a user interface configured to: display a plurality of received physiological events in a graphical representation of a feature space; receive user input to identify a user-specified physiological event; and display information of the user-specified physiological event and an indication of a set of physiological events in at least one event group represented by a representative event.

[0023] In Example 13, the subject matter of Example 12 may optionally include wherein the user interface is configured to receive user input of a similarity threshold or user selection of a predetermined clustering density.

[0024] In Example 14, the subject matter of any one or more of Examples 11-13 optionally includes wherein the controller circuit is configured to: generate an estimate of a workload reduction associated with assigning a user decision of a representative event to each physiological event in a set of physiological events in at least one event group; and determine or adjust a similarity threshold based on the generated estimate of the workload reduction.

[0025] In Example 15, the subject matter described in any one or more of Examples 11-14 optionally includes, wherein the controller circuit is configured to: generate an estimate of an error rate associated with assigning a user ruling of a representative event to each physiological event in a set of physiological events in at least one event group; and determine or adjust a similarity threshold based on the generated error rate estimate.

[0026] Example 16 is a method for managing multiple physiological events detected by a medical device in a patient's body, the method comprising: receiving information about multiple physiological events; generating a corresponding feature set for each of the multiple physiological events using the received information; clustering the multiple physiological events into different event groups using the generated feature sets of the multiple physiological events, the different event groups each including a corresponding set of physiological events; determining a representative event from at least one of the different event groups that represents the set of physiological events in at least one event group; and outputting a representative event and an indication to a user or process that the representative event has been determined and represents the set of physiological events in at least one event group.

[0027] In Example 17, the subject matter described in Example 16 optionally includes: initiating automatic display of information about the determined representative events on a user interface; hiding information about a set of physiological events in at least one event group to avoid display on the user interface; and initiating on-demand display of information about one or more physiological events in a set of physiological events in at least one event group in response to a user command via the user interface.

[0028] In Example 18, the subject matter of Example 17 optionally includes: receiving a ruling of a representative event from a user via a user interface; and automatically assigning the received ruling of the representative event to each physiological event in a set of physiological events in at least one event group.

[0029] In Example 19, the subject matter of any one or more of Examples 16-18 optionally includes prioritizing storage or transmission of information about the determined representative event over storage and transmission of information about a set of physiological events in at least one event group.

[0030] In Example 20, the subject matter according to any one or more of Examples 16-19 optionally includes, wherein clustering multiple physiological events into different event groups includes: initializing cluster centers using a feature set from one of the multiple physiological events; iteratively updating the cluster centers using the central tendency of the feature sets correspondingly generated from the physiological events in the event group until a convergence criterion or an iteration stopping criterion is met; and assigning the physiological events to the clustered event groups based on a similarity measure between the physiological events and the iteratively updated cluster centers.

[0031] In Example 21, the subject matter according to any one or more of Examples 16-20 optionally includes, wherein clustering multiple physiological events into different event groups includes: using feature sets generated accordingly from the received multiple physiological events and the user-specified physiological events to calculate a corresponding similarity measure between each of the received multiple physiological events and the user-specified physiological event; determining a set of physiological events in at least one event group whose corresponding similarity measures exceed a similarity threshold; and identifying the user-specified physiological event as a representative event in at least one event group.

[0032] In Example 22, the subject matter described in Example 21 optionally includes, via a user interface: displaying multiple received physiological events in a graphical representation of a feature space; receiving user-specified physiological events and user input of a similarity threshold or user selection of a predetermined clustering density; and displaying information about the user-specified physiological events and an indication of a set of physiological events in at least one event group representing representative events.

[0033] In Example 23, the subject matter of any one or more of Examples 21-22 optionally includes: generating an estimate of workload reduction or an estimate of error rate associated with assigning user decisions of representative events to each of a set of physiological events in at least one event group; and determining or adjusting a similarity threshold based on the generated estimate of workload reduction or the generated estimate of error rate.

[0034] The systems, devices, and methods discussed herein can improve physiological event and alarm management in patient monitoring systems. As previously mentioned, one of the challenges in physiological event management is that clinicians often need to handle a large number of excess physiological events or alarm notifications, which may be time-consuming and costly. This document provides a technical solution by clustering physiological events into groups, identifying representative events in each event group, and prioritizing physiological events in the same group for inspection and adjudication, such as automatically displaying only representative events for adjudication, while hiding other events in the event group to avoid display unless the user requests (i.e., presenting events other than representative events on demand), thereby simplifying the inspection and adjudication process. Compared with conventional physiological event and alarm management systems and methods, the clustering-based event inspection and adjudication described herein according to various embodiments can greatly reduce the number of events or alarm notifications presented to clinicians at almost no additional cost or system complexity. Therefore, the systems and methods described herein better integrate medical resources to provide services for patients with critical illnesses.

[0035] The clustering-based event inspection and adjudication discussed in this document can also improve the function of the computer system for managing physiological events and alarms. Event clustering, presentation and adjudication can be implemented and performed in a communicator, mobile monitor, programmer or remote patient management system that communicates with AMD. Therefore, in some cases, improved physiological events and alarm management can be achieved without modifying existing patient AMD or physiological event detectors. Because only a group of reduced physiological events (e.g., representative events in the clustered event groups) are presented for adjudication, the complexity and operating cost of the patient management system can be reduced. Prioritized data storage (such as only automatically storing representative events in event groups, and only storing other events (i.e., storage on demand) according to user requests) can utilize memory space more effectively. In certain embodiments, the physiological event detection implemented in AMD can be updated based on the user's adjudication of physiological events. The updated detection can help reduce false positive or false negative detection, and can arrange, prescribe or provide less unnecessary equipment treatment, medicine and program, can extend the battery life and life of AMD, and can achieve overall system cost saving.

[0036] This summary is an overview of some of the teachings of the present application and is not intended to be a unique or exhaustive treatment of the subject matter. Further details about this subject matter can be found in the detailed description and the appended claims. Other aspects of the present disclosure will be apparent to those skilled in the art upon reading and understanding the following detailed description and viewing the accompanying drawings, each of which should not be construed as limiting. The scope of the present disclosure is defined by the appended claims and their legal equivalents. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Various embodiments are shown by way of example in the figures of the accompanying drawings. Such embodiments are exemplary and are not intended to be exhaustive or exclusive embodiments of the subject matter.

[0038] Figure 1 An example of a patient management system and a portion of an environment in which the system may operate are generally shown.

[0039] Figure 2 An example of a physiological event management system configured to cluster physiological events to facilitate review and adjudication by a clinician is generally shown.

[0040] Figure 3 An example of a cardiac event management system configured to evaluate and prioritize cardiac events detected by a medical device associated with a patient is generally shown.

[0041] Figure 4A-4B shows the use of an unsupervised clustering algorithm ( Figure 4A) or user-specified cluster centers and clustering criteria ( Figure 4B ) Example of clustering physiological events in feature space.

[0042] Figure 5 Examples of at least portions of user interfaces for displaying information about physiological events and receiving user decisions about the events are shown.

[0043] Figure 6 Examples of workload reduction curves and adjudication error rate curves at different radius values ​​corresponding to user-defined clustered event regions are shown.

[0044] Figure 7 is a flow chart illustrating an example of a method for managing presentation and adjudication of physiological events detected by a medical device in a patient.

[0045] Figure 8 A block diagram of an example machine is generally shown upon which any one or more of the techniques (eg, methodologies) discussed herein may be performed. DETAILED DESCRIPTION

[0046] Disclosed herein are systems, devices, and methods for managing physiological events generated by a medical device in a patient. An exemplary system includes a controller circuit that can receive information about a plurality of physiological events detected by a medical device in a patient, generate a corresponding feature set for each of the plurality of physiological events using the received information, and cluster the physiological events into different event groups using the values ​​of the time or morphological features of the generated feature set. Each of the clustered event groups includes a corresponding set of physiological events. The controller circuit can determine a representative event representing the set of physiological events of the event group from at least one event group, and output to a user or process the representative event and an indication that the representative event has been determined and represents a set of physiological events in at least one event group. The representative event can be automatically displayed and adjudicated by the user, while other physiological events in the same event group can be hidden to avoid display, and can be assigned the same adjudication as the representative event by default unless requested by the user and can only be displayed and / or adjudicated on demand.

[0047] Although this document is focused on arrhythmia event management, it should be understood by those skilled in the art that this is only an example and not a limitation. According to the various examples described in this document, the systems, devices and methods for physiological event and alarm management can be applied to the management of other physiological events. The methods or techniques described in this document can be implemented in various mobile (e.g., implantable, wearable or portable) or fixed devices or medical systems.

[0048] Figure 1An example patient management system 100 and a portion of an environment in which the patient management system 100 may operate are shown. The patient management system 100 may perform a range of activities including remote patient monitoring and diagnosis of disease conditions. Such activities may be performed in the vicinity of the patient 101, such as at the patient's home or office, through a centralized server such as in a hospital, clinic, or doctor's office, or through a remote workstation such as a secure wireless mobile computing device.

[0049] The patient management system 100 may include one or more ambulatory medical devices, an external system 105, and a communication link 111 that provides communication between the one or more ambulatory medical devices and the external system 105. The one or more ambulatory medical devices may include an implantable medical device (IMD) 102, a wearable medical device (WMD) 103, or one or more other implantable, leadless, subcutaneous, external, wearable, or ambulatory medical devices configured to monitor, sense, or detect information from the patient 101, determine physiological information about the patient 101, or provide one or more therapies to treat various conditions of the patient 101, such as one or more cardiac or non-cardiac conditions (e.g., dehydration, sleep apnea, etc.).

[0050] In an example, IMD 102 may include one or more conventional cardiac rhythm management devices implanted in the patient's chest, having a lead system including one or more transvenous, subcutaneous, or non-invasive leads or catheters to position one or more electrodes or other sensors (e.g., heart sound sensors) in, on, or around the heart or one or more other locations in the chest, abdomen, or neck of patient 101. In another example, IMD 102 may include, for example, a monitor implanted subcutaneously in the chest of patient 101, IMD 102 including a housing containing circuitry and, in some examples, one or more sensors, such as a temperature sensor, etc.

[0051] IMD 102 may include an evaluation circuit configured to detect or determine specific physiological information of patient 101, or determine one or more conditions, or provide information or alarms to a user, such as patient 101 (e.g., patient), clinician, or one or more other caregivers or processes. IMD 102 may alternatively or additionally be configured as a therapeutic device configured to treat one or more medical conditions of patient 101. Therapy may be delivered to patient 101 via a lead system and associated electrodes or using one or more other delivery mechanisms. Therapy may include delivering one or more drugs to patient 101, such as using IMD 102 or one or more other ambulatory medical devices. In some examples, therapy may include cardiac resynchronization therapy for correcting asynchrony and improving cardiac function in patients with heart failure. In other examples, IMD 102 may include a drug delivery system, such as a drug infusion pump, to deliver drugs to the patient for management of arrhythmias or complications caused by arrhythmias, hypertension, or one or more other physiological conditions. In other examples, IMD 102 may include one or more electrodes configured to stimulate the patient's nervous system or provide stimulation to muscles of the patient's airway, etc.

[0052] WMD 103 may include one or more wearable or external medical sensors or devices (e.g., an automatic external defibrillator (AED), a Holter monitor, a patch-based device, a smart watch, a smart accessory, a wrist- or finger-worn medical device such as a finger-based photoplethysmography sensor, etc.).

[0053] The external system 105 may include a dedicated hardware / software system, such as a programmer, a remote server-based patient management system, or alternatively a system defined primarily by software running on a standard personal computer. The external system 105 may manage the patient 101 through the IMD 102 or one or more other ambulatory medical devices connected to the external system 105 via the communication link 111. In other examples, the IMD 102 may be connected to the WMD 103, or the WMD 103 may be connected to the external system 105 via the communication link 111. This may include, for example, programming the IMD 102 to perform one or more of acquiring physiological data, performing at least one self-diagnostic test (such as for device operating status), analyzing physiological data, or optionally delivering or adjusting treatment for the patient 101. In addition, the external system 105 may send information to the IMD 102 or WMD 103 via the communication link 111, or receive information from the IMD 102 or WMD 103. Examples of information may include: real-time or stored physiological data from patient 101; diagnostic data, such as detection of patient hydration status, hospitalization, response to therapy delivered to patient 101, or device operating status of IMD 102 or WMD 103 (e.g., battery status, lead impedance, etc.). Communication link 111 may be an inductive telemetry link, a capacitive telemetry link, or a radio frequency (RF) telemetry link, or wireless telemetry based on, for example, "strong" Bluetooth or IEEE 802.11 Wireless Fidelity "Wi-Fi" interface standards. Other configurations and combinations of patient data source interfaces are also possible.

[0054] The external system 105 may include an external device 106 located near one or more mobile medical devices, and a remote device 108 located relatively far from one or more mobile medical devices and communicating with the external device 106 via a communication network 107. Examples of the external device 106 may include a medical device programmer. The remote device 108 may be configured to evaluate the collected patient or patient information and provide alarm notifications, as well as other possible functions. In an example, the remote device 108 may include a centralized server that acts as a central hub for the storage and analysis of the collected data. The server may be configured as a single, multiple or distributed computing and processing system. The remote device 108 may receive data from multiple patients. The data may be collected by one or more mobile medical devices and other data acquisition sensors or devices associated with the patient 101. The server may include a memory device to store the data in a patient database. The server may include an alarm analyzer circuit to evaluate the collected data to determine whether a specific alarm condition is met. The satisfaction of the alarm condition may trigger the generation of an alarm notification, such as provided by one or more human-perceivable user interfaces. In some examples, the alarm condition may alternatively or additionally be evaluated by one or more mobile medical devices (such as implantable medical devices). By way of example, the alarm notification may include a web page update, a telephone or pager call, an email, SMS, a text or "instant" message, and a message to the patient and a direct notification to both emergency services and clinicians. Other alarm notifications are also possible. The server may include an alarm prioritization circuit that is configured to prioritize alarm notifications. For example, a similarity metric between physiological data associated with a detected medical event and physiological data associated with historical alarms may be used to prioritize alarms for detected physiological events.

[0055] The remote device 108 may additionally include one or more locally configured clients or remote clients securely connected to the server via the communication network 107. Examples of clients may include personal desktops, laptops, mobile devices, or other computing devices. System users, such as clinicians or other qualified medical professionals, can use the client to securely access stored patient data collected in a database in the server, and select and prioritize patients and alarms for healthcare provision. In addition to generating alarm notifications, the remote device 108, including the server and interconnected clients, can also execute a follow-up plan by sending a follow-up request to one or more mobile medical devices, or by sending a message or other communication as a compliance notification to the patient 101 (e.g., the patient), a clinician, or an authorized third party.

[0056] The communication network 107 can provide wired or wireless interconnection. In an example, the communication network 107 can be based on the Transmission Control Protocol / Internet Protocol (TCP / IP) network communication specification, although other types or combinations of networking implementations are also possible. Similarly, other network topologies and arrangements are also possible.

[0057] One or more of the external device 106 or remote device 108 may output the detected physiological events to a system user, such as a patient or clinician, or to a process including, for example, an instance of a computer program executable in a microprocessor. In an example, the process may include automatically generating a recommendation for antiarrhythmic therapy, or a recommendation for further diagnostic testing or treatment. In an example, the external device 106 or remote device 108 may include a corresponding display unit for displaying physiological or functional signals, or an alarm, an alert, an emergency call, or other form of warning to signal the detection of an arrhythmia. In some examples, the external system 105 may include an external data processor configured to analyze physiological or functional signals received by one or more ambulatory medical devices and confirm or reject the detection of an arrhythmia. Computationally intensive algorithms, such as machine learning algorithms, may be implemented in the external data processor to retrospectively process data to detect arrhythmias.

[0058] Portions of one or more mobile medical devices or external systems 105 may be implemented using hardware, software, firmware, or a combination thereof. Portions of one or more mobile medical devices or external systems 105 may be implemented using dedicated circuits that may be constructed or configured to perform one or more functions, or may be implemented using general-purpose circuits that may be programmed or otherwise configured to perform one or more functions. Such general-purpose circuits may include a microprocessor or a portion thereof, a microcontroller or a portion thereof, or a programmable logic circuit, a memory circuit, a network interface, and various components for interconnecting these components. For example, a "comparator" may include, among other things, an electronic circuit comparator that may be constructed to perform a specific function of a comparison between two signals, or the comparator may be implemented as a portion of a general-purpose circuit that may be driven by a code that instructs a portion of a general-purpose circuit to perform a comparison between two signals. A "sensor" may include an electronic circuit configured to receive information and provide an electronic output representing such received information.

[0059] The therapeutic device 110 can be configured to send information to or receive information from one or more of the mobile medical devices or the external system 105 using the communication link 111. In an example, one or more mobile medical devices, the external device 106, or the remote device 108 can be configured to control one or more parameters of the therapeutic device 110. The external system 105 can allow programming of one or more mobile medical devices, and can receive information about one or more signals acquired by one or more mobile medical devices, such as can be received via the communication link 111. The external system 105 can include a local external implantable medical device programmer. The external system 105 can include a remote patient management system, which can monitor the patient's status or adjust one or more treatments, such as from a remote location.

[0060] Figure 2 An example of a physiological event management system 200 is generally shown that is configured to cluster physiological events to improve event presentation and adjudication. At least a portion of the system 200 can be implemented in an external system 105 (such as one or more of the external device 106 or the remote device 108), or distributed between the external system 105 and one or more of the IMD 102 or WMD 103.

[0061] The system 200 may include one or more of a memory circuit 210, a controller circuit 220, a user interface 230, and an optional therapy circuit 250. The memory circuit 210 may be included in a storage device in the external system 105, such as within the external device 106 or the remote device 108. Alternatively, the memory circuit 210 may be included in an electronic medical record (EMR) system. The memory circuit 210 may store episodes of patient physiological events, such as those detected and recorded by the IMD 102 or WMD 103, in a physiological event library 212. In an example, the memory circuit 210 may be communicatively coupled to the IMD 102 or WMD 103 and receive episodes of physiological events from the IMD 102 or WMD 103, such as via the communication link 115, as described in reference to FIG. Figure 3 discussed.

[0062] In an example, the physiological event episodes stored in the physiological event library 212 may include cardiac events, such as arrhythmia episodes detected and recorded by the IMD 102 or WMD 103. Examples of arrhythmia episodes may include atrial arrhythmia episodes, supraventricular arrhythmia episodes, or ventricular arrhythmia episodes, etc. The arrhythmia episode may include corresponding physiological data sensed from one or more physiological sensors during the detected arrhythmia event, or additional physiological data sensed before and / or after the arrhythmia event is detected. The physiological data associated with the arrhythmia episode may include electrocardiographic signals, such as one or more electrocardiogram (ECG) or electrogram (EGM) signals sensed at various cardiac sites using different electrode combinations, such as one or more atrial EGMs or one or more ventricular EGMs. Additionally or alternatively, the physiological data may include cardiac mechanical signals or hemodynamic signals, such as cardiac pressure signals, impedance signals, heart sound signals, etc. In various examples, each arrhythmia episode may additionally include an arrhythmia detection or classification generated by a medical device such as IMD 102 or WMD 103. The arrhythmia detection or classification is a designation of a particular arrhythmia type, such as atrial fibrillation, atrial flutter, ventricular tachycardia, or ventricular fibrillation, etc. Other information about the arrhythmia episode, such as measurements or signal metrics obtained from physiological data (e.g., atrial rate, ventricular rate, variability of atrial rate or ventricular rate), may also be associated with the corresponding episode and stored in the physiological event library 212.

[0063] In some examples, the physiological event library 212 can include patient-triggered episodes, including physiological data sensed from one or more physiological sensors in response to a patient trigger, such as when a patient experiences a physiological event. Other information (such as patient input regarding the presence of a physiological event and the severity of symptoms, temporal information of symptoms (such as the start and end time of the patient-triggered episode)) can also be associated with the patient-triggered episode and included in the physiological event library 212.

[0064] Although the discussion of physiological event management in this document focuses on arrhythmia episodes, this is intended to be illustrative and not restrictive, nor is it limiting in any way. The onset of other types of physiological events (such as syncope, heart failure exacerbation events, or heart failure decompensation events) can also be stored, analyzed, and provided to clinicians for adjudication using the systems, devices, and methods discussed herein.

[0065] The controller circuit 220 can be implemented as a component of a microprocessor circuit, which can be a special-purpose processor, such as a digital signal processor, an application-specific integrated circuit (ASIC), a microprocessor, or other type of processor for processing information including physical activity information. Alternatively, the microprocessor circuit can be a general-purpose processor that can receive and execute instruction sets that perform the functions, methods, or techniques described herein.

[0066] Controller circuit 220 may include a circuit set including one or more other circuits or subcircuits, including feature extractor circuit 221, clustering circuit 222, display control circuit 225, and arbiter circuit 226. The circuits or subcircuits may perform the functions, methods, or techniques described herein alone or in combination. In an example, the hardware of the circuit set may be designed to perform a specific operation (e.g., hardwired) in a fixed manner. In an example, the hardware of the circuit set may include variably connected physical components (e.g., execution units, transistors, simple circuits, etc.) that include physically modified computer-readable media (e.g., magnetic, electrical, movable placement of fixed aggregate particles, etc.) to encode instructions for specific operations. When the physical components are connected, the basic electrical properties of the hardware components change, for example, from an insulator to a conductor, and vice versa. The instructions enable embedded hardware (e.g., an execution unit or a loading mechanism) to create components of the circuit set in hardware via variable connections to perform parts of a specific operation when in operation. Therefore, when the device is operating, the computer-readable medium is communicatively coupled to other components of the circuit set components. In an example, any physical component may be used in more than one component of more than one circuit set. For example, in operation, an execution unit may be used in a first circuit of a first circuit set at one point in time and reused by a second circuit in the first circuit set, or reused by a third circuit in a second circuit set at a different time.

[0067] The feature extractor circuit 221 may receive information about physiological events from the physiological event library 212, such as N events {X1, X2, . . . , X N}, and extract the corresponding feature set from each of the received events (e.g., event X k A set of M features {S1, S2, ..., S M}). In an example, the information of the received physiological events may include physiological data (e.g., ECG, EGM, or other sensor signals) recorded during an arrhythmia episode (and optionally before and / or after an arrhythmia episode) detected by an ambulatory device such as IMD 102 or WMD 103. The features (e.g., M features {S1, S2, . . . , S M}) may include one or more of heart rate distribution features, arrhythmia duration, or morphological features. Heart rate distribution features are important features of atrial or ventricular tachyarrhythmias and may be represented by the amount of heartbeats for each of a plurality of heart rates or a plurality of heart rate ranges (or the cumulative duration of these heartbeats) or a percentage of total heartbeats (or a percentage of total heartbeat duration) within a specified time period. Arrhythmia duration represents the duration from the start to the termination of the arrhythmia detected by the IMD 102 or WMD 103. Morphological features include signal waveform characteristics, such as slope, peak amplitude, curvature, area under the curve, or a measure of similarity (e.g., correlation) between a portion of the attack signal and a predetermined morphological template. In some examples, the features extracted by the feature extractor circuit 221 from each of the received arrhythmia episodes may include time information of the arrhythmia episode, such as the time of day when the arrhythmia episode is detected and recorded by the IMD 102 or WMD 103.

[0068] The clustering circuit 222 may cluster the physiological events based on the feature set (such as N events {X1, X2, . . . , X N} of each of the M features {S1, S2, …, S M}) Cluster the received physiological events into different event groups 223. The extracted feature set can form a feature space S, such as a space composed of M features {S1, S2, ..., S M} spans an M-dimensional space. Each physiological event can be represented as a data point in the feature space S. In an example, clustering can be performed using an unsupervised clustering algorithm. In order to cluster the physiological events, the clustering circuit 222 can initialize one or more clusters, each cluster containing, for example, randomly selected physiological events. Physiological events (e.g., X) can be clustered based on a similarity measure between the physiological events and the cluster centers. k ) is assigned to one of the event groups 223. Examples of similarity metrics may include distance measures (e.g., Euclidean distance), connectivity, or strength between the corresponding feature sets of the physiological events in the feature space S and the cluster centers. A larger distance indicates that the similarity between the physiological events and the cluster centers is smaller. The cluster centers may be iteratively updated using the central tendency (e.g., mean or median) of the feature sets correspondingly extracted from the physiological events assigned to the event group until a convergence criterion or an iteration stop criterion is met.

[0069] Various clustering algorithms can be used to cluster received physiological events. Clustering algorithms may differ in a set of rules for defining similarities between data points in feature space. One class of clustering algorithms is based on a centroid model that interactively establishes clustered event groups using a similarity metric derived from the proximity of data points to the cluster centroid. In an example, the clustering circuit 222 can use a k-means clustering method that minimizes the intra-cluster variance between sets of physiological events in the same clustered event group. When N events are clustered into k groups, the k-means clustering method minimizes the sum of the intra-cluster variances of all k groups. In some examples, a variant of k-means clustering can be used to cluster N physiological events. In an example, k-median clustering uses the median (rather than the mean) of each feature dimension to determine the centroid or cluster center of each cluster. In another example, k-medoids use actual data points (observations) as cluster centers instead of the calculated mean of data points in the cluster that are not necessarily actual input data points. In addition, the k-centers minimize the sum of pairwise dissimilarity rather than the sum of squared Euclidean distances, which is more robust to noise and outliers than k-means clustering. In yet another example, fuzzy C-means clustering can be used to cluster received physiological events. Compared to hard clustering (such as k-means clustering) where data points are either assigned to a cluster or not assigned to a cluster, fuzzy C-means clustering is a soft clustering method that assigns fuzziness to each data point to represent the probability or likelihood that the data point belongs to each of two or more clusters. Fuzzy C-means is a soft clustering technique. In addition to k-means clustering or its variants or as an alternative to k-means clustering or its variants, other clustering methods can also be used, such as clustering based on statistical distribution models (e.g., Gaussian mixture models); connectivity-based clustering, which defines clusters by the maximum distance required to connect different parts of the cluster; density-based clustering methods, which define clusters as areas with higher density than the rest of the data set, etc.

[0070] Each of the one or more clustered event groups 223 includes a corresponding set of physiological events, which is a set of N received events {X1, X2, . . . , X N}. The clustering circuit 222 can determine a corresponding representative event 224 representing a physiological event in the corresponding event group from each of the clustered event groups 223. In an example, the representative event 224 can be identified as a physiological event in the event group that is closest to the centroid of the physiological events in the event group (e.g., the Euclidean distance in the feature space S). For example, for P physiological events {Y1, Y2, ..., Y P}, the cluster center Y * can be determined from the physiological events {Y1, Y2, ..., Y PThe centroid of the feature set (e.g., M-dimensional feature set) extracted accordingly in}. The distance from the cluster center Y in the group * Recent physiological events (e.g. k ) can be identified as a representative event. Figure 4A Discuss examples of using supervised clustering algorithms to cluster physiological events and identify representative events.

[0071] In addition to or as an alternative to automatic, unsupervised learning-based clustering (such as k-means clustering (or its variants)), in some examples, the clustering circuit 222 can cluster the received physiological events according to a user-specified set of cluster centers and clustering rules. In an example, the user can cluster physiological events (e.g., from N events {X1, X2, ..., X N} k ) is designated as the cluster center. The clustering circuit 222 can use its corresponding feature set to calculate a similarity measure (e.g., Euclidean distance in feature space S) between the user-specified cluster center and each of the N physiological events. Then, the clustering circuit 222 can establish a cluster event group by assigning corresponding similarity measures that meet the similarity criteria (e.g., the corresponding Euclidean distance to the cluster center is below a threshold) to these physiological events. Figure 4B Discuss an example of clustering physiological events using user-specified cluster centers and clustering criteria.

[0072] The display control circuit 225 can prioritize the display of the set of physiological events in each event group 223 on the display unit of the user interface 230. In an example, at least a portion of the user interface 230 can be implemented in the external system 105. The information of the displayed physiological events may include physiological data (e.g., ECG, EMG, or other sensor signals) recorded during the physiological event (and optionally before and / or after the physiological event), device parameters for detecting the physiological event, and a summary of the detection results including, for example, the detected event type and statistical data. In an example, the priority display of the event information may include automatic display of information about the representative event of the event group, and hiding the display of information about other physiological events (except the representative event) in the event group until or unless the user requests it. In an example, the display control circuit 225 may provide a notification to the user (e.g., a message displayed on the user interface 230) indicating that the representative event represents a set of physiological events in the event group, without automatically displaying information about a single physiological event other than the representative event, and prompting the user to provide a command to display information about any physiological event in the event group. In response to a user command, the display control circuit 225 can initiate an on-demand display of information about one or more physiological events in the event group. In an example, the user command can include a user selection of a physiological event from the event group. In response to the user selection, the display control circuit 225 can display information about the selected physiological event.

[0073] In some examples, the control circuit 220 can prioritize the storage of the physiological event sets in each event group 223 in the storage device, so that high priority events can be stored in the storage device before low priority events in the same group (e.g., Figure 3In some examples, the representative events of the corresponding event groups may be stored in the storage device with a higher priority than other events in the corresponding event groups. In order to save memory, in some examples, only the representative events of the corresponding event groups are stored in the storage device, and other events in the corresponding event groups may be discarded (i.e., not stored). In some examples, within the clustered event group, events that are dissimilar to the representative events ("dissimilar" events whose similarity values ​​are lower than a threshold or farther from the representative events or the clustering center in the feature space S) may have a higher priority than events that are similar to the representative events (e.g., "similar" events whose similarity values ​​are higher than a threshold or closer to the representative events or the clustering center in the feature space S). Since "similar" events are better represented by representative events than "dissimilar" events, "dissimilar" events are prioritized over "similar" event sorting, which can allow "dissimilar" events to be retained, presented to users, checked and ruled, thereby reducing the error rate associated with assigning the same ruling of representative events to all other events in the same event group. In some examples, high priority events can be automatically stored in a storage device, and low priority events can be stored on demand (i.e., according to user's request). In some examples, event priorities in different clustered event groups can be based on the number of events in the corresponding event group to ensure that various event types can be checked and ruled. For example, between a "dense" event group with a large number of events and a "sparse" event group with a relatively small number of events, more events from a "dense" event group rather than a "sparse" event group can be assigned high priority. The priority display and priority storage of physiological events based on clustering as described herein advantageously utilize system sources more effectively, and improve the function of a computer system for managing physiological events.

[0074] The arbiter circuit 226 can receive a user ruling on the physiological events in the clustered event group 223. The user can provide the ruling through the user interface 230. The ruling can include a user specification of the event type of the physiological event presented to the user. In the example of arrhythmia ruling, the user can identify the arrhythmia type, such as atrial fibrillation, atrial flutter, supraventricular tachycardia, ventricular tachycardia, or ventricular fibrillation. The arbiter circuit 226 can compare the event type identified by the user with the device detection result generated by the IMD 102 or WMD 103, and if the user ruling is consistent with the device detection result, the episode is identified as a true positive (TP) (or appropriate) detection, or if the user ruling is different from the device detection result, it is identified as a false positive (FP) (or inappropriate) detection. If a TP or FP decision cannot be made, the episode can be identified as an uncertain event. In addition, the user can provide annotations about the episode characteristics or diagnostic information of the physiological event episode. For example, when ruling an AF episode detected by the device, the user (e.g., a clinician) can specify one of multiple episode characteristics as the reason for forming his or her ruling decision. Refer to the following Figure 5 Examples of user interfaces for receiving adjudications or annotations of physiological events are discussed.

[0075] In some examples, when information about such events (e.g., ECG, EGM, or other sensor data) is displayed on the user interface, the arbitrator circuit 226 can arbitrate physiological events in the clustered event group. Based on the priority display of physiological events in the clustered event group, the arbitrator circuit 226 can prioritize event adjudication in the order in which the events are displayed. For example, since the representative event is automatically displayed before other events in the same event group, the representative event can be adjudicated before other physiological events displayed on demand. In some examples, when adjudicating the representative event, the arbitrator circuit 226 can assign the same adjudication of the representative event to each of the physiological events in the event group. Therefore, unless otherwise modified (e.g., by the user), by default, all physiological events in the event group will have the same event type as the representative event that has been adjudicated. In an example, in response to the on-demand display of a physiological event selected from the clustered event group, the arbitrator circuit 226 can initiate an on-demand adjudication of such a physiological event, thereby allowing the user to confirm, reject, or modify the default adjudication. Clustering-based prioritization and adjudication as discussed herein may not only improve the functionality of computer systems used to manage physiological events, but may also reduce clinician workload and improve the efficiency of physiological event review and adjudication.

[0076] In some examples, as more additional physiological events are detected from the patient and added to the event library 212, the controller circuit 220 can use information about these additional physiological events to update the previously established clusters. The update of the clusters can be performed periodically, or in response to the number of additional events received reaching a threshold. In some examples, the controller circuit 220 can initiate a process of updating the clusters based on the ruling performance. The ruling performance can be measured by an estimate of the workload reduction associated with assigning the same ruling of the representative event to all other physiological events in the same event group and an estimate of the ruling error rate. In an example, the controller circuit 220 can generate an estimate of the ruling error rate based on the on-demand ruling of the physiological events in the clustered event group (except the representative event). If the estimated error rate exceeds the fault tolerance level, the controller circuit 220 can update the clustering, such as by re-initiating the clustering process using the updated received arrhythmia attack set, or by adjusting one or more clustering criteria (e.g., defining a similarity measure or distance threshold for clustering). In another example, the controller circuit 220 may determine a performance metric that is proportional to the amount of workload reduction and inversely proportional to the adjudication error rate, such that a high workload reduction will result in an increase in the performance metric, while a high adjudication error will decrease the performance metric. If the performance metric is below a performance threshold, the controller circuit 220 may update the clustering. The updating of the clustering may include updating of representative events of the corresponding clustering. In some examples, the updated representative events may determine an active adjustment to one or more clustering criteria (e.g., a similarity metric threshold that defines the size or boundaries of a clustered event group) based on a deviation of the performance metric from the performance threshold. More active adjustments (e.g., a substantial reduction in the similarity threshold) may be made in response to a severe deterioration in adjudication performance.

[0077] As previously described, the user interface 230 may include a display unit that can be controlled by the display control circuit 225 to display information about physiological events, and a user input device for receiving user input, such as a ruling on a physiological event displayed on the display unit. The user interface 230 may be coupled to a printer for printing a hard copy of the detection information. The information may be presented in a table, chart, schematic diagram, or any other type of text, table, or graphic presentation format. The presentation of the output information may include audio or other media formats. In an example, the output unit may generate an alarm, warning, emergency call, or other form of warning to send a signal about the detected physiological event to the user. In some examples, the user interface 230 may additionally generate a suggestion for adjusting the operation of the IMD 102 or WMD 103 based on the ruling of the physiological event, such as a suggested adjustment of a parameter for sensing a physiological signal or a parameter for detecting a physiological event.

[0078] The optional therapy circuit 250 can be configured to deliver therapy to the patient in response to the detection of a target physiological event. Examples of therapy can include electrical stimulation therapy delivered to the heart, neural tissue, other targeted tissue, cardioversion therapy, defibrillation therapy, or drug therapy including delivery of a drug to a tissue or organ. In some examples, the therapy circuit 250 can modify an existing therapy, such as adjusting stimulation parameters or drug dosage.

[0079] Figure 3 Generally, an example of a cardiac event management system 300 is shown that is configured to evaluate and prioritize cardiac events detected by a medical device associated with a patient. The system 300 includes an ambulatory medical device (AMD) 310 and an external system 320 that are communicatively coupled to each other via a communication link 115. The AMD 310 (which is a Figure 1 102 or WMD 103) can include sensor circuitry 311 for sensing one or more physiological signals from a subject. The physiological signals can be sensed via one or more implantable, wearable, or other ambulatory sensors or electrodes associated with the patient. The sensors can be incorporated into or otherwise associated with an ambulatory device such as IMD 102 or WMD 103. Examples of physiological signals may include a surface electrocardiogram (ECG) sensed from electrodes placed on the body surface, a subcutaneous ECG sensed from electrodes placed under the skin, an intracardiac electrogram (EGM) sensed from one or more electrodes on a lead system, a thoracic or cardiac impedance signal, an arterial pressure signal, a pulmonary artery pressure signal, a left atrial pressure signal, a RV pressure signal, a LV coronary pressure signal, a coronary blood temperature signal, a blood oxygen saturation signal, a heart sound signal (such as sensed by a mobile accelerometer or an acoustic sensor), a physiological response to activity, an apnea-hypopnea index, one or more respiratory signals (such as a respiratory rate signal or a tidal volume signal), brain natriuretic peptide (BNP), a blood panel, sodium and potassium levels, blood glucose levels, and other biomarkers and biochemical markers, etc. The sensor circuit 311 may include one or more subcircuits to digitize, filter, or perform other signal conditioning operations on the received physiological signals. In some examples, the sensor circuit 311 may record patient-triggered episodes. When a patient exhibits certain signs or symptoms or experiences a precursor event indicative of a target physiological event, a trigger may be generated and detected by a patient-triggered detector. Detection of a patient trigger may activate sensor circuit 311 to record a patient-triggered episode and acquire physiological data, such as one or more physiological signals.

[0080] The arrhythmia detector circuit 312 can be configured to detect an arrhythmia episode using one or more sensed physiological signals. Examples of arrhythmias can include atrial fibrillation, atrial flutter, supraventricular tachycardia, ventricular tachycardia, or ventricular fibrillation. Detection can be based on timing or morphological features extracted from one or more physiological signals. In an example, the arrhythmia detector circuit 312 can use a configurable detection algorithm to detect a specific arrhythmia, so that one or more detection algorithm features can be added or modified via a programming device. Detected arrhythmia episodes (including physiological data collected during or additionally before and / or after detection and test results) can be stored in the internal memory 314.

[0081] The communication circuit 315 may transmit the detected arrhythmia episodes (including physiological data and device-generated detection results) to the external system 320 via the communication link 115. The transmission may be performed continuously, periodically at a predetermined time, or in response to a data query command sent from the external system 320 to the AMD 310. The external system 320 (e.g., Figure 1 The external system 105 (an embodiment of the external system 105 shown in FIG. 1 ) can receive arrhythmia episodes via the communication circuit 325 and store the received arrhythmia episodes in the external memory 322. The external memory 322 (which is an embodiment of the memory circuit 210) can store the arrhythmia episodes in the physiological event library 212. The external system 320 can also include a controller circuit 220 and a user interface 230. The controller circuit 220 can arrange for the presentation of one or more arrhythmia episodes for arbitration. As described above with reference to Figure 2 As described, the controller circuit 220 can cluster the received arrhythmia episodes into different event groups, each event group including a set of episodes represented by a representative episode in the corresponding event group, and prioritize the display of arrhythmia episodes in the clustered event group. The user interface 230 can initiate automatic display of information (e.g., physiological data and AMD detection results) about the representative episodes in the clustered event group in response to user commands, and initiate on-demand display of information about other arrhythmia episodes in the clustered event group. The user interface 230 can additionally receive a user-determined arrhythmia type for the representative episode. By default, all arrhythmia episodes in the event group will have the same user-determined arrhythmia type as the representative event, unless modified by the user via the on-demand determination process, as described above with reference to Figure 2In some examples, the controller circuit 220 may assign an arrhythmia episode received from the AMD 310 to one of the established clustered event groups, such as based on its similarity (e.g., distance in feature space S) to each of the representative episodes of the corresponding clustered event group. By default, the assigned arrhythmia episode may have the same adjudicated arrhythmia type as the representative episode, unless or until modified by the user via the on-demand display and adjudication process.

[0082] The external system 320 includes a programmer 324 that can generate commands for programming the AMD 310. The commands can include recommended adjustments to one or more detection parameters of the arrhythmia detector circuit 312, or data collection parameters of the sensor circuit 311, etc. The recommended adjustments can be confirmed or otherwise modified by a user (e.g., a clinician) via the user interface 230 and forwarded to the AMD 310 via the communication link 115. The AMD 310 can detect the target physiological event using the modified algorithm.

[0083] although Figure 3 The controller circuit 220 is shown to be included in the external system 320, but this is by way of example and not limitation. In some examples, at least a portion of the controller circuit 220 (such as the feature extractor circuit 221 and the clustering circuit 222) can be implemented in the AMD 310, while some other portions of the controller circuit 220 (such as the display control circuit 225 and the arbiter circuit 226) can be implemented in the external system 320. In the AMD 310, arrhythmia episodes detected by the arrhythmia detector circuit 312 and / or arrhythmia episodes stored in the internal memory 314 can be processed by the feature extractor circuit 221 and the clustering circuit 222 and clustered into one or more clustered event groups. The clustered arrhythmia episodes can be stored in the internal memory 314 and sent to the external system 320 via the communication link 115 automatically or upon user request.

[0084] Seizure data storage and / or transmission may be prioritized based on clustering of seizures. High priority seizures may be stored in a storage device (e.g., internal memory 314 or external memory 322) and / or sent between devices (e.g., from mobile medical device 310 to external system 320) before low priority seizures in the same group. Additionally or alternatively, more system resources (e.g., storage space and / or communication bandwidth) may be allocated for storing and / or sending high priority seizures rather than for storing and / or sending low priority seizures. In an example, a representative seizure of a corresponding event group may have a higher priority than other seizures in the corresponding event group. In some examples, within a clustered event group, a higher priority may be assigned to "dissimilar" seizures (similarity values ​​below a threshold) rather than "similar" events (similarity values ​​above a threshold). Sorting "dissimilar" events over "similar" events may allow "dissimilar" events to be retained, presented to a user, inspected, and adjudicated, thereby reducing the error rate associated with assigning the same adjudication of a representative event to all other events in the same event group. In some examples, the priority treatment of the occurrences in different clustered event groups can be based on the number of events in the corresponding event group to ensure that various event types are checked and adjudicated. In some examples, high priority events can be automatically stored in a storage device and / or sent between devices, while low priority events can be stored and / or sent on demand (i.e., upon user request). In order to save system resources (e.g., storage space and / or communication bandwidth), in some examples, only representative occurrences of the corresponding event group are stored and / or sent, and other events in the corresponding event group can be discarded.

[0085] In the external system 320, the display control circuit 225 can prioritize the display of arrhythmia episodes of the clustered event group, such as automatically displaying information about a representative episode while hiding other episodes in the event group from display until or unless requested by the user (i.e., displaying other episodes on demand). The arbiter circuit 226 can receive the user-arbitrated arrhythmia type of the representative episode of the event group. The programmer 324 can generate commands for programming the AMD 310.

[0086] Figure 4A-4B An example of clustering physiological events in a feature space S is shown. Each physiological event is represented by a data point in a graphical representation of the feature space S. The coordinates of the data point correspond to a corresponding set of feature values ​​extracted from the corresponding physiological event. By way of example and not limitation, Figure 4A and 4BAs shown, each physiological event is represented by a data point in a two-dimensional feature space spanned by features S1 and S2. In an example of clustering arrhythmia episodes detected by a medical device from a patient, the feature set may include heart rate distribution features, arrhythmia duration, morphology features, or temporal features, such as the time of day when the arrhythmia episode was detected. Figure 4A and 4B The diagrams shown in may each be displayed on the display unit of the user interface 230 .

[0087] Figure 4A The automatic clustering of physiological events using an unsupervised clustering algorithm (such as k-means clustering or its variants) is shown, as described above with reference to Figure 2 As shown in Figure 400A, three clustered event groups 410, 420, and 430 are formed, each event group includes a corresponding set of physiological events and a cluster center (e.g., centroid) representing all physiological events in the event group. For example, clustered event group 420 has cluster center 421. Clustering circuit 222 can determine a representative event 422 closest to cluster center 421 from event group 420. Indications that representative event 422 and representative time 422 represent physiological events of event group 420 can be displayed on user interface 230.

[0088] Information about representative event 422 may be automatically displayed on user interface 230 , and a user decision of representative event 422 may be received from a user. Figure 5 An example of at least a portion of a user interface 500 (an embodiment of a display unit of the user interface 230) is shown for displaying information about physiological events and receiving user decisions about the events. By way of example and not limitation, the information may include physiological data 512 and measurement trends 514 obtained from the physiological data 512. Information about a patient identification and an episode number may also be displayed and may be selected, such as using drop-down lists, check boxes, radio buttons, list boxes, buttons, toggles, text fields, and other input control elements on the user interface 400. The physiological data 512 may be sensed using electrodes or physiological sensors in communication with a medical device and collected during, or alternatively before or after, a detected physiological event. In an example, the physiological data 512 may be sensed using electrodes or physiological sensors in communication with a medical device and collected during, or alternatively before or after, a detected physiological event. Figure 5By way of non-limiting example, the physiological data 512 includes an ECG or EGM sensed at a cardiac site, such as a ventricle. In some examples, two or more physiological signals may be displayed, including EGMs from multiple cardiac sites or via different sensing electrode configurations, cardiac mechanical signals, or hemodynamic signals sensed from one or more sensors. Measurement trends 514 may include intra-channel or inter-channel timing information, such as heart rate trends, heart rate variability trends, or atrioventricular interval trends. The displayed information may include a detection summary 520. By way of example, the detection summary 520 may include the types of physiological events detected by the AMD, as well as the measurements obtained by the AMD from the sensed physiological signals. In Figure 5 In the example shown, the displayed episode is detected as an AF episode with a ventricular rate of 170 bpm and a duration of 140 seconds.

[0089] The user interface portion 500 may include a display area for receiving user annotations 530 of the displayed episode, such as a determination of the type of event (e.g., a particular arrhythmia type), or a designation of an appropriate (e.g., a true positive) detection indicating that the user is consistent with the arrhythmia type detected by the device, or a designation of an inappropriate (e.g., a false positive) detection indicating that the user is inconsistent with the arrhythmia type detected by the device.

[0090] Return to reference Figure 4A In addition to automatically displaying information about representative event 422, information about other events in the same event group (such as event 423) can also be displayed in response to a user command. As shown, a user can use a pointing device (such as a mouse pointer 440 on the user interface shown) to select an event (e.g., event 423) in the clustered event group. In response to the user selection, information about the selected event 423 can be displayed in a manner similar to the automatic display of representative event 422, such as Figure 5 In response to the on-demand display of the event 423 , the user may be prompted to provide an on-demand ruling or annotation for the selected event 423 .

[0091] As mentioned above Figure 2As described, when adjudicating the representative event 422, the arbitrator circuit 226 can assign the same adjudication of the representative event to each physiological event in the event group. The preferential display and adjudication of physiological events based on clustering as described herein advantageously utilizes system resources more efficiently and improves the functionality of the computer system for managing physiological events. It can also reduce the workload of clinicians and improve the efficiency of clinicians' inspection and adjudication of physiological events. In some examples, the user can further identify a subset of physiological events in the event group, but not all. The identified subset includes physiological events having corresponding similarity metrics below a similarity threshold. The physiological events in the identified subset can be assigned the same event type as the representative event. For example, the user can identify a bounded region 425 in the feature space S that contains the representative event 422. The bounded region 425 can have user-defined boundaries. In the example Figure 4A In the example shown, a user can define a bounded area 425 with a radius of "r" centered on the representative event 422. The radius "r" can be adjusted by the user via a user interface. In the example, the user can select from a plurality of predefined areas of different sizes or shapes centered on the representative event 422. In the example, the user can select from a plurality of predetermined radii, such as one of a "large", "medium" or "small" radius with a corresponding predetermined value. Alternatively, the user can select from a plurality of predefined areas, each area representing a different density level of physiological events in a corresponding clustered event group. In the example, the predefined areas can include "dense clusters" (small areas with densely clustered events in feature space), "sparse clusters" (large areas with sparsely distributed events in feature space), or any intermediate density level (e.g., medium density clusters, medium sparse clusters).

[0092] Since the radius “r” represents a similarity threshold for the representative event 422, the choice of radius “r” may have an impact on adjudication performance, as measured by the workload reduction and adjudication error rate associated with assigning the same adjudication for the representative event to all other physiological events in the user-defined subgroup. Figure 6Examples of workload reduction curves 610 and adjudication error rate curves 620 at different radius values ​​corresponding to user-defined clustered event regions are shown. The workload reduction curve 610 shows the relationship between the workload reduction (for examining and adjudicating events) and the radius value. The adjudication error rate curve 620 shows the adjudication error rate at different radius values. When a small radius "r" is used, more physiological events are excluded from the bounded region 425 and are not assigned a default adjudication (the same adjudication as the representative event 422). Adjudication of physiological events outside such an area will increase the workload of the clinician (i.e., less workload reduction). On the other hand, since the events within the bounded region 425 defined by the small radius "r" are more similar to (or closer to) the representative event 422, the default adjudication (the same adjudication as the representative event 422) is more likely to be accurate, and a lower adjudication error rate can be expected. In contrast, a large radius "r" will result in a larger bounded region 425, and more physiological events will be assigned to the default adjudication (the same adjudication as the representative event 422). This may reduce workload, but may increase the adjudication error rate. As Figure 6 In the example shown, when the radius "r" increases from 20 to 30, the workload reduction increases from approximately 20% (data point 612) to 35% (data point 614), while the adjudication error rate increases from approximately 1% (data point 622) to 3% (data point 624).

[0093] In an example, a user may provide an expected workload reduction or level of tolerance associated with assigning the same ruling of representative event 422 to all events within bounded region 425, and controller circuit 220 may determine a radius "r" based on the expected workload reduction or level of tolerance. In another example, controller circuit 220 may determine a performance metric that is proportional to the workload reduction and inversely proportional to the ruling error rate, such that a high workload reduction will result in an increase in the performance metric, and a high ruling error will decrease the performance metric. Controller circuit 220 may determine an "optimal" radius corresponding to a performance metric that exceeds a performance threshold.

[0094] Figure 4BClustering of physiological events using user-specified cluster centers and clustering criteria is shown. As shown in Figure 400B, a user can specify a physiological event (e.g., event 452) as the center or representative event of a cluster event group that has not yet been established. In an example, a user can determine a designated representative event (e.g., event 452) before clustering the event. In order to establish a cluster event group, the clustering circuit 222 can use a corresponding feature set to calculate a similarity measure between each physiological event and the representative event 452, and establish a cluster event group by assigning corresponding similarity measures that meet the similarity criteria to these physiological events. In an example, the similarity measure includes the Euclidean distance in the feature S, and a cluster event group can be established to include those physiological events within a bounded area 455 centered on a representative event 452 with a radius "r". The radius "r" can be adjusted by the user via a user interface. In an example, a user can select one of a plurality of predetermined radii, such as one of a "large", "medium" or "small" radius with a corresponding predetermined value. Alternatively, the user can select from multiple predefined regions identified as “dense clusters” (small regions in feature space with densely clustered events), “sparse clusters” (large regions in feature space with sparsely distributed events), or any intermediate density level (e.g., medium-dense clusters, medium-sparse clusters).

[0095] Information about representative event 452 may be automatically displayed on user interface 230. Figure 5 As shown, a user decision representing event 452 may be received from a user. Figure 4A Similarly described, information about other events in the same event group, such as event 453, may be displayed in response to a user command. In response to the on-demand display of event 453, the user may be prompted to provide on-demand rulings or comments for the selected event 453.

[0096] When arbitrating the representative event 452, the arbiter circuit 226 may assign the same arbiter of the representative event to each physiological event within the bounded region 455. Figure 4A As discussed, defining the radius "r" of the bounded region 455 can impact the workload reduction and ruling error rate associated with assigning the ruling of the representative event 452 to all other physiological events in the user-defined subgroups. Figure 6As shown, a small radius "r" will result in less workload reduction and lower ruling errors. Conversely, a larger radius "r" will result in more workload reduction and higher ruling error rates. A user can provide an expected workload reduction or tolerance level associated with assigning the same ruling of representative event 452 to all events within bounded area 455, and controller circuit 220 can determine radius "r" based on the expected workload reduction or tolerance level.

[0097] In an example, the controller circuit 220 determines the value of the radius "r" for a given workload reduction (e.g., a 50% reduction in event data to be inspected) or a set time for inspection and arbitration (e.g., 15 minutes), and determines an estimated error rate based on the radius "r" value. When the actual error rate (within the set inspection and arbitration time) exceeds the threshold error rate, a notification or alarm can be generated and presented to the user via the user interface 230. In another example, the controller circuit 220 can determine the value of the radius "r" for a given fault tolerance rate (e.g., 20%), and determine the estimated workload reduction or the estimated inspection and arbitration time based on the radius "r" value. When the actual inspection and arbitration time (for a given error rate) exceeds the threshold inspection and arbitration time, a notification or alarm can be generated and presented to the user via the user interface 230.

[0098] In another example, the controller circuit 220 may determine a performance metric that is proportional to the amount of workload reduction and inversely proportional to the arbitration error rate, such that high workload reduction increases the performance metric and high arbitration errors decrease the performance metric. The controller circuit 220 may determine an "optimal" radius corresponding to a performance metric that exceeds a performance threshold.

[0099] Figure 7 is a flow chart illustrating an example of a method 700 for managing presentation and adjudication of physiological events detected by a medical device in a patient. Physiological events may include, for example, arrhythmia episodes detected and recorded by an IMD 102 or WMD 103. The method 700 may be implemented in and performed by an ambulatory medical device, such as an implantable or wearable device, or implemented and performed in a remote patient management system. In an example, the method 700 may be implemented in and performed by an IMD 102, WMD 103, or external system 105.

[0100] At 710, information about a physiological event detected from a patient can be received, such as from a memory circuit 210 storing episodes of patient physiological events detected by IMD 102 or WMD 103. An arrhythmic episode can include corresponding physiological data sensed from one or more physiological sensors during the detection of the arrhythmic event, or additional physiological data sensed before and / or after the detection of the arrhythmic event. Physiological data associated with an arrhythmic episode can include electrocardiographic signals, such as one or more ECG or EGM signals. In some examples, a physiological event can include a patient-triggered episode.

[0101] At 720, a corresponding feature set may be generated based on the received information for each physiological event, such as using feature extractor circuit 221. In examples where the received information includes physiological data recorded during an arrhythmia episode (e.g., ECG, EGM, or other sensor signals), the feature set may include one or more heart rate distribution features, arrhythmia duration features, morphology features, or time features extracted from the arrhythmia episode.

[0102] At 730, the physiological events can be clustered into different event groups based on the feature sets of the physiological events, such as using clustering circuit 222. As described above with reference to Figure 2 As described, the extracted feature set can form a feature space S, and each physiological event can be represented as a data point in the feature space S. Clustering can be based on an unsupervised learning algorithm, such as k-means clustering, k-center point or fuzzy C-means clustering algorithm. Then, the received physiological events can be clustered into one or more clustered event groups, each clustered event group including a corresponding set of physiological events.

[0103] At 740, from each of the clustered event groups, a corresponding representative event can be identified to represent all physiological events in the corresponding event group. Figure 4A As shown, a representative event can be identified as a physiological event in an event group that is closest to the centroid of the physiological events in the event group (e.g., the Euclidean distance in the feature space S). In some examples, as an alternative to clustering based on unsupervised learning, the received physiological events can be clustered at 730 according to user-specified cluster centers and a set of clustering rules. For example, a user can specify a physiological event as a cluster center. A similarity measure between the user-specified cluster center and each of the physiological events (e.g., the Euclidean distance in the feature space S) can be determined using a corresponding feature set. A clustered event group can be established by assigning corresponding similarity measures that meet similarity criteria to these physiological events (such as a corresponding distance to the user-specified cluster center being below a similarity threshold), as described above with reference to Figure 4BAt 740, the user-specified physiological event may be identified as a representative event. The similarity threshold may be defined or adjusted by the user (such as via the user interface 230). In an example, the user may define a bounded region in the feature space S around the user-specified physiological event. Physiological events having corresponding graphical representation feature sets that fall within the user-defined region belong to the same clustered event group. In an example, the user-defined region may be centered on the user-specified physiological event and have a user-defined radius "r", such as Figure 4B As shown. The radius "r" (which represents the similarity threshold of the representative event) can be defined or adjusted by the user. In the example, the user can select from a plurality of predefined areas of different sizes or shapes centered on the representative event 422, or from a plurality of predetermined radii (e.g., "large", "medium", and "small" radii) with corresponding predetermined values. Alternatively, the user can select from a plurality of predefined areas that are identified as "dense clusters" (small areas with densely clustered events in feature space), "sparse clusters" (large areas with sparsely distributed events in feature space), or any intermediate density level (e.g., medium-dense clusters, medium-sparse clusters).

[0104] The clustering results including representative events and indications that the representative events represent a set of physiological events in the clustered event group can be output to a user or process. For example, at 752, the physiological events in the clustered event group can be displayed in a priority order. For example, information about the representative event (e.g., ECG, EGM, or other recorded sensor data) can be automatically displayed on a user interface, while information about other physiological events in the same event group is hidden to avoid display until or unless the user requests it. In an example, the user can be notified about the event group (e.g., N events) represented by the representative event. The user can be prompted to select a hidden physiological event from the clustered event group for display. In response to the use selection, information about the selected event can be displayed.

[0105] At 754, a user decision on the displayed physiological event can be received from the user via the user interface. Figure 5As shown, the adjudication may include user specification of an event type for a physiological event. Based on the priority display of physiological events, adjudication of physiological events in the same group may also be prioritized. For example, a representative event that is automatically displayed may be adjudicated before other physiological events are displayed on demand in an event group (e.g., as selected by a user). In some examples, when adjudicating a representative event, the same adjudication of the representative event may be assigned to each of the physiological events in the event group. Therefore, unless otherwise modified (e.g., by a user), all physiological events in an event group will, by default, have the same event type as the adjudicated arrhythmia type for the representative event. The default adjudication may be confirmed, rejected, or modified by the user.

[0106] The clustering-based prioritization and adjudication discussed herein can reduce the workload of clinicians and improve the efficiency of physiological event review and adjudication. The amount of workload reduction can be directly related to the clustering criteria (such as a similarity threshold), or the size or shape of the user-defined region, or the user-defined radius "r" in the feature space, such as Figure 4A-4B On the other hand, assigning the same ruling to all physiological events in the same clustered event group can introduce ruling errors. Figure 6 As shown, a small radius "r" will result in less workload reduction and a lower adjudication error rate; conversely, a larger radius "r" will result in more workload reduction, but a higher adjudication error rate. The similarity threshold or radius "r" can be determined or adjusted to meet user-specified workload reduction and / or error tolerance requirements. In some examples, an "optimal" similarity threshold or radius "r" can be determined to optimize a performance metric that is proportional to the workload reduction and inversely proportional to the adjudication error rate.

[0107] Figure 8 Generally, a block diagram of an example machine 800 is shown on which any one or more of the techniques (eg, methods) discussed herein may be performed. Portions of this description may apply to the computing framework of various portions of an LCP device, an IMD, or an external programmer.

[0108] In an alternative embodiment, the machine 800 can operate as a standalone device, or can be connected (e.g., networked) to other machines. In a networked deployment, the machine 800 can operate in the capacity of a server machine, a client machine, or both in a server-client network environment. In an example, the machine 800 can act as a peer machine in a peer-to-peer (P2P) (or other distributed) network environment. The machine 800 can be a personal computer (PC), a tablet computer, a set-top box (STB), a personal digital assistant (PDA), a mobile phone, a network device, a network router, a switch or a bridge, or any machine capable of executing instructions (sequentially or otherwise) specifying the actions to be taken by the machine. In addition, although only a single machine is shown, the term "machine" should also be deemed to include any collection of the following machines, which independently or jointly execute one (or more) instruction sets to implement any one or more methods discussed herein, such as cloud computing, software as a service (SaaS), and other computer clustering structures.

[0109] As described herein, examples may include logic or multiple components or mechanisms, or may be operated by them. A circuit set is a collection of circuits implemented in a tangible entity, which includes hardware (e.g., simple circuits, gates, logic, etc.). Circuit set components can be flexible over time and potential hardware variability. A circuit set includes components that can perform specific operations individually or in combination when operating. In an example, the hardware of the circuit set can be designed to perform specific operations (e.g., hardwired) invariably. In an example, the hardware of the circuit set may include variably connected physical components (e.g., execution units, transistors, simple circuits, etc.), which include physically modified computer-readable media (e.g., magnetic, electrical, movable placement of invariant aggregated particles, etc.) to encode instructions for specific operations. When the physical components are connected, the basic electrical properties of the hardware components change, for example, from an insulator to a conductor, and vice versa. The instructions enable embedded hardware (e.g., an execution unit or a loading mechanism) to create components of the circuit set in hardware via variable connections to perform parts of specific operations when operating. Therefore, when the device is operating, the computer-readable medium is communicatively coupled to other components of the circuit set components. In an example, any physical component may be used in more than one component of more than one circuit set. For example, in operation, an execution unit may be used in a first circuit of a first circuit set at one point in time and reused by a second circuit in the first circuit set, or reused by a third circuit in the second circuit set at a different time.

[0110] The machine (e.g., computer system) 800 may include a hardware processor 802 (e.g., a central processing unit (CPU), a graphics processing unit (GPU), a hardware processor core, or any combination thereof), a main memory 804, and a static memory 806, some or all of which may communicate with each other via an interconnect (e.g., a bus) 808. The machine 800 may also include a display unit 810 (e.g., a raster display, a vector display, a holographic display, etc.), an alphanumeric input device 812 (e.g., a keyboard), and a user interface (UI) navigation device 814 (e.g., a mouse). In an example, the display unit 810, the input device 812, and the UI navigation device 814 may be a touch screen display. The machine 800 may additionally include a storage device (e.g., a drive unit) 816, a signal generating device 818 (e.g., a speaker), a network interface device 820, and one or more sensors 821, such as a global positioning system (GPS) sensor, a compass, an accelerometer, or other sensors. The machine 800 may include an output controller 828, such as a serial (e.g., universal serial bus (USB), parallel or other wired or wireless (e.g., infrared (IR), near field communication (NFC), etc.) connection to communicate with or control one or more peripheral devices (e.g., printer, card reader, etc.).

[0111] The storage device 816 may include a machine-readable medium 822 having stored thereon one or more data structure sets or instruction sets 824 (e.g., software) embodying or used by any one or more of the techniques or functionality described herein. The instructions 824 may also reside, completely or at least partially, within the main memory 804, within the static memory 806, or within the hardware processor 802 during execution thereof by the machine 800. In an example, one or any combination of the hardware processor 802, the main memory 804, the static memory 806, or the storage device 816 may constitute a machine-readable medium.

[0112] Although the machine-readable medium 822 is illustrated as a single medium, the term “machine-readable medium” may include a single medium or multiple media (eg, a centralized or distributed database and / or associated caches and servers) configured to store one or more instructions 824 .

[0113] The term "machine-readable medium" may include any medium capable of storing, encoding or carrying instructions executed by the machine 800 and causing the machine 800 to perform any one or more of the techniques of the present disclosure, or any medium capable of storing, encoding or carrying data structures used by or associated with these instructions. Non-limiting machine-readable medium examples may include solid-state memory and optical and magnetic media. In an example, the aggregated machine-readable medium includes a machine-readable medium having a plurality of particles with a constant (e.g., stationary) mass. Therefore, the aggregated computer-readable medium is not a transient propagation signal. Specific examples of aggregated machine-readable media may include: non-volatile memory, such as semiconductor memory devices (e.g., electrically programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM)) and flash memory devices; disks, such as internal hard disks and removable disks; magneto-optical disks; and CD-ROM and DVD-ROM disks.

[0114] The instructions 824 may also be sent or received over a communication network 826 using a transmission medium via the network interface device 820, which may utilize any of a number of transmission protocols (e.g., frame relay, Internet Protocol (IP), transmission control protocol (TCP), user datagram protocol (UDP), hypertext transfer protocol (HTTP), etc.). Example communication networks may include a local area network (LAN), a wide area network (WAN), a packet data network (e.g., the Internet), a mobile telephone network (e.g., a cellular network), a plain old telephone (POTS) network, and a wireless data network (e.g., a wireless network known as a wireless network). The Institute of Electrical and Electronics Engineers (IEEE) 802.11 family of standards, known as The IEEE 802.16 family of standards), the IEEE 802.15.4 family of standards, peer-to-peer (P2P) networks, and the like. In an example, the network interface device 820 may include one or more physical jacks (e.g., Ethernet, coaxial, or telephone jacks) or one or more antennas to connect to the communication network 826. In an example, the network interface device 820 may include multiple antennas to wirelessly communicate using at least one of single-input multiple-output (SIMO), multiple-input multiple-output (MIMO), or multiple-input single-output (MISO) technology. The term "transmission medium" should be understood to include any intangible medium that is capable of storing, encoding, or carrying instructions executed by the machine 800, and includes digital or analog communication signals or other intangible media to facilitate the communication of such software.

[0115] Various embodiments are shown in the above-mentioned figures. One or more features from one or more of these embodiments may be combined to form other embodiments.

[0116] The method examples described herein may be at least partially machine or computer implemented. Some examples may include a computer readable medium or machine readable medium encoded with instructions, which are operable to configure an electronic device or system to perform the method described in the above examples. The implementation of this method may include code, such as microcode, assembly language code, high-level language code, etc. Such code may include computer readable instructions for performing various methods. The code may form part of a computer program product. In addition, the code may be tangibly stored on one or more volatile or non-volatile computer readable media during execution or at other times.

[0117] The foregoing detailed description is intended to be illustrative rather than limiting.The scope of the disclosure should, therefore, be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled.

Claims

1. A system for managing a plurality of physiological events detected by a medical device in a patient, the system comprising: A controller circuit is configured to: receiving information about the plurality of physiological events; for each physiological event in the plurality of physiological events, generating a corresponding feature set using the received information, the feature set comprising a time or morphology feature with a corresponding value; clustering the plurality of physiological events into different event groups using the values ​​of the temporal or morphological features of the generated feature set, the different event groups each including a corresponding physiological event set; determining, from at least one of the different event groups, a representative event representing the set of physiological events in the at least one event group; as well as The representative event and an indication that the representative event has been determined and represents the set of physiological events in the at least one event group are output to a user or a process of the system.

2. The system of claim 1 , wherein the controller circuit is configured to: initiating automatic display of information about the determined representative event on a user interface; hiding information about the set of physiological events in the at least one event group from being displayed on the user interface; and In response to a user command via the user interface, an on-demand display of information regarding one or more physiological events in the set of physiological events in the at least one event group is initiated.

3. A system according to claim 2, wherein the user command comprises a user selection of a physiological event from the set of physiological events in the at least one event group, and wherein the controller circuit is configured to display information about the selected physiological event on the user interface in response to the user selection.

4. The system according to any one of claims 2-3, comprising a user interface configured to receive a ruling on the representative event from a user, The controller circuit is configured to assign the received ruling of the representative event to each physiological event in the set of physiological events in the at least one event group.

5. The system of any one of claims 1-4, wherein the controller circuit is configured to prioritize storage of information about the determined representative event over storage of information about the set of physiological events in the at least one event group in a storage device.

6. The system of any one of claims 1-5, wherein the controller circuit is configured to prioritize transmission of information about the determined representative events over transmission of information about the set of physiological events in the at least one event group between different devices.

7. The system of any one of claims 1-6, wherein the plurality of physiological events include an arrhythmia episode detected from the patient, and the generated corresponding feature set includes at least one of: Heart rate distribution characteristics; Duration of arrhythmia; Morphological characteristics; or The time of day at which the plurality of physiological events are detected.

8. The system according to any one of claims 1 to 7, wherein: In order to determine the representative event, the controller circuit is configured to: determining, in a feature space, a centroid of the set of physiological events in the at least one event group using a set of features correspondingly generated from at least a portion of the set of physiological events; as well as The representative event in the at least one event group is determined as the physiological event that is closest to the determined centroid.

9. The system according to any one of claims 1 to 8, wherein: In order to cluster the plurality of physiological events, the controller circuit is configured to: Initializing a cluster center using a feature set of a physiological event among the plurality of physiological events; Iteratively updating the cluster centers using the central tendency of feature sets correspondingly generated from physiological events in the event group until a convergence criterion or an iteration stopping criterion is met; as well as Based on the similarity measure between the physiological events and the iteratively updated cluster centers, the physiological events are assigned to cluster event groups.

10. The system of claim 9, wherein the controller circuit is configured to: calculating a respective similarity measure between the representative event and each physiological event in the set of physiological events in the at least one event group; selecting a subset of events from the set of physiological events in the at least one event group, the subset of events each having a corresponding similarity measure below a similarity threshold; as well as An indication that the representative events represent the selected subset of events is output to a user or a process of the system.

11. The system of any one of claims 1-10, wherein the controller circuit is configured to: calculating a corresponding similarity measure between each physiological event in the received plurality of physiological events and the user-specified physiological event using feature sets generated correspondingly from the received plurality of physiological events and the user-specified physiological event; determining a set of physiological events in the at least one event group whose corresponding similarity measures exceed a similarity threshold; as well as The physiological event specified by the user is determined as the representative event in the at least one event group.

12. The system of claim 11, comprising a user interface configured to: displaying the received plurality of physiological events in a graphical representation of feature space; receiving user input to identify a physiological event specified by the user; as well as Information about the user-specified physiological event is displayed along with an indication that the representative event represents the set of physiological events in the at least one event group.

13. The system of claim 12, wherein the user interface is configured to receive user input of the similarity threshold or user selection of a predetermined clustering density.

14. The system of any one of claims 11-13, wherein the controller circuit is configured to: generating an estimate of a workload reduction associated with assigning the user ruling of the representative event to each physiological event in the set of physiological events in the at least one event group; and The similarity threshold is determined or adjusted based on the generated estimate of the workload reduction.

15. The system of any one of claims 11-14, wherein the controller circuit is configured to: generating an error rate estimate associated with assigning the user ruling of the representative event to each physiological event in the set of physiological events in the at least one event group; and The similarity threshold is determined or adjusted based on the generated error rate estimate.

Images