Supervised Cardiac Event Detection

Abstract

Systems and methods for detecting physiological events in a patient are described herein. An embodiment of a medical system includes a memory circuit for storing physiological event episodes detected and recorded by a medical device. The system includes a control circuit for analyzing the stored physiological event episodes and determining the presence of a target cardiac event under a plurality of detection settings. Using the presence of a target cardiac event determined from the stored physiological event episodes and a user's ruling on the stored event episodes, the control circuit can select a detection setting from the plurality of detection settings to detect a subsequent target cardiac event. The control circuit can also prioritize the physiological event episodes for storage in the memory circuit.

Description

[0001] Related Applications

[0002] This application claims the benefit of priority under 35 U.S.C. §119(e) to U.S. Provisional Patent Application Serial No. 62 / 696,499, filed on July 11, 2018, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This document relates generally to medical devices and, more particularly, to systems, devices, and methods for detecting cardiac events, detected onset of cardiac events. Background Art

[0004] Implantable medical devices (IMDs) have been used to monitor patient health or disease states and deliver treatments. For example, implantable cardioverter defibrillators (ICDs) are used to monitor certain abnormal heart rhythms. Some IMDs can be used to monitor the progression of chronic diseases, such as deterioration of heart function due to congestive heart failure (CHF). In addition to diagnostic capabilities, IMDs can also provide treatments for treating or alleviating certain medical conditions, such as cardiac electrical stimulation therapy for treating arrhythmias or correcting cardiac asynchrony in CHF patients.

[0005] An IMD can record medical data associated with detected physiological events such as arrhythmias or heart failure (WHF). Some IMDs can register the onset of physiological events triggered by patients and record physiological data in response to patient triggering. An IMD can be interconnected with a patient management system via a data communication network. Device data such as medical data associated with detected physiological events can be sent to a patient management system, through which a healthcare professional can remotely follow up with a patient or regularly evaluate the function of an IMD. For example, a healthcare provider can review recorded medical data associated with the onset of a physiological event, determine the presence or possible causes of a physiological event, or evaluate whether a prescribed treatment has led to a desired therapeutic outcome. Summary of the invention

[0006] Ambulatory medical device (AMD) can detect cardiac events (e.g., arrhythmias) using programmable detection settings such as detection parameters and associated sensitivity levels. After detecting a cardiac event, AMD can record an episodic event. Patient management systems can be used to manage the onset of physiological events. For example, the patient management system can often receive alarm notifications about cardiac events, such as arrhythmias or heart failure (WHF) events detected by AMD. Users (e.g., clinicians) can review the onset of physiological events, make annotations, arrange follow-up visits for patients, or reprogram AMD and other operations.

[0007] Patient management system can manage physiological event attacks from multiple AMDs simultaneously. Manual review and annotation of physiological event data (such as arrhythmia attacks) detected by a large number of devices may require a large amount of clinical, technical and human resources, which may be expensive or time-consuming for medical institutions. Some alarm notifications are caused by repeated false positive detections of cardiac events performed by AMD. False positive detections may have the same or similar potential causes. FP detection may inappropriately trigger treatment (e.g., arrhythmia treatment delivered by AMD) or other medical interventions. In addition, FP detection may repeatedly trigger alarm notifications to require medical care or attack review and annotation. In order to prevent or reduce repeated FP detections, especially those with the same or similar potential causes, it is necessary to correctly and timely adjust the cardiac event detection settings in AMD. The inventors have recognized the unmet needs for physiological event detection and medical alarm management, particularly the needs for improved systems and methods for automatically learning from previous FP detections of patients, adjusting detection settings and improving AMD functions.

[0008] The document discusses, among other things, systems, devices, and methods for detecting physiological events in a patient. An embodiment of a medical system includes a memory circuit for storing physiological event episodes such as those recorded by an ambulatory medical device. The medical system includes a control circuit for performing simulations on the stored physiological event episodes to determine the presence of a target cardiac event under different detection settings. The control circuit may provide a user (e.g., a clinician) with the determined presence of a target cardiac event under a first detection setting, and receive a ruling from the user on the determination of the presence of the target cardiac event under the provided first detection setting. The control circuit may redetermine the presence of the target cardiac event in the stored physiological event episodes under a second detection setting different from the first detection setting, and provide the user with the presence of the target cardiac event redetermined under the second detection setting. The control circuit may compare the determination of the presence of the target cardiac event under the first detection setting and the second detection setting, and present the comparison to the user, such as on a display unit. Based on the comparison, the user may select between the first detection setting and the second detection setting. The control circuit may receive the user selection to detect a subsequent target cardiac event. The control circuit may prioritize the physiological event episodes for storage in the memory circuit.

[0009] Example 1 is a system for detecting cardiac events from a patient. The system includes a memory circuit and a control circuit. The memory circuit is configured to store physiological event episodes from a patient recorded by a medical device. The control circuit includes a detection control circuit, which is configured to: determine the presence of a target cardiac event in one or more of the stored physiological event episodes under a first detection setting; provide the presence of the target cardiac event determined under the first detection setting to a user; receive a ruling from the user on the presence of the provided target cardiac event determined under the first detection setting; redetermine the presence of the target cardiac event in one or more of the stored physiological event episodes under a second detection setting different from the first detection setting; provide the user with the presence of the target cardiac event redetermined in the one or more stored physiological event episodes under the second detection setting; and receive a selected detection setting in response to the provided presence of the redetermined target cardiac event to subsequently determine the presence of the target cardiac event in the patient.

[0010] In Example 2, the subject matter of Example 1 optionally includes a detection control circuit, which can be configured to determine a first false positive (FP) detection count corresponding to the first detection setting and a second FP detection count corresponding to the second detection setting, and provide the determined first FP detection count and second FP detection count to the user.

[0011] In Example 3, the subject matter of any one or more of Examples 1-2 optionally includes a detection control circuit that can be configured to determine a receiver operating characteristic (ROC) having an operating point including the first detection setting and the second detection setting, and provide the determined ROC to the user.

[0012] In Example 4, the subject matter of any one or more of Examples 1-3 may optionally include a first detection setting and a second detection setting, which may include respective first sensitivity levels and second sensitivity levels. To determine the presence of a target cardiac event in one of the stored physiological event episodes, the detection control circuit may be configured to compare a physiological parameter derived from one of the stored physiological event episodes to the first sensitivity level and the second sensitivity level.

[0013] In Example 5, the subject matter of Example 4 optionally includes a first sensitivity level and a second sensitivity level, each representing a threshold value or a value range of the physiological parameter.

[0014] In Example 6, the subject matter of any one or more of Examples 4-5 can optionally include a target cardiac event that can include an atrial tachyarrhythmia, and the multiple sensitivity levels can include thresholds or value ranges for at least one of: heart rate; heart rate stability; electrogram morphology measurements; or cardiac contractility measurements.

[0015] In Example 7, the subject matter of any one or more of Examples 4-6 optionally includes a detection control circuit that can be configured to determine, for each of the stored physiological event episodes, a lowest sensitivity level (Sens LST ), and further use the stored physiological event onset Sens LST to select detection settings.

[0016] In Example 8, the subject matter of Example 7 may optionally include a control circuit, the control circuit may further include a storage control circuit, the storage control circuit being configured to store the stored physiological event occurrence sensor. LST To prioritize the stored physiological event episodes.

[0017] In Example 9, the subject matter of Example 8 may optionally include a storage control circuit, the storage control circuit may be configured to: if the Sens LST Below the sensitivity level threshold, the event is assigned a higher priority, and if the Sens LST Exceeding the sensitivity level threshold, the event occurrence is assigned a lower priority.

[0018] In Example 10, the subject matter of Example 9 optionally includes a storage control circuit that can be configured to: store a first number of data features of the event occurrence if a high priority is assigned; and store a second, lower number of data features of the event occurrence if a low priority is assigned.

[0019] In Example 11, the subject matter of any one or more of Examples 1-10 may optionally include a first detection setting and a second detection setting, which may include respective first duration thresholds and second duration thresholds. To determine the presence of the target cardiac event in one of the stored physiological event episodes, the detection control circuit may be configured to compare the duration of one of the stored physiological event episodes to the first duration threshold and the second duration threshold.

[0020] In Example 12, the subject matter of any one or more of Examples 1-11 optionally includes a user interface configured to receive user input of a determination of a stored physiological event onset, and the control circuitry may be configured to program selected detection settings for subsequent determination of the presence of a target cardiac event in a patient.

[0021] In Example 13, the subject matter of Example 12 may optionally include a user interface which may be configured to display an indication of the presence of the target cardiac event in the stored physiological event episodes under the first detection setting and the second detection setting.

[0022] In Example 14, the subject matter of any one or more of Examples 1-13 may optionally include an ambulatory medical device (AMD) configured to detect a target cardiac event from subsequent patient physiological event episodes using the received selection of detection settings.

[0023] In Example 15, the subject matter of any of claims 1-14 optionally includes a control circuit that can be configured to automatically select between a first detection setting and a second detection setting to detect a subsequent target cardiac event, and the selection can be based on the presence of the target cardiac event determined in each of the stored physiological event episodes under the first detection setting and the second detection setting.

[0024] Example 16 is a method for detecting a cardiac event. The method includes the steps of determining the presence of a target cardiac event in one or more stored physiological event episodes stored in a memory at a first detection setting using a control circuit; providing the presence of the target cardiac event determined at the first detection setting to a user; receiving the provided determination of the target presence; using the control circuit, re-determining the presence of the target cardiac event in one or more of the stored physiological event episodes at a second detection setting different from the first detection setting; providing the user with the re-determined presence of the target cardiac event in the one or more stored physiological event episodes at the second detection setting; and in response to the provided re-determined presence of the target cardiac event, receiving a selected detection setting for subsequent determination of the presence of the target cardiac event in a patient.

[0025] In Example 17, the subject matter of Example 16 optionally includes determining a first false positive (FP) detection count corresponding to the first detection setting and a second FP detection count corresponding to the second detection setting, and providing the determined first FP detection count and second FP detection count to a user.

[0026] In Example 18, the subject matter of any one or more of Examples 16-17 optionally includes determining a receiver operating characteristic (ROC) having an operating point including the first detection setting and the second detection setting, and providing the determined ROC to a user.

[0027] In Example 19, the subject matter of any one or more of Examples 16-18 optionally includes a first detection setting and a second detection setting, which may include respective first sensitivity levels and second sensitivity levels. Determining the presence of the target cardiac event in the stored physiological event episodes includes using a comparison of a physiological parameter derived from the stored physiological event episodes with the first sensitivity level and the second sensitivity level.

[0028] In Example 20, the subject matter of Example 19 optionally includes, for each of the stored physiological event episodes, determining a lowest sensitivity level (Sens LST ); and using the stored physiological event occurrence Sens LST A detection setting is selected from the plurality of sensitivity levels.

[0029] In Example 21, the subject matter of Example 20 may optionally include: using the storage control circuit to detect the occurrence of a stored physiological event based on the stored physiological event. LST The stored physiological event episodes are prioritized.

[0030] In Example 22, the subject matter of any one or more of Examples 16-21 optionally includes a first detection setting and a second detection setting, which may include corresponding first duration thresholds and second duration thresholds, and determining the presence of a target cardiac event in a stored physiological event episode includes: using a comparison of the duration of the stored physiological event episode with the first duration threshold and the second duration threshold.

[0031] In Example 23, the subject matter of any one or more of Examples 16-22 may optionally include detecting the target cardiac event from subsequent episodes of patient physiological events using the ambulatory medical device under the selected detection setting.

[0032] Example 24 is a method for detecting a cardiac event. The method includes the steps of: displaying on a user interface one or more first cardiac events detected in a physiological episode using a detection algorithm having a first detection setting; receiving, via the user interface, a verdict from a user on the accuracy of the one or more first cardiac events detected in the physiological episode using the first detection setting; displaying on the user interface one or more second cardiac events detected in the same physiological episode using a detection algorithm having a second detection setting different from the first detection setting; and updating the detection algorithm to detect cardiac events in subsequent physiological episodes using the second detection setting.

[0033] The systems, devices and methods discussed in this document can improve the performance of medical systems in detecting target cardiac events (such as arrhythmia events, worsening heart failure events and others). As discussed above, the challenge in cardiac event detection is repeated FP detection. This document provides a solution for selecting or adjusting detection settings using supervised learning from previous physiological event episodes of patients (such as those recorded by AMD). Supervised learning involves the user's ruling on the event episodes generated by the device. The detection settings corresponding to the expected performance of correctly detecting target cardiac events from previous physiological event episodes of patients are selected. Because the detection performance is based on a comparison with the user's ruling on the onset of physiological events, the selected detection settings can help AMD better identify subsequent target cardiac events based on the knowledge learned from previous physiological event episodes. Compared with conventional cardiac event detection techniques, the detection settings based on supervised learning discussed in this article can reduce FP detection while retaining the ability to identify TP events, with almost no additional cost or system complexity. With a lower FP rate, inappropriate treatment or medical intervention for patients can be avoided or reduced, and the time and burden of clinicians for onset assessment and ruling can be reduced. Therefore, the topics discussed in this article can better align healthcare resources to serve those patients with serious medical conditions.

[0034] The physiological event detection and prioritization discussed in this document can also improve the function of AMD and / or patient management system. The stored physiological event onset can be prioritized to be stored in a memory. Event prioritization can be performed in a communicator, a mobile monitor, a programmer or a remote patient management system that communicates with AMD. Like this, in some cases, improved alarm management can be achieved without modifying existing patient AMD or physiological event detectors. Because only physiological events with higher priority and / or more clinically relevant to medical diagnosis are stored in the system for clinician review or adjudication compared to traditional medical systems, more efficient memory use can be achieved. Utilizing reduced alarms and events for adjudication, the complexity and operating costs of the patient management system can be reduced. In addition, with reduced FP detection, less unnecessary device treatments, drugs and procedures can be arranged, prescribed or provided, thereby the life and battery life of AMD can be extended, and overall system cost savings can be achieved.

[0035] This summary is an overview of some teachings of the application and is not intended to be an exclusive or exhaustive treatment of this theme. Further details about this theme are 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 forming a part thereof (each of which will not be considered in a limiting sense). The scope of the present disclosure is limited by the appended claims and their legal equivalents. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Various embodiments are shown by way of example in the figures of the accompanying drawings. Such embodiments are illustrative and are not intended to be exhaustive or exclusive embodiments of the subject matter.

[0037] Figure 1 An example of a patient management system and portions of an environment in which the system may operate is generally shown.

[0038] Figure 2 Generally illustrated are examples of a physiological event detection and management system configured to adjust or select detection settings for detecting a target cardiac event in a patient.

[0039] Figure 3 An example of an arrhythmia management system configured to detect arrhythmias in a patient and manage detected arrhythmia episodes is generally shown.

[0040] Figure 4 Examples of user interfaces for displaying physiological event onsets, receiving user decisions on physiological event onsets, and interactive programming of detection settings are shown.

[0041] Figure 5 is a diagram illustrating an example of selecting or adjusting arrhythmia detection settings based on analysis of device-detected arrhythmia episodes stored in memory.

[0042] Figure 6 is a flow chart illustrating an example of a method of selecting or adjusting arrhythmia detection settings to detect a target cardiac event.

[0043] Figure 7 is a flow chart illustrating an example of a portion of a method for detecting target cardiac events from physiological event episodes and prioritizing the physiological event episodes for storage in a memory.

[0044] Figure 8 is a block diagram generally illustrating an example machine upon which any one or more of the techniques (eg, methodologies) discussed herein may be performed. DETAILED DESCRIPTION

[0045] Disclosed herein are systems, devices, and methods for detecting physiological events in a patient. Embodiments of a medical system include a memory circuit for storing machine-generated physiological event episodes, such as arrhythmia episodes recorded by an ambulatory medical device. The system can determine the presence of a target cardiac event in one or more of the stored event episodes under a first detection setting, provide the determined presence of the target cardiac event under the first detection setting to a user, and receive a ruling from the user regarding the presence of the determined target cardiac event. The control circuit can redetermine (e.g., simulate) the presence of the target cardiac event in the stored physiological event episodes in the same one or more stored event episodes (or one or more different stored event episodes) of the stored event episodes that have been previously analyzed and determined under a different second detection setting, and provide the user with the presence of the redetermined target cardiac event in one or more stored physiological event episodes under the second detection setting. The user can select a detection setting in response to the provided presence of the redetermined target cardiac event in one or more stored physiological event episodes. The system can receive the selected detection setting and use the selected detection setting to perform a subsequent determination of the presence of the target cardiac event. In an example, a determination of the presence of a target cardiac event at a first detection setting and a second detection setting, or a comparison between an adjudication and a redetermination, can be provided to the user. A selected detection setting for a subsequent determination of the presence of a target cardiac event can be received, such as from the user, and the system can program the selected detection setting for use in the subsequent determination.

[0046] Figure 1An example of a patient management system 100 and portions of an environment in which the system 100 may operate is generally 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 near the patient, such as at the patient's home or office, through a central server, such as at a hospital, clinic, or physician's office, or through a remote workstation, such as a secure wireless mobile computing device.

[0047] The patient management system 100 may include a mobile system 105 associated with the patient 102 , an external system 125 , and a telemetry link 115 that provides communication between the mobile system 105 and the external system 125 .

[0048] The mobile system 105 may include an ambulatory medical device (AMD) 110. In an example, the AMD 110 may be an implantable device that is implanted subcutaneously in the chest, abdomen, or other part of the patient 102. Examples of implantable devices may include, but are not limited to, pacemakers, pacemaker / defibrillators, cardiac resynchronization therapy (CRT) devices, cardiac remodeling control therapy (RCT) devices, neuromodulators, drug delivery devices, biotherapeutic devices, diagnostic devices such as cardiac monitors or loop recorders, or patient monitors, and others. The AMD 100 may alternatively or additionally include: a subcutaneous medical device, such as a subcutaneous monitor or diagnostic device; an externally monitored or treated medical device, such as an automated external defibrillator (AED) or a Holter monitor; or a wearable medical device, such as a patch-based device, a smart watch, or a smart accessory.

[0049] By way of example, AMD 110 can be coupled to a lead system 108. Lead system 108 can include one or more intravenous, subcutaneous, or non-invasively placed leads or catheters. Each lead or catheter can include one or more electrodes. The placement and use of lead system 108 and associated electrodes can be determined using the patient's needs and the capabilities of AMD 110. The associated electrodes on lead system 108 can be positioned at the patient's chest or abdomen to sense physiological signals indicative of cardiac activity, or physiological responses to diagnostic or therapeutic stimulation of target tissue. By way of example and not limitation, and as described above, the present invention provides a method for providing a plurality of lead systems 108 and associated electrodes. Figure 11 , the lead system 108 may be surgically inserted or positioned on the surface of the heart 101. The electrodes on the lead system 108 may be positioned on a portion of the heart 101 such as the right atrium (RA), the right ventricle (RV), the left atrium (LA), or the left ventricle (LV), or any tissue between or near the heart portions. In some examples, the lead system 108 and associated electrodes may alternatively be positioned on other parts of the body to sense physiological signals containing information about the patient's heart rate or pulse rate. In an example, the flow-type system 105 may include one or more leadless sensors that are not tied to the AMD 110 via the lead system 108. The leadless flow-type sensor may be configured to sense physiological signals and communicate wirelessly with the AMD 110.

[0050] AMD 110 can be configured as a monitoring and diagnostic device. AMD 110 can include a hermetically sealed canister that contains one or more of a sensing circuit, a control circuit, a communication circuit, a battery, and other components. The sensing circuit can sense physiological signals such as using a physiological sensor or an electrode associated with a lead system 108. Examples of physiological signals can include one or more of the following: electrocardiogram, intracardiac electrogram, arrhythmia, heart rate, heart rate variability, intrathoracic impedance, intracardiac impedance, arterial pressure, pulmonary artery pressure, left atrial pressure, right ventricular (RV) pressure, left ventricular (LV) coronary pressure, coronary artery blood temperature, blood oxygen saturation, one or more heart sounds, intracardiac acceleration, physical activity or exertion level, physiological response to activity, posture, respiratory rate, tidal volume, breath sounds, weight, or body temperature.

[0051] AMD 110 may include a detector circuit 160 for detecting physiological events using sensed physiological signals. In an example, physiological events include arrhythmias such as atrial fibrillation, atrial flutter, atrial tachycardia, supraventricular tachycardia, ventricular tachycardia or ventricular fibrillation, and other slow or fast arrhythmias. In an example, the detector circuit 160 is configured to detect syncope, presyncope events, or sudden events that may cause full syncope. In some examples, the detector circuit 160 is configured to detect deterioration of chronic medical conditions, such as worsening heart failure (WHF). The detector circuit 160 can monitor one or more physiological signals continuously or periodically and automatically detect physiological events. Additionally or alternatively, the detector circuit 160 can be configured to operate in a patient-triggered mode, register patient-triggered episodes, and record physiological data in response to a user-activated trigger. The trigger can be activated by the patient when the patient exhibits certain signs or symptoms or experiences a precursor event indicating a physiological event.

[0052] AMD 110 can be configured as a therapeutic device alternatively, which is configured to process arrhythmias or other heart diseases. AMD 110 may additionally include a therapeutic unit that can generate and deliver one or more treatments. Treatment can be delivered to patient 102 via lead system 108 and associated electrodes. Treatment may include electrotherapy, magnetic therapy or other types of treatment. The treatment may include antiarrhythmic therapy to treat arrhythmias or process or control one or more complications caused by arrhythmias, such as syncope, congestive heart failure or stroke and other. Examples of antiarrhythmic treatments may include pacing, cardioversion, defibrillation, neuromodulation, drug therapy, biological therapy and other types of treatment. In an example, treatment may include cardiac resynchronization therapy (CRT) for correcting asynchrony and improving cardiac function in CHF patients. In some examples, AMD 110 may include a drug delivery system, such as a drug infusion pump, for delivering drugs to patients to manage arrhythmias or complications caused by arrhythmias.

[0053] The external system 125 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 125 may manage the patient 102 through the AMD 110 connected to the external system 125 via the communication link 115. This may include, for example, programming the AMD 110 to perform one or more of the following: acquiring physiological data, performing at least one self-diagnostic test (such as for device operating status), analyzing physiological data to detect arrhythmias, or optionally delivering therapy to the patient 102 or adjusting therapy to the patient 102. In addition, the external system 125 may receive device data from the AMD 110 via the communication link 115. Examples of device data received by the external system 125 may include: real-time physiological data or stored physiological data from the patient 102, diagnostic data (such as detection of an event of arrhythmia or worsening of heart failure), response to therapy delivered to the patient 102, or device operability status of the AMD 110 (e.g., battery status and lead impedance). Telemetry link 115 may be an inductive telemetry link, a capacitive telemetry link, or a radio frequency (RF) telemetry link, or wireless telemetry (e.g., based on “strong” Bluetooth or IEEE 802.11 Wireless Fidelity “WiFi” interface standards). Other configurations and combinations of patient data source interfaces are possible.

[0054] By way of example and not limitation, external system 125 may include external device 120 near AMD 110 and remote device 124 at a location relatively remote from AMD 110 that communicates with external device 120 via telecommunication network 122. Examples of external device 120 may include a programmer device.

[0055] Remote device 124 can be configured to evaluate the patient data collected and provide alarm notification, and other possible functions. In an example, remote device 124 can include a central server that acts as a central hub for the patient data storage and analysis collected. The server can be configured as a single, multiple or distributed computing and processing system. Remote device 124 can receive patient data from multiple patients including, for example, patient 102. Patient data (e.g., physiological event attack) can be collected by AMD 110 and other data acquisition sensors or devices associated with patient 102. Remote device 124 can include a storage unit for storing patient data in a patient database. The storage unit can additionally store multiple detection settings, such as detection parameters and associated detection criteria (e.g., sensitivity level or detection threshold) or detection algorithms, which are used to detect the presence of target cardiac events (e.g., arrhythmias of a particular type) from stored patient data (e.g., event attacks detected and recorded by AMD 110). The server may analyze device-generated event episodes to determine the presence of a target cardiac event (eg, a type of arrhythmia) under a plurality of detection settings, and select a detection setting from the plurality of detection settings to detect a subsequent target cardiac event.

[0056] In an example, the presence of a target cardiac event may be determined in one or more physiological event episodes at a first detection setting, such as by a remote device 124. The determined presence of the target cardiac event in one or more physiological event episodes may be provided to a user, such as a clinician, for example, using a display. The user may adjudicate the provided determination, such as using a user interface. In response to the adjudication, the presence of the target cardiac event may be re-determined in the same (or in other examples, different) one or more physiological event episodes at a second detection setting that is different from the first detection setting. The re-determined presence of the target cardiac event may be provided to the user, and a selected detection setting (e.g., one of the first detection setting or the second detection setting, one or more other detection settings, etc.) may be received from the user, such as by a user interface. One or more subsequent determinations may be made using the selected detection setting.

[0057] In some examples, a supervised learning approach can be used to select detection settings that involve comparing the detected presence of a target cardiac event with a user's ruling on a device-generated event onset. Detection settings can be selected based on the comparison. Remote device 124 can send the selected detection settings to AMD 110, such as via communication link 115. Device settings selected based on supervised learning from a patient's previous physiological event onsets can allow AMD 110 to better detect subsequent target cardiac events. For example, those cardiac events that have similar characteristics to previously ruled FP episodes are less likely to be detected; therefore, inappropriate treatment or medical intervention can be avoided. Improved event detection can also reduce the number of episodes to be reviewed and ruled by the user.

[0058] By way of example, the alarm notification may include a web page update, a telephone or pager call, an E-mail, an SMS, a text message, or an "instant" message, as well as a message to the patient and a simultaneous direct notification to emergency services and clinicians. Other alarm notifications are possible. In some examples, the server may include a physiological event prioritization circuit configured to prioritize the alarm notifications. For example, a similarity metric between physiological data associated with the detected physiological event and physiological data associated with historical alarms may be used to prioritize alarms for detected physiological events.

[0059] The remote device 124 may additionally include one or more locally configured clients or remote clients securely connected to the server via the network 122. Examples of clients may include personal desktop computers, notebook computers, mobile devices, or other computing devices. Users (such as clinicians or other qualified medical professionals) may 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. The remote device 124, including the server and interconnected clients, may execute a follow-up plan by sending a follow-up request to AMD110, or by sending a message or other communication as a compliance notification to the patient 102, clinician, or authorized third party.

[0060] The network 122 can provide wired or wireless interconnection. In an example, the network 122 can be based on the Transmission Control Protocol / Internet Protocol (TCP / IP) network communication specification, although other types or combinations of network implementations are possible. Similarly, other network topologies and deployments are possible.

[0061] One or more of the external device 120 or the remote device 124 may output the detected physiological event to a user such as a patient or clinician, or a process including an instance of a computer program that can be executed in a microprocessor, for example. In an example, the process may include automatically generating a recommendation for treatment or a recommendation for further diagnostic testing or treatment. In an example, the external device 120 or the remote device 124 may include a display unit for displaying a physiological signal or a functional signal, or an alarm, a warning, an emergency call, or other form of warning for issuing a signal that an arrhythmia has been detected. In some examples, the external system 125 may include an external data processor that is configured to analyze the physiological signal or the functional signal received by the AMD 110 and confirm or deny the detection of a physiological event. Computationally intensive algorithms, such as machine learning algorithms, may be implemented in the external data processor to retrospectively process data to detect arrhythmias.

[0062] Parts of AMD 110 or external system 125 can be implemented using hardware, software, firmware or a combination thereof. Parts of AMD 110 or external system 125 can be implemented using a dedicated circuit that can be constructed or configured to perform one or more specific functions, or can be implemented using a general-purpose circuit that can be programmed or otherwise configured to perform one or more specific 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, among other aspects, a "comparator" may also include an electronic circuit comparator that can be constructed to perform a specific comparison function between two signals, or the comparator may be implemented as a part of a general-purpose circuit that can be driven by a code that instructs a part of a general-purpose circuit to perform a comparison between two signals.

[0063] Figure 2 An example of a physiological event detection and management system 200 is generally shown, which is configured to determine or adjust detection settings for detecting target cardiac events. Such detection settings can be programmed into a medical device (such as AMD 110) to detect subsequent target cardiac events from a patient. The system 200 can prioritize physiological event episodes detected from a patient and store the episodes in a memory according to the episode priority. At least a portion of the system 200 can be implemented in an external system 125 such as one or more of an external device 120 or a remote device 124, or distributed between the AMD 110 and the external system 125.

[0064] The system 200 may include one or more of a memory circuit 210, a control 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 125, such as within the external device 120 or the remote device 124. 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 AMD 110, in an episode library 212. In an example, the memory circuit 210 may be communicatively coupled to the AMD 110 and receive episodes of physiological events from the AMD 110, such as via the communication link 115, which will be referenced Figure 3 Have a discussion.

[0065] In an example, the physiological event episodes in the episode library 212 may include arrhythmia episodes such as those detected and recorded by AMD 110. Examples of arrhythmia episodes may include atrial arrhythmia episodes, supraventricular arrhythmia episodes, or ventricular arrhythmia episodes, among others. 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 detected arrhythmia event. The physiological data associated with the arrhythmia episode may include cardiac electrical signals, such as one or more electrogram (EGM) signals (such as one or more atrial EGMs or one or more ventricular EGMs) sensed at various cardiac sites using different electrode combinations. Additionally or alternatively, the physiological data may include: cardiac mechanical signals or hemodynamic signals, such as cardiac pressure signals, impedance signals, heart sound signals, and others. In various examples, each arrhythmia episode may also additionally include an arrhythmia detection or classification generated by a medical device (such as AMD 110). Arrhythmia detection or classification is the designation of a particular arrhythmia type, such as atrial fibrillation, atrial flutter, ventricular tachycardia, or ventricular fibrillation, among others. Other information about arrhythmia episodes, such as measurements or signal metrics obtained from physiological data (e.g., atrial rate, ventricular rate, variability of atrial or ventricular rate), can also be associated with the corresponding episode and stored in the episode library.

[0066] In some examples, the episode library 212 may 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 symptom severity, timing information of the symptom, such as the start and end time of the patient-triggered episode) may also be associated with the patient-triggered episode and included in the episode library 212.

[0067] Although the discussion of physiological event management in this document focuses on arrhythmia episodes, this is meant to be illustrative and not restrictive or limiting in any way in nature. The onset of other types of physiological events (such as syncope, worsening heart failure events, or heart failure decompensation events) can also be stored, analyzed, and provided to a clinician for adjudication using the systems, devices, and methods discussed in this document.

[0068] The control circuit 220 may be implemented as part of a microprocessor circuit, which may be a special-purpose processor, such as a digital signal processor, an application-specific integrated circuit (ASIC), a microprocessor, or other types of processors for processing information including physical activity information. Alternatively, the microprocessor circuit may be a general-purpose processor that may receive and implement an instruction set that performs the functions, methods, or techniques described herein.

[0069] The control circuit 220 may include a circuit group including one or more other circuits or subcircuits, including an onset analyzer circuit 221, an onset arbiter circuit 222, a detection control circuit 225, and a storage control 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 group may be designed to perform a specific operation (e.g., hardwired) in a fixed manner. In an example, the hardware of the circuit group may include variably connected physical components (e.g., execution units, transistors, simple circuits, etc.), which include a computer-readable medium that is physically modified (e.g., magnetically, electrically, removably placed, etc., of fixed aggregate particles) to encode instructions for a specific operation. When the physical components are connected, the underlying electrical properties of the hardware composition change, such as 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 a member of the circuit group in hardware via a variable connection to perform a portion of a specific operation when in operation. Therefore, when the device operates, the computer-readable medium is communicatively coupled to other components of the circuit group member. In an example, any one of the physical components may be used in more than one member of more than one circuit group. For example, in operation, an execution unit may be used in a first circuit of a first circuit group at one point in time and reused by a second circuit of the first circuit group, or reused by a third circuit of a second circuit group at a different time.

[0070] The episode arbiter circuit 222 can receive user input regarding an arbitrating of a physiological event episode, such as retrieved from the episode library 212. Physiological data collected during the physiological event episode, and optionally the detection results generated by the AMD, can be displayed 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 125. The user can provide an arbitrating through the user interface 230. The arbitrating can include a user specification of a cardiac event type in the physiological event episode. In an example, the arbitrating includes a user specification of the following arrhythmia types, such as atrial fibrillation, atrial flutter, supraventricular tachycardia, ventricular tachycardia, or ventricular fibrillation. The episode arbiter circuit 222 can compare the user specification of the arrhythmia type with the detection results generated by the AMD, and if the user specification is consistent with the detection results generated by the AMD, the episode is identified as a true positive (TP) (or appropriate) detection, or if the user specification is different from the detection results generated by the AMD, the episode 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 uncertain. In addition, the user can provide annotations regarding diagnostic information or episode characterizations of the physiological event episode. For example, when an AF episode detected by the device is adjudicated, the user (e.g., a clinician) can specify one of a plurality of episode characterizations as the reason for his or her adjudication decision.

[0071] The bout analyzer circuit 221 may include a detection analog circuit 223 configured to analyze a physiological event bout, such as N bouts {X1, X2, . . . , X N The detection analog circuit 223 can use the detection algorithm to detect the N episodes {X1, X2, ..., X N Each of the candidate detection settings {S1,S2,…,S M}, where M represents the number of candidate detection settings. The detection algorithm used by the detection simulation circuit 223 can be the same as or similar to the detection algorithm used by the AMD to detect the target cardiac event (such as an arrhythmia detector based on the timing or morphology of one or more cardiac signals). The candidate detection settings {S1, S2, ..., S M} can be represented by multiple sensitivity levels associated with a particular physiological parameter. Each sensitivity level can correspond to a detection threshold or value range of the physiological parameter. k , if the physiological parameters satisfy the detection setting S i If the condition exceeds the corresponding threshold, the detection analog circuit 223 determines that the detection setting S i In outbreak X kIf the physiological parameters fail to meet the requirements of different detection settings S j If the condition is lower than the corresponding threshold, the detection simulation circuit 223 determines that the detection setting S j In outbreak X k There is no target cardiac event (e.g., an atrial fibrillation event). A lower sensitivity level may correspond to a higher detection threshold and thus be less sensitive to the target cardiac event. In other words, the target cardiac event is less likely to be detected using a lower sensitivity level than a higher sensitivity level.

[0072] Physiological parameters used to determine the presence of a target cardiac event may include physiological signal features or a combination of multiple signal features extracted from a physiological signal or otherwise measured. In the example of arrhythmia detection, physiological parameters may include: temporal features representing the timing of atrial or ventricular events, or the relative timing between atrial and ventricular events, such as heart rate, heart rate variability, or atrioventricular conduction delay, among others. Physiological parameters may alternatively be morphological features representing the depolarization pattern of an atrial or ventricular electrogram. Physiological parameters may also include signal features representing the force of cardiac contractility, which may be extracted from cardiac pressure, impedance, or heart sound signals.

[0073] Usually, if the first detection setting S i Next, from a specific stored episode (e.g. X k ) detects a target cardiac event, then the second, more sensitive detection setting S j A more sensitive detection setting may be represented by a higher sensitivity level or a lower detection threshold. In some examples, the detection analog circuit 223 may determine the target cardiac event that is capable of detecting the onset X. k The minimum sensitivity level for target cardiac events in LST ) corresponding detection settings. Figure 5 Discussion shows Sens for multiple episodes LST .

[0074] The detection performance analyzer 224 can detect the event occurrences {X1, X2, . . . , X N} is compared with the user's decision of the stored event onset provided by the onset decider circuit 222 and is selected in the candidate detection settings {S1, S2, ..., S M} to identify the target cardiac event from the stored event episodes. In an example, the detection performance can be determined by comparing the candidate detection settings {S1, S2, ..., S M}The corresponding false positive (FP) counts {FP1, FP2, …, FPM In another example, the detection performance may be represented by a minimum sensitivity level (Sens) corresponding to the stored physiological event onset. LST ) is represented by the FP count of the candidate detection settings {S1, S2, ..., S M}.

[0075] The simulation results generated by the detection simulation circuit 223, such as the detection of multiple candidate settings {S1, S2, ..., S M}, along with the physiological event episode being analyzed, can be presented to a user (e.g., a clinician), such as via a display unit on user interface 230. Additionally or alternatively, detection performance for identifying target cardiac events from stored event episodes under different candidate detection settings, such as generated by detection performance analyzer 224, can be similarly presented to the user, such as displayed on a display unit of user interface 230. The user can review the physiological event episodes and detection performance under different candidate detection settings and select from the candidate detection settings, or modify an existing detection setting, to detect future physiological events.

[0076] The detection control circuit 225 is configured to select a plurality of candidate settings {S1, S2, . . . , S M}Select Detection Settings S * In an example, the detection control circuit 225 selects the S corresponding to the FP count that satisfies a certain condition, such as being below the FP threshold. * In another example, the selected S * Corresponding to the M candidate detection settings {S1,S2,…,S M}The corresponding FP counts {FP1, FP2,…, FP M}The smallest FP count (FP min ), or the lowest sensitivity level (Sens LST ) The corresponding FP count of FP min In some examples, the selected S * can correspond to an operating point on the ROC that results in a desired tradeoff between sensitivity and false positive rate. * The selected detection setting S may correspond to the operating point that maximizes the sum of sensitivity and specificity, or equivalently the difference between sensitivity and false positive rate, which is called the Youden index. *The AMD may be programmed to detect subsequent target cardiac events from the patient.

[0077] In some examples, instead of selecting from a plurality of candidate settings {S1, S2, ..., S M}Automatically select detection settings S * , the detection control circuit 225 may receive a user's selection of a detection setting from a candidate setting. In an example, the detection simulation circuit 223 may perform a simulation to determine the presence of a target cardiac event in a stored physiological event episode under a first detection setting S1, and the detection performance analyzer 224 may determine a first detection performance, such as an FP count under the detection setting S1. The presence of the target cardiac event determined under S1 and the first detection performance may be provided to the user (e.g., displayed on a display unit of the user interface 230). The detection control circuit 225 may receive a ruling from the user on the determination of the presence of the target cardiac event under the provided first detection setting. In response to the received ruling, the detection simulation circuit 223 may re-determine the presence of the target cardiac event in a stored physiological event episode under a different second detection setting S2, and the detection performance analyzer 224 may determine a second detection performance, such as an FP count under the detection setting S2. The presence of the target cardiac event determined under S2 and the corresponding detection performance may be provided to the user. The user may select a detection setting among a plurality of settings, such as between S1 and S2, or including S1 and S2. In some examples, the detection control circuit 225 can compare the determination of the presence of the target cardiac event at S1 and S2 and the first detection performance and the second detection performance to the user, such as on a display unit. Based on the comparison, the user can select between the first detection setting and the second detection setting. The detection control circuit 225 can use the detection setting selected by the user to detect a subsequent target cardiac event.

[0078] In some examples, the detection settings {S1, S2, ..., S M} may additionally or alternatively be composed of a plurality of different duration thresholds {Dur1, Dur2, ..., Dur M} indicates that the target cardiac event is only considered to be present if it lasts for no less than a specific duration threshold (e.g., Dur i ) is detected during the entire time period, the detection analog circuit 223 determines that the physiological event occurs (for example, X k ) in the target cardiac event. For example, the target cardiac event is detected only when a physiological parameter (e.g., ventricular rate variability) exceeds a sensitivity level of at least Dur i The detection stimulation circuit 223 determines that AF exists in the stored physiological event episode only when the duration threshold {Dur1, Dur2, ..., Dur MDuration thresholds represent different confidence levels in detecting a target event from a physiological event episode. For example, if the AF detected in the first stored episode X1 lasts longer than Dur i But smaller than Dur j (>Dur i ) duration, and the AF detected in the second stored episode X2 is maintained longer than Dur j duration, the confidence of the AF detection attached to the second episode X2 is higher than the confidence of the AF detection attached to the first episode X1.

[0079] Automatic detection setting selection or adjustment may be attempted periodically at a scheduled time or at a particular frequency. Alternatively, automatic detection setting selection or adjustment may be triggered by an event, such as when adjudication has revealed a high number of FP detections from a patient (eg, exceeding a threshold FP count).

[0080] The storage control circuit 226 is configured to prioritize the physiological event episodes in the memory circuit 210. The stored event episodes may be prioritized based on the Sens LST Prioritize episodes. Typically, Sens LST Indicates the confidence of detecting the target event from the seizure. LST The lower the value (e.g., the higher the detection threshold), the higher the confidence in the target cardiac event detection. LST Below the sensitivity level threshold, a higher priority can be assigned to the event, and if the Sens LST Exceeding the sensitivity level threshold, a lower priority may be assigned to the event episode. Storage control circuit 226 may store high priority episodes in memory circuit 210 before low priority episodes.

[0081] The storage control circuit 226 can additionally allocate memory space based on event priority. In an example, more memory space can be allocated for high priority episodes than for low priority episodes. If additional high priority episodes are generated, memory can be dynamically allocated. For example, memory space storing low priority episodes can be reallocated for high priority episodes.

[0082] In some examples, episodes of patient physiological events in the episode library 212 may be processed before being re-stored in the memory circuit 210. One example of such data processing is data reduction, such as a downsampling operation or digitization of data samples to improve memory usage efficiency. In an example, low priority episodes may be downsampled at a higher data reduction rate (e.g., using a lower sampling rate and / or a lower resolution) than high priority episodes. Additionally or alternatively, data reduction may involve data truncation such that only selected portions of the episode are stored in the memory 210. In an example, low priority episodes may be truncated to a shorter duration with less data than high priority episodes. In an example of priority-based storage of atrial fibrillation (AF) episodes, cardiac data (e.g., EGM data) may be stored for higher priority AF episodes of longer duration, while only episode characteristic data, such as ventricular rate and AF duration (e.g., AF burden), may be stored for low priority AF episodes.

[0083] In addition to prioritizing pre-existing episodes stored in the episode library 212, the detection control circuit 225 may also prioritize subsequent episodes detected and recorded by the AMD 110 based on their corresponding Sens LST In this example, a higher priority can be assigned to its Sens LST Episodes X at or below the specified sensitivity level threshold p , and are stored in the memory 212. A lower priority may be assigned to its corresponding Sens LST Episodes X exceeding the specified sensitivity level threshold q , where only the truncated data (e.g., seizure characteristics) are stored in the memory 212. Figure 5 Discussion based on Sens LST Example of assigning priorities to episodes.

[0084] The priorities of the stored physiological event episodes may additionally or alternatively be used in prioritized data transmission. In an example, a high priority episode may be sent between the AMD 110 and the external system 125 before a low priority episode. In another example, more communication bandwidth may be allocated for sending high priority episodes compared to low priority episodes. This priority-based control of communication time, sequence, or bandwidth may help clinicians to promptly address medical events of higher clinical significance or higher clinical interest, so that appropriate clinical intervention may be provided as needed. The priorities of the stored physiological event episodes may additionally or alternatively be used in prioritized data output, such as presenting the stored physiological event episodes to a user via the user interface 220. In an example, a high priority episode may be presented to a user before a low priority episode.

[0085] The user interface 230 may include a display unit for displaying the event onset and a plurality of selectable onset characterizations for adjudication. In addition, the display unit may provide suggestions for adjusting AMD programming. The user interface 230 may be coupled to a printer for printing a hard copy of the detection information. The information may be represented in a table, chart, figure, or any other type of text, table, or graphical representation format. The presentation of 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 for issuing a signal about a detected physiological event to a user. The information may be represented in a table, chart, figure, or any other type of text, table, or graphical representation format. The presentation of 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 for issuing a signal about a detected physiological event to a user. In some examples, the user interface 230 may additionally generate suggestions for adjusting AMD programming, such as programming one or more detection algorithms in the characterization algorithm association 214 to the AMD.

[0086] The optional therapy circuit 250 can be configured to deliver therapy to the patient in response to the detection of a target cardiac event. Examples of therapy can include electrical stimulation therapy delivered to the heart, neural tissue, other target tissue, cardioversion therapy, defibrillation therapy, or drug therapy including the 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.

[0087] Figure 3 Generally shown is an example of an arrhythmia management system 300 configured to detect arrhythmias and manage arrhythmia episodes detected from a patient. The arrhythmia management system 300 includes an AMD 310 and an external system 320 that are communicatively coupled to each other via a communication link 115 .

[0088] As Figure 1AMD 310 of the embodiment of AMD 110 shown in FIG. 3 may include sensor circuitry 311 for sensing one or more physiological signals from a subject. The physiological signals may be sensed via one or more implantable, wearable, or otherwise mobile sensors or electrodes associated with the patient. The sensors may be incorporated into a mobile device such as AMD 110 or otherwise associated therewith. Examples of physiological signals may include: a surface electrocardiogram (ECG) sensed from electrodes placed on the surface of the body, a subcutaneous ECG sensed from electrodes placed under the skin, an intracardiac electrogram (EGM) sensed from one or more electrodes on the lead system 108, a chest 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 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, glucose levels and other biomarkers and biochemical markers, among others. 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 register a patient-triggered episode. A trigger may be generated and detected by a patient-triggered detector when the patient exhibits certain signs or symptoms or experiences a precursor event indicative of a target cardiac event. Detection of a patient trigger may activate sensor circuitry 311 to register a patient-triggered episode and acquire physiological data such as one or more physiological signals.

[0089] The arrhythmia detector circuit 312 can be configured to detect arrhythmias using one or more sensed physiological signals. Examples of arrhythmias may include atrial fibrillation, atrial flutter, supraventricular tachycardia, ventricular tachycardia, or ventricular fibrillation. The 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 detection or additionally before and / or after detection, and detection results) can be stored in the internal memory 314.

[0090] 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 scheduled time, or in response to a data query command sent from the external system 320 to the AMD 310. The external system 320, as an embodiment of the external system 125, may receive the arrhythmia episodes via the communication circuit 325. The external memory 322, as an embodiment of the memory circuit 210, may store the arrhythmia episodes in the episode library 212. The external system 320 also includes a detection setting optimizer circuit 326, which is an embodiment of at least a portion of the control circuit 220. The detection setting optimizer circuit 326 may perform an analysis of the arrhythmia episodes stored in the external memory 322 to detect the presence of a target arrhythmia type (e.g., AF) using an arrhythmia detection algorithm such as that used by the arrhythmia detector circuit 312 in the AMD 310. The detection of the target arrhythmia may be performed using a plurality of candidate detection settings, such as different sensitivity levels. The external system 320 includes a user interface 230 that enables a user to annotate the stored arrhythmia episodes, including providing an adjudication decision. The detection setting optimizer circuit 326 can select a detection setting from the candidate detection settings that corresponds to a desired detection performance, such as the number of false positive (FP) detections in the stored arrhythmia episodes. As discussed above, the detection setting optimizer circuit 326 can also optimize the detection settings, such as based on the Sens associated with each arrhythmia episode. LST Arrhythmia episodes are assigned priorities and prioritized.The stored arrhythmia episodes may be presented to a user, such as via user interface 230, in an order according to episode priority for evaluation and decision making.

[0091] The external system 320 includes a programmer 324 that can generate commands for programming the AMD 310 with selected detection settings and other event sensing, arrhythmia detection, or data collection commands. In an example, the selected detection settings can be confirmed or otherwise modified by the user via the user interface 230 and forwarded to the AMD 310 via the communication link 115. The AMD 310 can use the selected detection settings to detect target arrhythmias, record arrhythmia episodes, and send the arrhythmia episodes to the external system via the communication link 115.

[0092] Figure 4An example of at least a portion of a user interface 400 for displaying physiological event onsets, receiving user decisions on physiological event onsets, and interactive programming of detection settings is shown. The user interface portion 400, which is an embodiment of a display unit of the user interface 230, includes a display of information of physiological event onsets generated by a medical device such as AMD 310. By way of example and not limitation, the information may include physiological data 412 and measurement trends 414 obtained from the physiological data 412. Information regarding patient identification and number of episodes may also be displayed and may be selected, such as using drop-down lists, check boxes, radio buttons, list boxes, buttons, toggle buttons, text fields, and other input control elements on the user interface 400. The physiological data 412 may be sensed using electrodes or physiological sensors that communicate with the medical device and collected during, or alternatively before or after, a detected physiological event. By means of Figure 4 In the non-limiting example shown in , physiological data 412 includes electrograms 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, hemodynamic signals, or cardiac mechanical signals sensed from one or more sensors. Measurement trends 414 may include intra-channel or inter-channel timing information, such as heart rate trends, heart rate variability trends, or atrioventricular septal trends. The displayed information may include a detection summary 420. By way of example, the detection summary 420 may include the types of physiological events detected by the AMD, as well as measurements from the sensed physiological signals taken by the AMD. In Figure 4 In the example shown, the displayed episode is detected as an AF episode having a ventricular rate of 170 bpm and a duration of 140 seconds.

[0093] The user interface portion 400 may include a display area for receiving: user annotation of the displayed episode (such as a determination of the event type (e.g., a particular arrhythmia type)), or a designation of an appropriate (e.g., a true positive) detection indicating to the user that the arrhythmia type detected by the device is consistent, or an inappropriate (e.g., a false positive) detection indicating to the user that the arrhythmia type detected by the device is inconsistent.

[0094] The user interface portion 400 may include one or more of the input control elements (e.g., buttons on a screen) that allow a user to run a bout analysis 440 and program detection settings 450. When run bout analysis 440 is activated, the bout analyzer circuit 221 may analyze bouts of physiological events stored in the bout library 212. Detection performance under a plurality of candidate detection settings, such as sensitivity levels and / or duration thresholds, may be displayed on the user interface 400. Figure 5An example of an episode analysis and a presentation of the analysis results are discussed. When programming detection settings 450 is activated, a detection setting may be selected, or an existing detection setting in the AMD may be adjusted and programmed into the AMD. In an example, a user (e.g., a clinician) may manually select or adjust a detection setting based on an analysis of an episode of a patient's physiological events. Alternatively, as previously described with reference to Figure 2 As discussed, the detection control circuit 225 may automatically select or adjust the detection setting selection based on detection performance, such as FP counts or ROC at a plurality of candidate detection settings. The user may confirm or modify the automatic selection of the detection setting.

[0095] Figure 5 500 is a diagram illustrating an example of selecting or adjusting an arrhythmia detection setting based on an analysis of arrhythmia episodes detected by a device stored in a memory. By way of example, five episodes 511-515 recorded by an AMD from a patient are each analyzed by an episode analyzer circuit 221 to determine whether atrial fibrillation (AF) is present in the corresponding episode under each of five different detection settings. The episode analyzer circuit 221 may use an AF detection algorithm that is the same or similar to the AF detection algorithm used by the AMD. The detection algorithm includes a comparison of measurements of physiological parameters obtained from the episodes with a sensitivity level. Physiological parameters used to detect AF may include a ventricular heart rate threshold, a ventricular heart rate variability threshold, and others.

[0096] The five different detection settings are represented by sensitivity levels 1-5, corresponding to detection thresholds 521-525 for specific physiological parameters. Higher sensitivity levels correspond to lower detection thresholds, which have a higher probability of detecting an AF event. Figure 5 As shown in FIG. 1 , sensitivity level 1 < level 2 < level 3 < level 4 < level 5; and corresponding threshold 521 > threshold 522 > threshold 523 > threshold 524. If the physiological parameter falls within the value range (e.g., for sensitivity level 3, between thresholds 522 and 523), it is determined that AF is present in the stored episodes at a specific sensitivity level (e.g., level 3).

[0097] A minimum sensitivity level (Sens) at which AF can be detected may be determined for each of episodes 511-515, such as using episode analyzer circuit 221. LST ). For example, because AF was detected in episode 513 at sensitivity levels 3, 4, and 5, the Sens LST is level 3 (the lowest among levels 3, 4, and 5). The bout analyzer circuit 221 can similarly determine the Sense values ​​of level 1 for bout 511, level 2 for bout 512, level 2 for bout 4, and level 4 for bout 5. LST,etc.

[0098] Each of the episodes 511-515 may be arbitrated, such as using the episode arbiter circuit 222, as one of a proper AF detection (i.e., a true positive or TP detection) labeled as a "Y" episode, an improper AF detection (i.e., a false positive or FP detection) labeled as an "N" episode, or an unarbitrated or indeterminate episode labeled as an "I" episode. The detection control circuit 225 may use the stored episodes and the arbitrated minimum sensitivity level (Sense LST ) to select or adjust the detection settings. Figure 2 As discussed, the selection can be based on detection performance, such as FP counts or sense of physiological event onsets corresponding to multiple candidate settings. LST , or an ROC or metric taken therefrom. For example, the detection control circuit 225 may suggest adjusting sensitivity level 4 (which corresponds to the detection threshold 524 currently being used by AMD) to a lower sensitivity level 2 (which corresponds to the detection threshold 522). Since level 2 has a lower sensitivity than level 4, AMD will avoid FP detection of episodes 513 and 515. Programming the new sensitivity level 2 to AMD may proactively reduce future FP detections, such as events with similar characteristics to episodes 513 or 515. In an example, the adjusted or selected detection settings may be displayed to the user along with the detection performance, and the user may confirm or modify the automatically determined detection settings. Alternatively, the user may manually select or adjust the detection settings (e.g., sensitivity level or detection threshold).

[0099] like Figure 5 As shown in FIG. 5 , each of the bouts 511 - 515 may also be annotated with a corresponding duration (eg, 2 minutes). The bout analyzer circuit 221 may be configured to detect the duration of the bout at multiple duration thresholds {Dur1, Dur2, . . . , Dur M The presence of AF in each episode is determined at a specific sensitivity level only if the physiological parameter satisfies the condition with respect to the sensitivity level for the entire time period that is not shorter than the duration threshold.

[0100] The storage control circuit 226 can determine the priority for storing the episodes 511-515 in the memory. Figure 2 As discussed, with lower Sens LST The episodes of have a higher priority to be stored in the memory. Episodes 511, 512 and 514 have their Sens at lower levels 1 and 2. LST , and each is assigned a higher priority. Attacks 513 and 515 each have Sense at higher sensitivity levels 3 and 4 LST, and thus each is assigned a lower priority. High priority episodes 511, 512, and 514 may have more data to be stored in memory with a larger space allocation, while low priority episodes 513 and 515 are not stored in memory, or have less data (e.g., only episode characteristics) to be stored in memory.

[0101] Figure 6 is a flow chart showing an example of a method 600 for selecting or adjusting arrhythmia detection settings to detect a target cardiac event in a patient. Examples of physiological events include arrhythmias such as atrial fibrillation, atrial flutter, atrial tachycardia, supraventricular tachycardia, ventricular tachycardia, or ventricular fibrillation and other bradyarrhythmias or tachyarrhythmias. The method 600 can be implemented and executed in a mobile medical device such as an implantable or wearable medical device or in a remote patient management system. In an example, the method 600 can be implemented in and executed by an AMD 110, one or more devices in an external system 125, or a physiological event detection and management system 200. Although the present document focuses on arrhythmia detection, the systems and methods discussed herein, or variations thereof, can be used to detect and manage other physiological events, such as syncope, presyncope, or chronic medical conditions such as worsening heart failure (WHF) events.

[0102] The method 600 begins at 610, where user decisions on multiple physiological event episodes (such as arrhythmia episodes detected and recorded by AMD 110) can be received. The arrhythmia episodes can each include physiological data sensed from one or more physiological sensors during the detected arrhythmia event, or additionally include physiological data sensed before and / or after the detected arrhythmia event, and can be stored in the episode library 212. The physiological data associated with the arrhythmia episode can include cardiac electrical or mechanical signals or hemodynamic signals, such as cardiac pressure signals, impedance signals, heart sound signals, and others. Other information about the arrhythmia episodes can also be received at 610, such as measurements or signal metrics obtained from the physiological data (e.g., atrial rate, ventricular rate, variability of atrial or ventricular rate) and device-generated arrhythmia detection or classification decisions associated with each arrhythmia episode. Arrhythmia detection or classification is the designation of a specific arrhythmia type, such as atrial fibrillation, atrial flutter, ventricular tachycardia, or ventricular fibrillation, and others.

[0103] Information about the arrhythmia episode may be presented to a user (eg, a clinician), such as by displaying it on a screen of user interface 230. The user may use, for example, a Figure 4The decision may be provided by the input control element displayed on the display shown in . The decision may include a user designation of the presence of a particular physiological event such as an arrhythmia type (e.g., atrial fibrillation, atrial flutter, supraventricular tachycardia, ventricular tachycardia, or ventricular fibrillation). In some examples, the decision may include a TP decision (which indicates the consistency between the decision and the test results generated by the AMD) or a designation as a FP decision (which indicates the inconsistency between the decision and the test results generated by the AMD). If a decision on the arrhythmia type or a TP or FP decision cannot be made, the episode may be designated as uncertain. In some examples, the decision may include episode characterization or diagnostic information.

[0104] At 620, the physiological event episodes may be analyzed to determine the presence of a target cardiac event under a set of candidate detection settings for each of the stored physiological event episodes, such as using episode analyzer circuit 221. If the physiological parameter satisfies the condition (e.g., exceeds a threshold), then the target cardiac event is determined to be present in the received physiological event episode X at detection setting S1. k If the physiological parameter fails to meet the condition (such as being lower than the corresponding threshold), then the detection setting S j The target cardiac event is determined to be no longer occurring k . The detection algorithm used at 620 to determine the presence of a target cardiac event can be the same as or similar to the detection algorithm used by AMD for detecting and recording the onset of physiological events, such as an arrhythmia detector based on the timing or morphology of cardiac signals sensed from one or more cardiac sites. Candidate detection settings can be represented by multiple sensitivity levels for a particular physiological parameter. Each sensitivity level can correspond to a detection threshold or a range of values ​​for a physiological parameter. The physiological parameters used to determine the presence of a target cardiac event can include physiological signal features (such as time features or morphological features) extracted from the physiological signal or otherwise measured, or a combination of multiple signal features.

[0105] The candidate detection settings may additionally or alternatively be represented by a plurality of duration thresholds. The target cardiac event is determined to be present in the stored episode only if the target cardiac event remains detected throughout a time period that is not shorter than a particular duration threshold. In an example where an arrhythmia is detected from a stored episode, a detection corresponding to a longer duration threshold indicates that the detected arrhythmia persisted for a longer duration and is therefore more likely to be a true arrhythmia event than a detection corresponding to a shorter duration threshold.

[0106] At 630, a detection performance for detecting a target cardiac event from a physiological event onset under the candidate detection setting may be determined, such as by using a comparison of the detection result regarding the physiological event onset at 620 with the user's verdict on the physiological event onset at 610. The detection performance may be represented by a false positive (FP) count corresponding to the candidate detection setting, or by a receiver operating characteristic (ROC) that depicts the detection sensitivity and false positive rate at various operating points represented by the candidate detection setting.

[0107] At 640, a detection setting can be selected from the candidate detection settings based on the determined performance. In an example, the selected detection setting corresponds to an FP count that satisfies a certain condition (such as, below an FP threshold). In another example, the selected detection setting corresponds to a minimum FP count (FPmin) among the candidate detection settings. In yet another example, the selected detection setting can be determined as an operating point on a ROC curve corresponding to a desired tradeoff between sensitivity and false positive rate, such as an operating point that maximizes the difference between sensitivity and false positive rate.

[0108] At 650, the selected detection settings may be programmed into the AMD, automatically or upon user confirmation, to detect subsequent target cardiac events from the patient. Automatic detection setting selection or adjustment may be attempted periodically at a scheduled time or at a specific frequency. Alternatively, automatic detection setting selection or adjustment may be triggered by an event, such as when adjudication has revealed a large number of FP detections from the patient (e.g., exceeding a threshold FP count).

[0109] Figure 7 is a flow chart illustrating an example of a portion of a method 700 that determines performance for detecting target cardiac events from physiological event episodes and prioritizes physiological event episodes for storage in a memory. Method 700 may represent an embodiment of a portion of algorithm 600 , such as step 630 .

[0110] At 710, the detection results obtained at 620 regarding the stored physiological event onset may be used to determine a lowest sensitivity level (Sens) among the sensitivity levels corresponding to the set of candidate detection settings. LST ), at which the target cardiac event can be detected from the onset of physiological events. LST Indicates the confidence of detecting the target event from the seizure. LST The lower (eg, the higher the detection threshold), the higher the confidence in detecting the target cardiac event.

[0111] At 720, the physiological event onset may be detected using the Sens LSTand adjudication to determine the detection performance. Examples of detection performance may include a minimum sensitivity level (Sens LST ) corresponding to the FP count. Then, the Sense corresponding to the stored physiological event can be LST Among the corresponding FP counts, a detection setting corresponding to FPmin is selected at 640 .

[0112] The Sens determined at 710 LST The sensitization control circuit 226 may be used to prioritize physiological event episodes at 730, such as pre-existing episodes stored in the episode library 212 and subsequent episodes recorded by the AMD. For example, the episode prioritization may be performed using the storage control circuit 226. LST Below the sensitivity level threshold, a higher priority can be assigned to the event; and if the Sens LST Exceeding a sensitivity level threshold, a lower priority may be assigned to the event occurrence.

[0113] At 740, physiological event episodes can be stored in a memory (such as episode library 212) according to their respective priorities. High priority episodes can be stored in the memory circuit before low priority episodes. More memory space can be allocated for high priority episodes compared to low priority episodes. In an example, when additional high priority episodes are provided (such as detected and recorded by AMD), memory space for storing low priority episodes can be reallocated for high priority episodes.

[0114] The priority of physiological event episodes can also be used to determine the amount of information about the physiological event episodes to be stored in the memory. In various examples, in order to improve the efficiency of memory usage, physiological event episodes can be data reduced before they are stored in the memory. Data reduction can be achieved using a low sampling rate or a low data resolution, or data truncation can be achieved by storing only selected portions of the episode in the memory. In an example, low priority episodes can be reduced at a higher data reduction rate (such as a lower sampling rate or a lower resolution) than high priority episodes. In another example, low priority episodes can be truncated to a shorter duration than high priority episodes. In an example of prioritizing AF episodes, cardiac data (e.g., EGM) collected during AF can be stored for longer durations for high priority AF episodes, while for low priority AF episodes, only episode characteristic data such as ventricular rate and AF duration (AF burden) are stored in the memory.

[0115] In addition to priority-based data storage, the stored priorities of physiological event episodes can be used additionally or alternatively to schedule data transmission at 740, such as timing, sequencing, or bandwidth allocation, for sending physiological event episodes from one device to another. For example, high priority episodes can be sent from AMD 110 to external system 125 before low priority episodes. More communication bandwidth can be allocated to send high priority episodes than low priority episodes. Physiological event episodes can be output to a user based on the stored priorities of the physiological event episodes. In an example, high priority episodes can be presented to a user before low priority episodes.

[0116] Figure 8 A block diagram generally illustrates an example machine 600 upon which any one or more of the techniques (eg, methodologies) 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.

[0117] In an alternative embodiment, the machine 800 can be operated as a standalone device, or can be connected (e.g., networked) to other machines. In a networked deployment, the machine 800 can operate in a server-client network environment with the capabilities of a server machine, a client machine, or both. 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 PC, a set-top box (STB), a personal digital assistant (PDA), a mobile phone, a network appliance, 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 considered to include any collection of the following machines, which individually 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 cluster configurations.

[0118] As described herein, examples may include logic or multiple components or mechanisms, or may be operated by them. A circuit group is a collection of circuits implemented in a tangible entity including hardware (e.g., simple circuits, gates, logic, etc.). Circuit group members may be flexible and potentially hardware-variable over time. A circuit group includes members that can perform specified operations individually or in combination when in operation. In an example, the hardware of the circuit group may be designed to perform specific operations (e.g., hardwired) invariably. In an example, the hardware of the circuit group may include variably connected physical components (e.g., execution units, transistors, simple circuits, etc.), which include physically modified (e.g., magnetically, electrically, removably placed, etc., of invariably aggregated particles) to encode computer-readable media of instructions for specific operations. When connecting physical components, the underlying electrical properties of the hardware composition, for example, change from an insulator to a conductor, and vice versa. Instructions enable embedded hardware (e.g., execution units or loading mechanisms) to create members of the circuit group in hardware via variable connections to perform parts of specific operations when in operation. Therefore, when the device operates, the computer-readable medium is communicatively coupled to other components of the circuit group members. In an example, any physical component may be used in more than one member of more than one circuit group. For example, in operation, an execution unit may be used in a first circuit of a first circuit group at one point in time and reused by a second circuit in the first circuit group, or reused by a third circuit in a second circuit group at a different time.

[0119] 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 interconnection link (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., a printer, a card reader, etc.).

[0120] 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.

[0121] 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 .

[0122] The term "machine-readable medium" may include any medium capable of storing, encoding, or carrying instructions for execution by the machine 800 and causing the machine 800 to perform any one or more of the techniques of the present disclosure, or capable of storing, encoding, or carrying data structures used by or associated with such instructions. Non-limiting machine-readable medium examples may include solid-state memory and optical and magnetic media. In an example, a large-capacity machine-readable medium includes a machine-readable medium having a plurality of particles having a constant (e.g., stationary) mass. Therefore, a large-capacity machine-readable medium is a non-temporary propagating signal. Specific examples of large-capacity 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.

[0123] Instructions 824 may also be sent or received over a communication network 826 using a transmission medium via a network interface device 820 utilizing any of a variety 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 Wi-Fi network). The Institute of Electrical and Electronics Engineers (IEEE) 802.11 series 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 others. 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 use at least one of single-input multiple-output (SIMO), multiple-input multiple-output (MIMO), or multiple-input single-output (MISO) technology for wireless communication. The term "transmission medium" should be taken to include any intangible medium that can store, encode, or carry instructions for execution by the machine 800, and includes digital or analog communication signals or other intangible media to facilitate the communication of such software.

[0124] Various embodiments are shown in the above figures. One or more features from one or more of these embodiments may be combined to form other embodiments.

[0125] The method examples described herein may be machine or computer implemented at least in part. 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 example. The implementation of such a method may include code, such as microcode, assembly language code or high-level language code or the like. 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.

[0126] 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 detecting a cardiac event from a patient, the system comprising: a memory circuit configured to store episodes of physiological events recorded by a medical device from a patient that satisfy a first detection setting of the medical device; as well as control circuitry, including detection control circuitry, configured to perform an offline analysis of the stored episodes of physiological events to determine the presence of a target cardiac event at a second detection setting having a detection parameter value different from the first detection setting of the medical device, comprising: displaying to a user on a user interface the presence of a target cardiac event of a first event onset determined under the first detection setting; receiving a ruling of a target cardiac event from the user regarding the onset of the first event under the first detection setting; determining, based on the received adjudication of the target cardiac event for the first event episode, an indication that the first event episode is a false-positive FP event episode under the first detection setting; In response to a determined indication that the first event episode is an FP event episode, re-determining the presence of the target cardiac event for stored physiological event episodes that satisfy the second detection setting; and Information regarding the presence of the re-determined target cardiac event for the stored physiological event onset under the first detection setting and the second detection setting is presented to reduce the decision burden on the user.

2. The system according to claim 1, wherein: The stored event onset occurred in the patient at a different time than the first event, wherein the control circuit is configured to program the medical device with the second detection setting to detect a future event onset of the target cardiac event in the patient.

3. The system according to claim 1 or 2, wherein: The detection control circuit is configured to determine a receiver operating characteristic (ROC) having an operating point including the first detection setting and the second detection setting, and provide the determined ROC to the user.

4. The system according to claim 1 or 2, wherein: The first detection setting and the second detection setting include corresponding first sensitivity levels and second sensitivity levels, and wherein, in order to determine the presence of the target cardiac event in one of the stored physiological event episodes, the detection control circuit is configured to compare a physiological parameter derived from one of the stored physiological event episodes with the first sensitivity level and the second sensitivity level.

5. The system according to claim 4, wherein: The first sensitivity level and the second sensitivity level each represent a threshold value or a value range of the physiological parameter.

6. The system according to claim 4, wherein: The target cardiac event comprises an atrial tachyarrhythmia, and the first and second sensitivity levels comprise respective first and second threshold values ​​or respective first and second value ranges of at least one of: Heart rate Heart rate stability; Electrogram morphometric measurements; or Cardiac contractility measurements.

7. The system according to claim 4, wherein: The detection control circuit is further configured as: For each of the stored physiological event episodes, determining a lowest sensitivity level Sens among a plurality of sensitivity levels including the first sensitivity level and the second sensitivity level that is capable of detecting the presence of the target cardiac event from the corresponding stored physiological event episode. LST ;and Use the stored physiological events to detect the occurrence of LST A detection setting is selected from the plurality of sensitivity levels.

8. The system according to claim 7, wherein: The control circuit further includes a storage control circuit configured to store the physiological event based on the stored Sens LST To prioritize the stored physiological event episodes.

9. The system according to claim 8, wherein: The storage control circuit is configured as follows: If the Sens LST Below the sensitivity level threshold, a higher priority is assigned to the event onset; and If the Sens LST Exceeding the sensitivity level threshold, the event occurrence is assigned a lower priority.

10. The system according to claim 9, wherein: The storage control circuit is configured to store a first number of data characteristic of the event occurrence if a high priority is assigned, and to store a second, lower number of data characteristic of the event occurrence if a low priority is assigned.

11. The system according to claim 1 or 2, wherein: The first detection setting and the second detection setting include corresponding first duration thresholds and second duration thresholds, and wherein, in order to determine the presence of the target cardiac event in one of the stored physiological event episodes, the detection control circuit is configured to compare the duration of one of the stored physiological event episodes with the first duration threshold and the second duration threshold.

12. The system of claim 1 or 2, comprising a user interface configured to receive user input of a determination of a stored physiological event onset, in, The control circuit is configured to program the selected detection settings for subsequent determination of the presence of the target cardiac event in the patient.

13. The system according to claim 12, wherein: The user interface is configured to display an indication of the presence of the target cardiac event in the stored physiological event episodes under the first detection setting and the second detection setting.

14. The system of claim 1 or 2, comprising an ambulatory medical device AMD configured to use the received selection of detection settings to detect a target cardiac event from subsequent episodes of patient physiological events.

15. The system according to claim 1 or 2, wherein: The control circuit is configured to automatically select between the first detection setting and the second detection setting to detect a subsequent target cardiac event, the selection being based on the presence of the target cardiac event determined in each of the stored physiological event episodes under the first detection setting and the second detection setting.

Images