CN117479981A

CN117479981A - Decision algorithm bypass conditions

Info

Publication number: CN117479981A
Application number: CN202280042358.3A
Authority: CN
Inventors: 郑雅健; S·R·兰德曼; B·D·冈德森; P·D·齐格勒; S·萨卡; K·T·奥斯迪吉恩; G·拉贾戈帕尔; E·M·伊波利托
Original assignee: Medtronic Inc
Current assignee: Medtronic Inc
Priority date: 2021-06-15
Filing date: 2022-05-27
Publication date: 2024-01-30

Abstract

The present disclosure describes techniques for bypassing algorithms configured to determine a likelihood that episode data is a false indication of a heart episode. A medical device system includes a processing circuit configured to receive episode data and determine whether to bypass the algorithm based on satisfaction of one or more bypass conditions in a set of bypass conditions. In response to bypassing the algorithm, the processing circuit stores the episode data as a true indication of the heart episode.

Description

Decision algorithm bypass conditions

Technical Field

The present disclosure relates generally to medical devices, and more particularly to analysis of signals sensed by medical devices.

Background

The medical device may be used to monitor physiological signals of a patient. For example, some medical devices are configured to sense Electrocardiograph (EGM) signals, such as Electrocardiogram (ECG) signals, that are indicative of electrical activity of the heart via electrodes. Some medical devices are configured to detect the occurrence of an arrhythmia, commonly referred to as a episode, based on the cardiac EGM and, in some cases, based on data from additional sensors. Exemplary cardiac arrhythmia types include asystole, bradycardia, ventricular tachycardia, supraventricular tachycardia, wide QRS wave tachycardia, atrial fibrillation, atrial flutter, ventricular fibrillation, atrioventricular block, premature ventricular contractions, and premature atrial contractions. The medical device may store the cardiac EGM and other data collected during the period of time that includes the episode as episode data. The medical device may also store episode data for a certain period of time in response to user input, e.g., from a patient.

The computing system may obtain episode data from the medical device to allow a clinician or other user to view the episode. The clinician may diagnose the medical condition of the patient based on the occurrence of the identified intra-episode arrhythmia. In some examples, a clinician or other viewer may view the episode data to annotate the episode, including determining whether an arrhythmia detected by the medical device actually occurred, to prioritize the episode and generate a report for further viewing by a clinician who designates the medical device for the patient or is otherwise responsible for care of a particular patient.

Disclosure of Invention

In general, this disclosure describes techniques for bypassing algorithms configured to classify episode data, including cardiac EGM data, as a true or false indication of a heart episode. In some examples, the processing circuit receives the episode data and determines to bypass the algorithm based on one or more bypass conditions in the set of bypass conditions being met. In response to bypassing the algorithm, the processing circuit stores the episode data as a true indication of the heart episode. Bypassing the algorithm in this manner may provide one or more advantages. For example, satisfaction of the bypass condition may indicate a likelihood that the heart attack is true such that a determination by the algorithm may not be necessary and/or the episode may be erroneously identified as false. Thus, bypassing the algorithm according to the techniques of this disclosure may improve the diagnosis of heart attacks and the quality of information provided from the medical system to the caregivers.

In some examples, a method of monitoring a patient includes: receiving, by processing circuitry of the medical device system, episode data for a heart episode; determining, by the processing circuitry and based on meeting one or more bypass conditions of the set of bypass conditions, an algorithm that bypasses a likelihood that is configured to determine that the episode data is a false indication of the heart episode; and storing, by the processing circuit and in response to bypassing the algorithm, the episode data as a true indication of the heart episode.

In some examples, a medical device system includes processing circuitry configured to: receiving episode data for a heart episode; determining whether to bypass an algorithm configured to determine a likelihood that the episode data is a false indication of the heart episode based on one or more bypass conditions in the set of bypass conditions being met; and in response to bypassing the algorithm, storing the episode data as a true indication of the heart episode.

In some examples, a computer-readable medium comprising instructions that, when executed, cause processing circuitry to: receiving episode data; determining whether to bypass an algorithm configured to determine a likelihood that the episode data is a false indication of a heart episode based on one or more bypass conditions in the set of bypass conditions being met; and in response to bypassing the algorithm, storing the episode data as a true indication of the heart episode.

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

Drawings

Fig. 1 is a conceptual diagram illustrating an exemplary medical device system.

Fig. 2 is a block diagram illustrating an exemplary configuration of the Implantable Medical Device (IMD) of fig. 1.

Fig. 3 is a conceptual side view illustrating an exemplary configuration of the IMD of fig. 1 and 2.

Fig. 4 is a functional block diagram illustrating an exemplary configuration of the computing system of fig. 1.

Fig. 5 is a flow chart illustrating exemplary operations for utilizing an exemplary medical device system.

Like reference numerals refer to like elements throughout the drawings and description.

Detailed Description

Various types of implantable and external medical devices detect arrhythmia episodes based on sensed cardiac EGMs and, in some cases, other physiological parameters. External devices that may be used for non-invasive sensing and monitoring of cardiac EGMs include wearable devices, such as patches, watches, rings, necklaces, or clothing, having electrodes configured to contact the patient's skin. Such external devices may facilitate relative patient movement during normal daily activities Long-term monitoring, and may periodically transmit collected data, such as episode data of detected arrhythmia episodes, to a remote patient monitoring system (sometimes referred to herein as a "monitoring system"), such as the meiton force care link ^TM Network (Medtronic Carelink) ^TM Network)。

An Implantable Medical Device (IMD) may sense and monitor a cardiac EGM and detect arrhythmia episodes. Exemplary IMDs for monitoring cardiac EGMs include: pacemakers and implantable cardioverter-defibrillators, which may be coupled to intravascular or extravascular leads; and a pacemaker having a housing configured for implantation within the heart, which may be leadless. Some IMDs that do not provide therapy, such as implantable patient monitors, sense cardiac EGMs. One example of such an IMD is the real LINQ commercially available from Medun force company (Medtronic plc) ^TM An Insertable Cardiac Monitor (ICM) that is percutaneously insertable. Such IMDs may facilitate relatively long-term monitoring of patients during normal daily activities, and may periodically transmit collected data, such as episode data for detected arrhythmia episodes, to a remote patient monitoring system, such as the meiton force Carelink ^TM A network.

Such web services may support centralized or clinical-based arrhythmia episode viewing by uploading episode data from medical devices and distributing the episode data to various users. The episode data may include an indication of one or more arrhythmias detected by the medical device during the episode. The episode data may also include data collected by the medical device during a period of time that includes times before and after the moment when the medical device determines that one or more arrhythmias have occurred. The episode data may include digitized cardiac EGMs during the time period, heart rates or other parameters derived from EGMs during the time period, and any other physiological parameter data collected by the medical device during the time period.

In response to receiving seizure data, the remote patient monitoring system may be configured to examine seizures and annotate those seizures. In an example, the monitoring system may apply one or more Atrial Fibrillation (AF) decision algorithms (such as a machine learning model) to the episode data to detect AF, time in AF, atrial Tachycardia (AT), time in AT/AF, pause (e.g., an extended R-R interval representing an interruption in ventricular depolarization), and other types of arrhythmias. In some cases, the decision algorithm of the monitoring system may classify the episode data as a true or false indication of a heart episode. These algorithms may help reduce the amount of time a physician spends examining episodes, thereby allowing them to focus on treating the patient. Nevertheless, in some scenarios, it may be preferable to bypass the algorithm and replace the algorithm with having the physician manually examine the episode data.

The present disclosure describes a medical device system that uses processing circuitry to bypass a decision algorithm of a monitoring system configured to classify episode data including cardiac EGM data as a true or false indication of a heart episode (e.g., AF episode). The medical device system may include a medical device, such as one of the devices described above or any other type of implantable device, such as a subcutaneous heart monitoring device, a single lumen ICD, an extravascular ICD, a subcutaneous ICD, or any other type of device configured to classify a detected heart attack. The system may also include an external device, such as a cloud-based system external to the cardiac monitoring device, as described above in Medtronic Carelink ^TM A network. The cloud-based system may include a monitoring system.

Since cardiac monitoring devices are typically battery powered and in the case of IMDs need to have sufficient battery life to justify implantation, these devices typically have limited processing power in order to limit battery consumption, which can limit the complexity of algorithms that can be implemented inside the cardiac monitoring device. Thus, the heart monitoring device may be configured to transmit data collected for a suspected heart attack to an external system, such that the external system may post-process the stored and transmitted data of the attack using advanced signal processing techniques for later review by a physician. The transmission of data may be scheduled to occur in response to an event (e.g., abnormal heart activity, etc.). For example, the cardiac monitoring apparatus may transmit episode data to an external system daily. Additionally or alternatively, the cardiac monitoring system may send event responsive transmissions. In such examples, the event may be something sensed by the heart monitoring device (e.g., by a episode deemed severe due to type or severity) or a user request.

The present disclosure describes advanced signal processing techniques that may be used by an external system to post-process episodes detected by a cardiac monitoring apparatus. Although the techniques of this disclosure will be described as being performed by an external system, it should be understood that in other embodiments, the described techniques may be performed by the IMD itself or a device (e.g., a smartphone, access point, or other edge device) for facilitating communication between the IMD and the external system. As described above, the medical device system may use processing circuitry to receive seizure data. The processing circuitry of the medical device system may then determine whether to bypass the decision algorithm based on satisfaction of one or more bypass conditions in the set of bypass conditions. In response to bypassing the decision algorithm, the processing circuit may store episode data as a true indication of the heart episode (such as an AF episode).

The set of bypass conditions may include various bypass conditions. One exemplary bypass condition may be a time period condition. When the episode data received by the processing circuitry of the medical device system is the first transmission of episode data for a heart episode for a period of time (e.g., one month), the medical device system may determine that the episode data satisfies a period of time condition. For example, if the transmission of seizure data by a medical device to a medical device system is a first transmission of seizure data during a certain period of time for a particular month (e.g., five months), the medical device system may determine that the seizure data satisfies a period of time condition and a decision algorithm that bypasses the monitoring system. Thus, the medical device system may store episode data in a memory (e.g., of the medical device system) for viewing by a physician.

In some examples, the time period may be based on the health of the patient. Exemplary health conditions may include congestive heart failure, hypertension, age, diabetes, past stroke, vascular disease, gender, and the like. For example, if the patient has a health condition such as congestive heart failure, hypertension, diabetes, and/or vascular disease, the period of time may be relatively short (e.g., 7 days to 14 days) to potentially increase the frequency with which the medical device system bypasses the decision algorithm. Additionally or alternatively, if the patient experiences a high frequency of episodes, the time period may be relatively short to potentially increase the frequency with which the medical device system bypasses the decision algorithm. In some examples, the medical device system may select a predetermined length of time period based on the health condition of the patient. Additionally or alternatively, the physician may manually define the length of the time period.

In another example, if the transmission of the episode data is a subsequent transmission of the episode data during the time period (e.g., a second transmission of the episode data), the medical device system may not bypass the decision algorithm such that the decision algorithm is able to determine a likelihood that the episode data is a true or false indication of a heart attack. Thus, the time period conditions may ensure that the medical device system stores a first transmission of episode data for any given time period. This may be beneficial because when treating a patient, a first transmission of seizure data during a certain period of time may be more relevant to a physician than a subsequent transmission of seizure data during the same period of time.

The set of bypass conditions may additionally or alternatively include interval conditions. When the episode data received by the processing circuitry of the medical device system is the first transmission of the episode data for a heart attack after a time interval (e.g., 10 days) has elapsed from a previous transmission of the episode data for the heart attack, the medical device system may determine that the episode data satisfies the interval condition. For example, if the transmission of episode data by a medical device to a medical device system is the first transmission of episode data after a time interval of 10 days has elapsed from a previous transmission of episode data for a heart attack, the medical device system may determine that the episode data satisfies the interval condition and a decision algorithm that bypasses the monitoring system. Thus, the medical device system may store episode data in a memory (e.g., of the medical device system) for viewing by a physician.

In another example, if the transmission of the episode data is a transmission of episode data before the time interval elapses (e.g., a transmission of episode data that remains 2 days before the time interval elapses), the medical device system may not bypass the decision algorithm such that the decision algorithm can determine the likelihood that the episode data is a true or false indication of a heart attack. In this way, the interval condition may ensure that the medical device system stores transmission of seizure data that occurs at least a predetermined time interval after transmission of immediately preceding seizure data. This may be beneficial because the first transmission of episode data after a time interval has elapsed may be unlikely to be a false indication of a heart attack, thus warranting a doctor's view of the episode data.

As described in more detail below, the set of bypass conditions may include additional bypass conditions including, but not limited to, an implant condition, a long duration condition, a short duration condition, a user input condition, a frailty condition, a blood pressure condition, and/or the like. The set of bypass conditions may also include a very fast rate with a rate start condition, a new start condition, an increase in edema or detection of a fall event condition, a decrease in activity duration condition, etc. Further, in some examples, the processing circuitry of the medical device system may be configured to weight each bypass condition in the set of bypass conditions for determining a bypass decision algorithm. In such examples, the processing circuit may assign a weight to each bypass condition in the set of bypass conditions, and in response to determining that the episode data satisfies one or more of the bypass conditions, calculate an aggregate weight for the one or more bypass conditions satisfied by the episode data. The processing circuitry may then determine to bypass the decision algorithm based on whether the aggregate weight satisfies a weight threshold. For example, if the aggregate weight exceeds a weight threshold, the processing circuitry may bypass the decision algorithm, storing episode data in memory (e.g., of the medical device system) for viewing by a physician. In some examples, the processing circuitry may determine satisfaction of one or more bypass conditions using decision trees, random forests, fuzzy logic, or the like in addition to or as an alternative to computing aggregate weights for the one or more bypass conditions.

Although described primarily with respect to remote patient monitoring systems, the techniques of this disclosure may also be applied to decision algorithms for medical devices having the ability to decide on heart attacks, such as heart monitoring devices. For example, the cardiac monitoring apparatus may include dedicated processing circuitry configured to perform a machine learning algorithm or other decision algorithm. Accordingly, a medical device (e.g., an insertable cardiac monitor or other implantable medical device) may be configured to individually perform one or more techniques of the present disclosure. However, in such examples, transmission of seizure data across a network may not be required (e.g., because collecting seizure data and determining seizure data may be performed by the same medical device).

Fig. 1 is a conceptual diagram illustrating an example of a medical device system 2 configured to bypass a decision algorithm in accordance with the techniques of this disclosure. Exemplary techniques may be used with IMD 10, which may communicate wirelessly with external device 12. In some examples, IMD 10 is implanted outside of the chest of patient 4 (e.g., subcutaneously in the chest position shown in fig. 1). IMD 10 may be positioned near a sternum near or just below a heart level of patient 4, e.g., at least partially within a heart outline. IMD 10 includes a plurality of electrodes (not shown in fig. 1) and is configured to sense cardiac EGMs via the plurality of electrodes. In some examples, IMD 10 employs LINQ ^TM Form of ICM. Although described primarily in the context of an example in which the medical device collecting episode data takes the form of an ICM, the techniques of the present disclosure may be implemented in a system including any one or more implantable or external medical devices, including monitors, pacemakers, or defibrillators.

External device 12 is a computing device configured for wireless communication with IMD 10. By way of example, external device 12 may be a mobile phone or other computing device of patient 4 or another user or a computing device that is detected to be in communication with IMD 10. External device 12 may be configured to communicate with computing system 24 via network 25. In some examples, external device 12 may provide a user interface and allow a user to interact with IMD 10. Computing system 24 may include a computing device configured to allow a user to interact with IMD 10 or data collected from the IMD via network 25.

External device 12 may be used to retrieve data from IMD 10 and may transmit the data to computing system 24 via network 25. The retrieved data may include values of physiological parameters measured by IMD 10, indications of episodes of cardiac arrhythmias or other diseases detected by IMD 10, collected episode data, and other physiological signals recorded by IMD 10. The episode data may include a segment of an EGM recorded by IMD 10, for example, as a result of IMD 10 determining that an episode of an arrhythmia or another disorder occurred during the segment, or in response to a request to record a segment from patient 4 or another user.

In some examples, computing system 24 includes one or more handheld computing devices, computer workstations, servers, or other networked computing devices. In some examples, computing system 24 may include one or more devices implementing monitoring system 450, including processing circuitry and storage devices. In some examples, computing system 24, network 25, and monitoring system 450 may pass the midton force Carelink ^TM A network or other patient monitoring system.

Network 25 may include one or more computing devices (not shown), such as one or more non-edge switches, routers, hubs, gateways, security devices (such as firewalls), intrusion detection and/or protection devices, servers, computer terminals, laptops, printers, databases, wireless mobile devices (such as cellular telephones or personal digital assistants), wireless access points, bridges, cable modems, application accelerators, or other network devices. The network 25 may comprise one or more networks managed by a service provider and may thus form part of a large-scale public network infrastructure (e.g., the internet). Network 25 may provide computing devices, such as computing system 24 and IMD 10, with access to the internet, and may provide a communication framework that allows the computing devices to communicate with one another. In some examples, network 25 may be a dedicated network that provides a communication framework that allows computing system 24, IMD 10, and/or external device 12 to communicate with each other but that separates computing system 24, IMD 10, or external device 12 from devices external to network 25 for security purposes. In some examples, communications between computing system 24, IMD 10, and external device 12 are encrypted.

Monitoring system 450, e.g., implemented by processing circuitry of computing system 24, may implement the techniques of this disclosure, including applying a machine learning model or other model or algorithm to episode data to detect arrhythmias. Monitoring system 450 may receive episode data for episodes from a medical device comprising IMD 10, which may store the episode data in response to detection of its arrhythmia and/or user input. Based on the application of the one or more arrhythmia classification algorithms, monitoring system 450 may determine a likelihood that one or more types of one or more arrhythmias occur during an episode, which in some examples includes an arrhythmia identified by a medical device storing episode data. Monitoring system 450 may, for example, receive episode data, such as ECG data, for an episode of a patient from IMD 10. The monitoring system 450 may then apply one or more algorithms, such as a machine learning model, to classify the episode data as a true or false indication of a heart episode.

The processing circuitry of medical device system 2 (e.g., IMD 10, external device 12, computing system 24, and/or one or more other computing devices) may be configured to perform the exemplary techniques of the present disclosure for bypassing algorithms configured to classify episode data including cardiac EGM data as a true or false indication of a heart episode. In response to the processing circuitry of the medical device system 2 receiving seizure data, the processing circuitry may determine whether to bypass the decision algorithm based on meeting one or more bypass conditions in the set of bypass conditions, as discussed in more detail with respect to fig. 4. In response to bypassing the decision algorithm, the processing circuit may store episode data as a true indication of the heart episode (such as an AF episode).

Fig. 2 is a block diagram illustrating an exemplary configuration of IMD 10 of fig. 1. As shown in fig. 2, IMD 10 includes processing circuitry 50, sensing circuitry 52, communication circuitry 54, memory 56, sensors 58, switching circuitry 60, and electrodes 16A, 16B (hereinafter "electrode 16"), one or more of which may be disposed on a housing of IMD 10. In some examples, memory 56 includes computer readable instructions that, when executed by processing circuitry 50, cause IMD 10 and processing circuitry 50 to perform various functions attributed to IMD 10 and processing circuitry 50 herein. Memory 56 may include any volatile, non-volatile, magnetic, optical, or electrical media, such as Random Access Memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), electrically Erasable Programmable ROM (EEPROM), flash memory, or any other digital media.

The processing circuitry 50 may include fixed function circuitry and/or programmable processing circuitry. The processing circuit 50 may include any one or more of a microprocessor, a controller, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), or equivalent discrete or analog logic circuit. In some examples, processing circuitry 50 may include multiple components (such as one or more microprocessors, one or more controllers, one or more DSPs, one or more ASICs, or any combinations of one or more FPGAs), as well as other discrete or integrated logic circuitry. The functions attributed to processing circuitry 50 herein may be embodied as software, firmware, hardware or any combination thereof.

The sensing circuit 52 may be selectively coupled to the electrodes 16A, 16B via a switching circuit 60 as controlled by the processing circuit 50. The sensing circuit 52 may monitor signals from the electrodes 16A, 16B to monitor the electrical activity of the heart of the patient 4 of fig. 1 and generate cardiac EGM data for the patient 4. In some examples, processing circuitry 50 may identify sensed characteristics of the cardiac EGM to detect an arrhythmia episode for patient 4. Processing circuitry 50 may store digitized cardiac EGMs and characteristics of EGMs for detecting an arrhythmia episode in memory 56 as episode data for the detected arrhythmia episode. In some examples, processing circuitry 50 stores one or more segments of cardiac EGM data, features derived from cardiac EGM data, and other episode data in response to instructions from external device 12 (e.g., when patient 4 experiences one or more symptoms of an arrhythmia and inputs a command to external device 12 instructing IMD 10 to upload data for analysis by a monitoring center or clinician).

In some examples, processing circuit 50 transmits episode data for patient 4 to an external device, such as external device 12 of fig. 1, via communication circuit 54. For example, IMD 10 sends digitized cardiac EGMs and other episode data to network 25 for processing by monitoring system 450 of fig. 1.

Sensing circuit 52 and/or processing circuit 50 may be configured to detect cardiac depolarizations (e.g., P-waves of atrial depolarizations or R-waves of ventricular depolarizations) when the cardiac EGM amplitude exceeds a sensing threshold. In some examples, for cardiac depolarization detection, sensing circuit 52 may include rectifiers, filters, amplifiers, comparators, and/or analog-to-digital converters. In some examples, sensing circuit 52 may output an indication to processing circuit 50 in response to sensing of cardiac depolarization. In this manner, processing circuitry 50 may receive an indication of detected cardiac depolarization corresponding to the presence of detected R-waves and P-waves in respective chambers of the heart. Processing circuitry 50 may use the detected indications of R-waves and P-waves to determine characteristics of the cardiac EGM (including depolarization intervals, heart rate) and detect cardiac arrhythmias (such as tachyarrhythmias and asystole). The sensing circuit 52 may also provide one or more digitized cardiac EGM signals to the processing circuit 50 for analysis, e.g., for cardiac rhythm discrimination and/or identification and characterization of cardiac EGM features such as QRS amplitude and/or width, or other morphological features.

In some examples, IMD 10 includes one or more sensors 58, such as one or more accelerometers, microphones, optical sensors, and/or pressure sensors. In some examples, the sensing circuitry 52 may include one or more filters and amplifiers for filtering and amplifying signals received from one or more of the electrodes 16A, 16B and/or other sensors 58. In some examples, the sensing circuit 52 and/or the processing circuit 50 may include rectifiers, filters and/or amplifiers, sense amplifiers, comparators, and/or analog-to-digital converters. The processing circuit 50 may determine the physiological parameter values of the patient 4 based on signals from the sensor 58, which may be used to identify arrhythmia episodes and stored as episode data in the memory 56.

Communication circuitry 54 may include any suitable hardware, firmware, software, or any combination thereof for communicating with another device, such as external device 12. The communication circuitry 54 may be configured to use any of a variety of wireless communication schemes (e.g., bluetooth @) Or Bluetooth Low energy (Bluetooth Low +)>) A) communicate. Under control of the processing circuitry 50, the communication circuitry 54 may receive downlink telemetry from the external device 12 or another device and transmit uplink telemetry to the external device or another device by way of an internal or external antenna (e.g., antenna 26). In some examples, the processing circuitry 50 may be configured to control the processing circuitry via an external device (e.g., external device 12) and a middleman force as developed by middleman force limited of irish dublin>A computer network of the network communicates with networked computing devices.

Although described herein in the context of exemplary IMD 10, the techniques for arrhythmia detection disclosed herein may be used with other types of devices. For example, the techniques may be used with an external cardiac defibrillator coupled to an electrode external to the cardiovascular system, micra configured to be implanted into the heart as commercially available from Midun force Inc. of Ireland Dublin ^TM Transcatheter pacemakers such as transcatheter pacing systems, e.g., real LINQ, also commercially available from meiton force corporation ^TM ICM, etc. may be inserted into a heart monitor, neurostimulator, drug delivery device, medical device external to patient 4, wearable device such as a wearable cardioverter defibrillator, fitness tracker or other wearable device, mobile device such as a mobile phone, "smart" phone, laptop computer, tablet computer, personal Digital Assistant (PDA), etc. or patch such as "smart" glasses, "smart" patchA piece or "smart" garment such as a "smart" watch.

Fig. 3 is a conceptual side view illustrating an exemplary configuration of IMD 10. In the example shown in fig. 3, IMD 10 may include a leadless subcutaneous implantable monitoring device having a housing 14 and an insulating cover 74. Electrodes 16A and 16B may be formed or placed on the outer surface of cover 74. The circuits 50-56 and 60 described above with respect to fig. 2 may be formed or placed on the inner surface of the cover 74 or within the housing 14. In the illustrated example, the antenna 26 is formed or placed on an inner surface of the cover 74, but in some examples may be formed or placed on an outer surface. In some examples, the sensor 58 may also be formed or placed on an inner or outer surface of the cover 74. In some examples, insulating cover 74 may be positioned over open housing 14 such that housing 14 and cover 74 enclose antenna 26, sensor 58, and circuits 50-56 and 60, and protect the antenna and circuits from fluids such as bodily fluids.

One or more of the antenna 26, the sensor 58, or the circuits 50-56 may be formed on the insulating cover 74, such as by using flip-chip technology. The insulating cover 74 may be flipped over onto the housing 14. When flipped over and placed onto housing 14, components of IMD 10 formed on the inside of insulating cover 74 may be positioned in gap 76 defined by housing 14. The electrode 16 may be electrically connected to the switching circuit 60 through one or more vias (not shown) formed through the insulating cover 74. The insulating cover 74 may be formed of sapphire (i.e., corundum), glass, parylene, and/or any other suitable insulating material. The housing 14 may be formed of titanium or any other suitable material (e.g., biocompatible material). The electrode 16 may be formed of any of stainless steel, titanium, platinum, iridium, or alloys thereof. In addition, the electrode 16 may be coated with a material such as titanium nitride or fractal titanium nitride, although other suitable materials and coatings for such electrodes may be used.

Fig. 4 is a block diagram illustrating an exemplary configuration of computing system 24. In the illustrated example, the computing system 24 includes processing circuitry 402 for executing applications 424, including a monitoring system 450 or any other application described herein. Computing system 24 may be any component or system that includes processing circuitry or other suitable computing environment for executing software instructions, and for example does not necessarily include one or more of the elements shown in fig. 4 (e.g., input device 404, communication circuitry 406, user interface device 410, or output device 412; and in some examples, components such as one or more storage devices 408 may not be co-located with or in the same rack as other components). In some examples, computing system 24 may be a cloud computing system distributed across multiple devices.

In the example of fig. 4, computing system 24 includes processing circuitry 402, one or more input devices 404, communication circuitry 406, one or more storage devices 408, user Interface (UI) devices 410, and one or more output devices 412. In some examples, computing system 24 also includes an application 424 and an operating system 416, such as a monitoring system 450, that may be executed by computing system 24. Each of the components 402, 404, 406, 408, 410, and 412 may be coupled (physically, communicatively, and/or operatively) for inter-component communication. In some examples, communication channel 414 may include a system bus, a network connection, an inter-process communication data structure, or any other method for communicating data. For example, components 402, 404, 406, 408, 410, and 412 may be coupled by one or more communication channels 414.

In one example, processing circuitry 402 is configured to implement functions and/or process instructions for execution within computing system 24. For example, processing circuitry 402 may be capable of processing instructions stored in storage 408. Examples of processing circuitry 402 may include any one or more of the following: a microprocessor, a controller, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), or an equivalent discrete or integrated logic circuit.

The one or more storage devices 408 may be configured to store information within the computing device 400 during operation. In some examples, storage 408 is described as a computer-readable storage medium. In some examples, storage 408 is temporary storage, meaning that the primary purpose of storage 408 is not long-term storage. In some examples, storage 408 is described as volatile memory, meaning that when the computer is turned off, storage 408 does not maintain stored content. Examples of volatile memory include RAM, dynamic Random Access Memory (DRAM), static Random Access Memory (SRAM), and other forms of volatile memory known in the art. In some examples, storage 408 is used to store program instructions that are executed by processing circuitry 402. In one example, storage 408 is used by software or application 424 running on computing system 24 to temporarily store information during program execution.

In some examples, storage 408 also includes one or more computer-readable storage media. Storage 408 may be configured to store a greater amount of information than volatile memory. Storage 408 may additionally be configured for long-term storage of information. In some examples, storage 408 includes non-volatile storage elements. Examples of such non-volatile storage elements include magnetic hard disks, optical disks, floppy disks, flash memory, or various forms of electrically programmable memory (EPROM) or electrically erasable and programmable memory (EEPROM).

In some examples, computing system 24 also includes communication circuitry 406 to communicate with other devices and systems, such as IMD 10 and external device 12 of fig. 1. Communication circuitry 406 may include a network interface card such as an ethernet card, an optical transceiver, a radio frequency transceiver, or any other type of device that may send and receive information. Other examples of such network interfaces may include 3G, 4G, 5G, and WiFi radios.

In one example, computing system 24 also includes one or more user interface devices 410. In some examples, user interface device 410 is configured to receive input from a user through tactile, audio, or video feedback. Examples of one or more user interface devices 410 include a presence-sensitive display, a mouse, a keyboard, a voice response system, a camera, a microphone, or any other type of device for detecting commands from a user. In some examples, the presence-sensitive display includes a touch-sensitive screen.

One or more output devices 412 may also be included in the computing system 24. In some examples, the output device 412 is configured to provide output to a user using tactile, audio, or video stimuli. In one example, output device 412 includes a presence-sensitive display, a sound card, a video graphics adapter card, or any other type of device for converting signals into a suitable form understandable to humans or machines. Additional examples of output devices 412 include speakers, cathode Ray Tube (CRT) monitors, liquid Crystal Displays (LCDs), or any other type of device that can generate an understandable output to a user.

Computing system 24 may include an operating system 416. In some examples, operating system 416 controls the operation of components of computing system 24. For example, in one example, operating system 416 facilitates communication of one or more application programs 424 and monitoring system 450 with processing circuitry 402, communication circuitry 406, storage 408, input device 404, user interface device 410, and output device 412.

The application programs 424 may also include program instructions and/or data that may be executed by the computing device 400. One or more example applications 424 that may be executed by the computing device 400 may include the monitoring system 450. Other additional applications not shown may be included alternatively or additionally to provide other functions described herein, and are not depicted for simplicity.

Computing system 24 may receive episode data for episodes stored by a medical device such as IMD 10 via communication circuitry 406. The storage 408 may store episode data for episodes in the storage 408. The episode data may have been collected by the medical device in response to the medical device detecting an arrhythmia and/or user input directing storage of episode data.

The monitoring system 450, as implemented by the processing circuit 402, may view and annotate the episode and generate a report or other description of the episode after the annotation for viewing by a clinician or other viewer. Monitoring system 450 may display episode data, arrhythmia type classification, and any other information described herein to a user using input device 404, output device 412, and/or communication circuit 406, and receive any comments or other inputs regarding episode data from the user.

In the example shown in fig. 4, the monitoring system 450 may apply one or more decision algorithms 452 to the episode data. The decision algorithm 452 may comprise, for example, a neural network, such as a deep neural network, which may comprise, for example, a convolutional neural network, a multi-layer perceptron, and/or an echo state network. In an example, decision algorithm 452 represents one or more arrhythmia classification machine learning models. The decision algorithm 452 may be configured to output, for each arrhythmia type classification of the plurality of arrhythmia type classifications, a value indicating a likelihood that type of arrhythmia occurred at any point in time during the episode. The monitoring system 450 may apply a configurable threshold (e.g., 50%, 75%, 90%, 95%, 99%) to the likelihood value to identify the episode as including one or more arrhythmia types, e.g., based on the likelihood that the classification meets or exceeds the threshold. Although fig. 4 shows an example in which the monitoring system 450 applies one or more decision algorithms 452 as part of its algorithm to classify the arrhythmia, in some examples the algorithm includes other artificial intelligence or other models or algorithms that do not necessarily require machine learning, such as linear regression, trend analysis, decision trees, rules, or thresholds.

In accordance with the techniques of this disclosure, processing circuit 402 is configured to execute computer-readable instructions stored within storage 408 that cause processing circuit 402 to bypass decision algorithm 452 configured to classify episode data as a true or false indication of a heart attack. As described above, the processing circuit 402 may determine whether to bypass the decision algorithm 452 based on satisfaction of one or more bypass conditions in the set of bypass conditions in response to receiving episode data. In response to bypassing decision algorithm 452, processing circuit 402 may store episode data as a true indication of a heart episode (such as an AF episode).

The set of bypass conditions may include various bypass conditions. One exemplary bypass condition may be a time period condition. When the episode data received by the processing circuit 402 is the first transmission of episode data for a cardiac episode for a certain time period (e.g., one month), the processing circuit 402 may determine that the episode data meets the time period condition. In some examples, the time period may be based on the health of the patient. Exemplary health conditions may include congestive heart failure, hypertension, age, diabetes, past stroke, vascular disease, gender, and the like. For example, if the patient has a health condition such as congestive heart failure, hypertension, diabetes, and/or vascular disease, the period of time may be relatively short (e.g., 7 days to 14 days) to potentially increase the frequency with which the medical device system bypasses the decision algorithm 452. In some examples, the medical device system may select a predetermined length of time period based on the health condition of the patient. Additionally or alternatively, the physician may manually define the length of the time period.

In an example, if the transmission of episode data by IMD 10 to medical device system 2 is the first transmission of episode data during a time period of a particular month (e.g., wubi), processing circuitry 402 may determine that the episode data satisfies the time period condition and bypass decision algorithm 452. Accordingly, the processing circuit 402 may store episode data in a memory (e.g., storage 408) for viewing by a physician.

In another example, if the transmission of episode data is a subsequent transmission of episode data during the period (e.g., a second transmission of episode data), the processing circuit 402 may not bypass the decision algorithm 452 such that the decision algorithm 452 is able to determine a likelihood that the episode data is a true or false indication of a heart attack. Thus, the time period conditions may ensure that the medical device system 2 stores a first transmission of episode data for any given time period. This may be beneficial because when treating a patient, a first transmission of seizure data during a certain period of time may be more relevant to a physician than a subsequent transmission of seizure data during the same period of time.

The set of bypass conditions may additionally or alternatively include interval conditions. When the episode data received by the processing circuit 402 is the first transmission of the episode data for a heart episode after a time interval (e.g., 10 days) has elapsed from a previous transmission of the episode data for the heart episode, the processing circuit 402 may determine that the episode data meets the interval condition. For example, if the transmission of episode data by IMD 10 to medical device system 2 is the first transmission of episode data after a time interval of 10 days from the previous transmission of the episode data for a heart attack, processing circuitry 402 may determine that the episode data satisfies the interval condition and bypass decision algorithm 452. Thus, the medical device system 2 may store episode data in memory for viewing by a physician.

In another example, if the transmission of seizure data is a transmission of seizure data before a time interval elapses (e.g., a transmission of seizure data that remains 2 days before the time interval elapses), the medical device system 2 may not bypass the decision algorithm 452, such that the decision algorithm 452 is able to determine a likelihood that the seizure data is a true or false indication of a heart attack. In this way, the interval condition may ensure that the medical device system 2 stores transmission of seizure data that occurs at least a predetermined time interval after transmission of immediately preceding seizure data. This may be beneficial because the first transmission of episode data after a time interval has elapsed may be unlikely to be a false indication of a heart attack, thus warranting a doctor's view of the episode data.

The set of bypass conditions may additionally or alternatively include implantation conditions. When the episode data received by the processing circuitry 402 is one of the first N transmissions of episode data for a heart attack after implantation of the IMD 10 of the medical device system 2, the processing circuitry 402 may determine that the episode data satisfies the implantation condition. For example, if N is 10 and the transmission of episode data by IMD 10 to medical device system 2 is the fifth transmission of episode data after implantation of IMD 10, processing circuitry 402 may determine that the episode data satisfies the implantation conditions and bypass decision algorithm 452. Thus, the medical device system 2 may store episode data in memory for viewing by a physician.

In another example, if the transmission of episode data is the eleventh transmission of episode data after implantation of IMD 10, medical device system 2 may not bypass decision algorithm 452 such that decision algorithm 452 is able to determine a likelihood that the episode data is a true or false indication of a heart attack. In this manner, the implantation conditions may ensure that medical device system 2 stores the first N transmissions of episode data after implantation of IMD 10. This may be beneficial because the first N transmissions of episode data after implantation of IMD 10 may be unlikely to be a false indication of a heart attack, thus warranting a physician's view of the episode data. It should be appreciated that N may be any number of transmissions, such as 5, 8, 12, 20, etc.

The set of bypass conditions may additionally or alternatively include a long-duration condition. When the duration of episode data received by the processing circuit 402 exceeds a long-duration threshold, the processing circuit 402 may determine that the episode data satisfies a long-duration condition. For example, if the long duration threshold is 30 minutes and the duration of episode data received by the processing circuit 402 is 31 minutes, the processing circuit 402 may determine that the episode data satisfies the long duration condition and bypass the decision algorithm 452. Thus, the medical device system 2 may store episode data in memory for viewing by a physician.

In another example, if the duration of the episode data is 15 minutes, the medical device system 2 may not bypass the decision algorithm 452 such that the decision algorithm 452 is able to determine the likelihood that the episode data is a true or false indication of a heart attack. In this way, the long duration condition may ensure that the medical device system 2 stores episode data for a duration equal to or greater than the long duration threshold. This may be beneficial because episode data having a duration equal to or greater than the long duration threshold may be unlikely to be a false indication of a heart attack, thus warranting a doctor's view of the episode data.

The set of bypass conditions may additionally or alternatively include a short duration condition. When the duration of episode data received by the processing circuit 402 is less than the short duration threshold, the processing circuit 402 may determine that the episode data satisfies the short duration condition. For example, if the short duration threshold is 2 minutes and the duration of episode data received by the processing circuit 402 is 1 second, the processing circuit 402 may determine that the episode data satisfies the short duration condition and bypass the decision algorithm 452. Thus, the medical device system 2 may store episode data in memory for viewing by a physician.

In another example, if the duration of the episode data is 3 seconds, the medical device system 2 may not bypass the decision algorithm 452 such that the decision algorithm 452 is able to determine the likelihood that the episode data is a true or false indication of a heart attack. In this way, the short duration condition may ensure that the medical device system 2 stores episode data that has a duration less than the short duration threshold. This may be beneficial because the doctor may have specifically programmed the asystole detection interval to be relatively short (e.g., 2 seconds or less), because the doctor considers episode data with such intervals to be a clinically significant event, thus warranting the doctor's view of the episode data.

The set of bypass conditions may additionally or alternatively include user input conditions. When the user provides a user input (e.g., actuation of a user interface) that causes the processing circuit 402 to bypass the algorithm during the bypass period, the processing circuit 402 may determine that the episode data satisfies the user input condition. For example, if the user presses a button on the external device 12 associated with the bypass decision algorithm 452, the processing circuitry 402 may determine that the user input condition is met and the bypass decision algorithm 452 continues for a bypass period of time (e.g., a predetermined time range that begins before the user input and ends after the user input). Thus, the medical device system 2 may store episode data in memory for viewing by a physician. This may be beneficial because the user may press a button each time the user experiences a potential heart attack symptom. Accordingly, episode data that occurs within the time frame of the user input (e.g., a few minutes before the user input until a few minutes after the user input) is unlikely to be a false indication of a heart attack, thus ensuring that the physician views the episode data.

The set of bypass conditions may additionally or alternatively include a debilitating condition. The processing circuit 402 may determine that the episode data satisfies the frailty condition when transmission of the episode data for a heart episode occurs within a time window of at least one of a patient falling or exhibiting physical instability (e.g., abnormal stride pattern, post-stance imbalance, increased transition time from standing to sitting, etc.). Such as accelerometers, gyroscopes, and/or the like included in sensor 58 of IMD 10 or external device 12 may be used to detect whether the patient has fallen or exhibited physical instability. For example, accelerometers may be used to monitor variability in stride duration to detect abnormal stride patterns, body stability after standing (e.g., balance), amount of time to sit-to-stand and to sit-to-stand transitions, and the like.

As an example of the processing circuit 402 bypassing the decision algorithm 452, if the beginning of the time window is 30 minutes before a fall or physical instability occurs, the end of the time window is 30 minutes after a fall or physical instability occurs, and the transmission of the episode data for a heart attack occurs 15 minutes after a fall occurs (e.g., detected by an accelerometer of the IMD 10), the processing circuit 402 may determine that the episode data satisfies the debilitation condition and bypass the decision algorithm 452. Thus, the medical device system 2 may store episode data in memory for viewing by a physician.

In another example, if the beginning of the time window is 30 minutes before a fall or physical instability occurs, the end of the time window is 30 minutes after a fall or physical instability occurs, and transmission of the episode data for a heart attack occurs 40 minutes before a fall occurs (e.g., detected by an accelerometer of IMD 10), processing circuitry 402 may not bypass decision algorithm 452 such that decision algorithm 452 can determine the likelihood that the episode data is a true or false indication of a heart attack. In this way, the debilitating condition may ensure that the medical device system 2 stores episode data that occur in a time window of at least one of a patient falling or exhibiting physical instability. This may be beneficial because transmission of episode data within such a time window may be unlikely to be a false indication of a heart attack, thus warranting a doctor's view of the episode data.

The set of bypass conditions may additionally or alternatively include blood pressure conditions. When the transmission of the episode data for the heart episode occurs within a time window in which the patient's blood pressure changes beyond a blood pressure threshold, the processing circuit 402 may determine that the episode data meets the blood pressure condition. For example, an optical sensor may be used to detect whether a change in the patient's blood pressure (e.g., systolic, diastolic, etc.) exceeds a blood pressure threshold. Additionally or alternatively, processing circuitry 402 may bypass decision algorithm 452 based on Pulse Transfer Time (PTT), which may be related to blood pressure, instead of blood pressure, as blood pressure may be difficult to monitor continuously (e.g., using IMD 10).

As an example of the processing circuit 402 bypassing the decision algorithm based on blood pressure, if the blood pressure threshold is 20 millimeters of mercury (mmHg), the change in systolic blood pressure is 40mmHg, the beginning of the time window is 30 minutes before the occurrence of such a change in blood pressure, the end of the time window is 30 minutes after the occurrence of the change in blood pressure, and the transmission of the seizure data of the heart attack occurs 20 minutes after the occurrence of the change in blood pressure, the processing circuit 402 may determine that the seizure data satisfies the blood pressure condition and bypassing the decision algorithm 452. Thus, the medical device system 2 may store episode data in memory for viewing by a physician.

In another example, if the change in systolic pressure is 15mmHg (or some other value less than the blood pressure threshold), the processing circuit 402 may not bypass the decision algorithm 452, such that the decision algorithm 452 is able to determine the likelihood that the episode data is a true or false indication of a heart attack. In this way, the blood pressure conditions may ensure that the medical device system 2 stores episode data that occur within a time window in which changes in the patient's blood pressure (e.g., systolic pressure, diastolic pressure, etc.) exceed a blood pressure threshold. This may be beneficial because transmission of episode data within such a time window may be unlikely to be a false indication of a heart attack, thus warranting a doctor's view of the episode data. It should be appreciated that the above example of the processing circuit 402 bypassing the decision algorithm 452 based on blood pressure may be substantially similar to the example of the processing circuit 402 bypassing the decision algorithm 452 based on PPT because PPT is related to blood pressure.

In some examples, the processing circuit 402 may be configured to weight each bypass condition in the set of bypass conditions to determine the bypass decision algorithm 452. In such examples, the processing circuit 402 may assign a weight to each bypass condition in the set of bypass conditions (e.g., as selected by a clinician, as determined by an algorithm such as a machine learning algorithm executed by the processing circuit 402), and in response to determining that the episode data satisfies one or more of the bypass conditions, calculate an aggregate weight for the one or more bypass conditions satisfied by the episode data. The processing circuit 402 may then determine to bypass the decision algorithm 452 based on the aggregate weights meeting the weight threshold. For example, if the aggregate weight (e.g., 99%) exceeds the weight threshold (e.g., 85%), the processing circuit 402 may bypass the decision algorithm 452 and store the episode data in memory for viewing by the physician.

The set of bypass conditions may additionally or alternatively include ischemic stroke conditions. When the patient previously experienced an ischemic stroke (e.g., stroke of known origin, cryptogenic stroke, etc.), the occurrence of which may be indicated by a user of the system via a user interface or retrieved from an electronic health record, and the episode data received by the processing circuit 402 is the first transmission of the episode data for the heart attack after a certain time interval (e.g., 15 days) has elapsed, the processing circuit 402 may determine that the episode data satisfies the ischemic stroke condition. For example, if the transmission of episode data by IMD 10 to medical device system 2 is the first transmission of episode data after a 15 day time interval, processing circuitry 402 may determine that the episode data satisfies the interval condition and bypass the decision algorithm. Thus, the medical device system 2 may store episode data in memory for viewing by a physician. Conversely, if the transmission of episode data by IMD 10 to medical device system 2 is not the first transmission of episode data after a 15 day time interval has elapsed or the transmission of episode data before a 15 day time interval has elapsed, processing circuitry 402 may not bypass decision algorithm 452 such that decision algorithm 452 is able to determine the likelihood that the episode data is a true or false indication of a heart attack.

The set of bypass conditions may additionally or alternatively include clinician activated conditions. When the clinician provides an input (e.g., actuation of a user interface) that causes the processing circuit 402 to bypass the algorithm during a bypass period, the processing circuit 402 may determine that the episode data satisfies the clinician activation condition. For example, after a clinically significant event, the clinician may program the processing circuit 402 to bypass the decision algorithm 452 for a bypass period (e.g., 3 days after the clinically significant event) such that any episode data transmitted during the bypass period is not decided by the bypass algorithm, but is stored in memory for viewing by the physician. Additionally or alternatively, the clinician may program certain standard thresholds and/or parameters to meet bypass conditions and bypass decision algorithm 452.

The set of bypass conditions may additionally or alternatively include a similarity condition. When the processing circuit 402 determines (e.g., using a machine learning algorithm) that the similarity between the episode data and the previous episode data determined (e.g., by a clinician) as a heart episode exceeds a similarity threshold, the processing circuit 402 may determine that the episode data meets a similarity condition.

In some examples, the bypass condition in the set of bypass conditions may depend on a medical condition of the patient. For example, for a patient experiencing a cryptogenic stroke, the set of bypass conditions may include a time period condition, a frailty condition, and a similarity condition. On the other hand, for patients experiencing syncope, the set of bypass conditions may include a time interval condition, a clinician activation condition, and a blood pressure condition. It should be understood that these examples are for illustration purposes, and that other sets of bypass conditions are contemplated by the present disclosure.

Further, it should be appreciated that any of the conditions described herein may be modified by the clinician to customize the bypass decision algorithm 452. For example, the clinician may select a duration, interval, threshold, event, sensitivity, etc. to customize any of the bypass conditions to suit the clinician's preferences and/or goals. In some examples, computing system 24 may store programming customized by the clinician and automatically customize bypass conditions based on clinician feedback (e.g., for a new patient).

In some examples, the processing circuit 402 may transmit an indication of the one or more bypass conditions satisfied to the clinician. The processing circuit 402 may also transmit a determination of the decision algorithm 452 regarding episode data that satisfies the bypass condition (e.g., a likelihood that the episode data is a true or false indication of a heart attack). In this manner, the clinician may compare the clinician's determination of episode data with the determination of decision algorithm 452 to assess the effectiveness, accuracy, etc. of one or more bypass conditions and/or decision algorithms.

Other exemplary bypass conditions may include the following:

other conditions are used to bypass decision algorithm 452 only when the R-wave amplitude sensed by IMD 10 is above a threshold amplitude of microvolts (e.g., 300 microvolts).

Bypass the decision algorithm 452 or require a very high confidence level before/after a medical intervention or if the patient is not taking medication. For example, after ablation, the physician wants to know if the ablation was successful and if the patient can be stopped from anticoagulation, so a very high sensitivity is required. Also, patients at high risk (e.g., stroke) who do not use anticoagulation require ultra-high sensitivity.

For any automatically detected episodes related to the episodes activated by the patient, the decision algorithm 452 is bypassed (the device definition is that if the automatic detection occurs within 20 minutes prior to activation, it is considered to be related). Previous analysis has shown that related episodes have a higher PPV as a true automatic episode.

Bypass decision algorithm 452 in a hierarchical manner such that there is a high risk of stroke (e.g., higher CHA ₂ DS ₂ Patients with a VASc score) are at lower risk of stroke than patients with a low risk of stroke (e.g., low CHA ₂ DS ₂ Vanc score) is bypassed more frequently. For CHA, for example ₂ DS ₂ Patients with VASc scores of 0-1 bypass the decision algorithm 452 every 1/30 episodes; for CHA ₂ DS ₂ Patients with VASc scores of 2-4 bypass the decision algorithm 452 every 1/15 episodes; for CHA ₂ DS ₂ Patients with VASc scores of > 5 do not bypass decision algorithm 452.

a. The preceding claims are re-usable with CHA ₂ DS ₂ Individual components of the vacc score (congestive heart failure, hypertension, age, diabetes, past stroke/TIA, vascular disease, female sex). For example, since elderly patients are more likely to suffer from AF, they may be older than younger patientsDecision algorithm 452 is bypassed more frequently.

The decision algorithm 452 is bypassed if the AF episode corresponds in time to a decrease in patient activity measured by the device. This may indicate that the patient feels symptoms and may therefore be more indicative of a true AF episode.

For patients with cryptogenic strokes, decision algorithm 452 is bypassed for all AF episode detection.

For the Heart Failure (HF) population, if the patient is in the high risk group (or within days of their first transition to the high risk group), decision algorithm 452 is bypassed. Any seizure detection that occurs at this time may be of greater concern to the clinician.

For the HF population, the decision algorithm 452 is bypassed based on one or more physiological parameters, such as respiratory rate, fluid indicated by impedance or heart rate variability decline (HRV), reduced activity, new AF, rapid rate during AF, etc. As described above, the clinician and/or algorithm may customize the threshold value of any of the bypass conditions to accommodate the particular preferences of the clinician and the personalized needs of the patient.

Decision algorithm 452 was bypassed for the first 3 tests that occurred within 1 week after hospitalization/clinical visit/dialysis/drug change.

For the first 3 PVC detections following ventricular extra-systole (PVC) ablation, decision algorithm 452 is bypassed (as the physician may want to know if the patient continues to have PVC after PVC ablation). Physicians may especially want to know the morphology of the PVC so that they can determine the source of the PVC.

For the first 2 ventricular arrhythmia episodes following QT prolongation or significant QT changes detected within the first 30 minutes, the decision algorithm 452 is bypassed (as QT changes may lead to polymorphic VT, which in turn may lead to sudden cardiac death).

For the different PVC morphology first detected by the device, the decision algorithm 452 is bypassed (the physician may want to know if the patient has polymorphic PVC to determine the location of the origin of the PVC in the heart. It is not desirable that the decision algorithm 452 omits one of the PVC morphologies, especially if that morphology is rare and only happens once a month or so).

If the patient is found to be at high HF risk, the decision algorithm 452 is bypassed for the first 2 ventricular arrhythmia episodes detection during the high risk period, as HF patients are sensitive to ventricular arrhythmias that may lead to cardiac arrest in these patients.

If the patient was hospitalized for an antiarrhythmic drug titration the latest time or if the patient's drug dose changed, the doctor may be programmed to bypass decision algorithm 452 for the first 3 ventricular arrhythmia episodes, as some drug doses may cause arrhythmia and the doctor may not want to miss these episodes.

If the sleep apnea algorithm detects more than 10 sleep apnea events at night, decision algorithm 452 is bypassed for the first 2 AF episodes of the patient during the day. A physician may want to know if frequent sleep apnea causes arrhythmia in the patient.

For ventricular arrhythmia episodes that occur within 1 hour of more than 10 sleep apnea episode detections, decision algorithm 452 is bypassed. Frequent sleep apnea episodes may cause ectopic beats and non-sustained VT during sleep, which makes the patient more susceptible to sudden cardiac death.

If the patient has heart failure or other risk factors, the physician may program the threshold to bypass decision algorithm 452 for arrhythmia detection that occurs within 2 hours of more than 10 sleep apnea episode detections.

If the average ventricular rate during AF (av.v.) is > threshold (threshold programmable by the physician or set), decision algorithm 452 is bypassed.

The decision algorithm 452 is bypassed as long as the patient is at high HF risk (or the decision algorithm 452 is bypassed only for the first heart attack during the period when the patient is at high HF risk). If AF occurs in the middle of HF, the physician may want to adjust the treatment for HF after a high risk alarm.

If the patient is at high risk of COPD, decision algorithm 452 is bypassed for the first 3 arrhythmia detections. (bronchodilators may increase the risk of arrhythmia, and doctors may want to know if patients experience frequent arrhythmias).

If more than 5 sleep apnea events are detected, decision algorithm 452 is bypassed for the first 3 arrhythmia detections that occur within 1 day. Sleep apnea can increase the relative risk of nocturnal paroxysmal AF and SVT.

If the patient exhibits an abnormal (e.g., nocturnal) breathing pattern, the decision algorithm 452 is bypassed for one hour.

It should be understood that the number of events (e.g., episode detection), time periods (e.g., seconds, minutes, days, etc.), and/or the like in the bypass condition are representative and are not intended to be limiting. Accordingly, the present disclosure contemplates other event numbers, time periods, and/or the like.

Fig. 5 is an exemplary technique for bypassing decision algorithm 452 in accordance with the techniques of the present invention. Although primarily described herein in the context of an example in which decision algorithm 452 and bypass module 454 are implemented by computing system 24, the techniques are not so limited. In some examples, one or both of decision algorithm 452 and bypass module 454 may be implemented, in whole or in part, by IMD 10 and/or external device 12.

According to the example of fig. 5, IMD 10 may collect episode data (502) indicative of electrical activity of the heart of patient 4 (e.g., via electrodes 16A, 16B). For example, processing circuitry 50 may store digitized cardiac EGMs and characteristics of EGMs for detecting an arrhythmia episode in memory 56 as episode data for the detected arrhythmia episode. In some examples, processing circuitry 50 stores one or more segments of cardiac EGM data, features derived from cardiac EGM data, and other episode data in response to instructions from external device 12 (e.g., when patient 4 experiences one or more symptoms of an arrhythmia and inputs a command to external device 12 instructing IMD 10 to upload data for analysis by a monitoring center or clinician).

Computing system 24 may receive episode data for episodes stored by a medical device such as IMD 10 via communication circuitry 406 (504). For example, IMD 10 sends digitized cardiac EGMs and other episode data to network 25 for processing by monitoring system 450 of fig. 1. In some examples, processing circuitry 50 of IMD 10 transmits episode data for patient 4 to external device 12 via communication circuitry 54, which then transmits the episode data to computing system 24. The episode data may have been collected by the medical device in response to the medical device detecting an arrhythmia and/or user input directing storage of episode data.

In response to computing system 24 receiving episode data, processing circuitry 402 of the computing system may determine whether to bypass decision algorithm 452 based on satisfaction of one or more bypass conditions in the set of bypass conditions (506). For example, in response to meeting one or more bypass conditions (yes of 506), the processing circuit 402 may bypass the decision algorithm 452, and the processing circuit 402 may store (e.g., in the storage 408) the episode data as a true indication of a heart episode (such as an AF episode) (508).

For example, if the transmission of episode data by IMD 10 to medical device system 2 is the first transmission of episode data during a time period of a particular month (e.g., wubi), processing circuitry 402 may determine that the episode data satisfies the time period conditions and bypass decision algorithm 452. Accordingly, the processing circuit 402 may store episode data in a memory (e.g., storage 408) for viewing by a physician. In another example, if the transmission of episode data is a subsequent transmission of episode data during the period (e.g., a second transmission of episode data), the processing circuit 402 may not bypass the decision algorithm 452.

In some examples, the processing circuit 402 may be configured to weight each bypass condition (e.g., a time period condition, a frailty condition, an implantation condition, etc.) in the set of bypass conditions to determine the bypass decision algorithm 452. In such examples, the processing circuit 402 may assign a weight to each bypass condition in the set of bypass conditions and, in response to determining that the episode data satisfies one or more of the bypass conditions, calculate an aggregate weight for the one or more bypass conditions satisfied by the episode data. The processing circuit 402 may then determine to bypass the decision algorithm 452 based on the aggregate weights meeting the weight threshold. For example, if the aggregate weight (e.g., 99%) exceeds the weight threshold (e.g., 85%), the processing circuit 402 may bypass the decision algorithm 452 and store the episode data in memory for viewing by the physician.

In response to the processing circuit 402 determining that the bypass condition is not met or the aggregate weight does not meet the weight threshold (NO of 506), the processing circuit 402 may not bypass the decision algorithm 452 and the decision algorithm 452 may determine a likelihood that the episode data is a true or false indication of a heart episode (510). The decision algorithm 452 may output, for each of a plurality of arrhythmia type classifications, a value indicating the likelihood that type of arrhythmia occurred at any point in time during the episode. The monitoring system 450 may apply a configurable threshold (e.g., 50%, 75%, 90%, 95%, 99%) to the likelihood value to identify the episode as including one or more arrhythmia types, e.g., based on the likelihood that the classification meets or exceeds the threshold.

In some examples, the techniques of this disclosure include a system comprising means for performing any of the methods described herein. In some examples, the techniques of this disclosure include a computer-readable medium comprising instructions that cause a processing circuit to perform any of the methods described herein.

It should be understood that the various aspects disclosed herein may be combined in different combinations than specifically presented in the specification and drawings. It should also be appreciated that, depending on the example, certain acts or events of any of the processes or methods described herein can be performed in a different order, may be added, combined, or omitted entirely (e.g., not all of the described acts or events may be required to perform the techniques). Additionally, although certain aspects of the present disclosure are described as being performed by a single module, unit, or circuit for clarity, it should be understood that the techniques of the present disclosure may be performed by a combination of units, modules, or circuits associated with, for example, a medical device.

In one or more examples, the techniques described may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions may be stored as one or more instructions or code on a computer-readable medium and executed by a hardware-based processing unit. Computer-readable media may include non-transitory computer-readable media corresponding to tangible media, such as data storage media (e.g., RAM, ROM, EEPROM, flash memory, or any other medium that can be used to store desired program code in the form of instructions or data structures and that can be accessed by a computer).

The instructions may be executed by one or more processors, such as one or more Digital Signal Processors (DSPs), general purpose microprocessors, application Specific Integrated Circuits (ASICs), field programmable logic arrays (FPGAs), or other equivalent integrated or discrete logic circuitry. Thus, the term "processor" or "processing circuit" as used herein may refer to any of the foregoing structure or any other physical structure suitable for implementation of the described techniques. In addition, the present technology may be fully implemented in one or more circuits or logic elements.

The following examples are illustrative of the techniques described herein.

Example 1: a method of monitoring a patient, comprising: receiving, by processing circuitry of the medical device system, episode data for a heart episode; determining, by processing circuitry and based on meeting one or more bypass conditions of a set of bypass conditions, a likelihood that bypass is configured to determine that the episode data is a false indication of the heart episode; and storing, by the processing circuit and in response to bypassing the algorithm, the episode data as a true indication of the heart episode.

Example 2: the method of embodiment 1, wherein the set of bypass conditions includes a time period condition, and wherein the episode data satisfies the time period condition when the episode data received by the processing circuit is a first transmission of episode data for the heart episode for a time period.

Example 3: the method of embodiment 2, wherein the length of the time period is based on the health condition of the patient.

Example 4: the method of any of embodiments 1-3, wherein the set of bypass conditions includes an interval condition, and wherein the episode data satisfies the interval condition when the episode data received by the processing circuit is a first transmission of the episode data of the heart episode after a time interval has elapsed from a previous transmission of the episode data of the heart episode.

Example 5: the method of any of embodiments 1-4, wherein the set of bypass conditions includes an implantation condition, and wherein the episode data satisfies the implantation condition when the episode data received by the processing circuit is one of a first N transmissions of episode data for the heart episode after implantation of an implantable medical device of the medical device system.

Example 6: the method of embodiment 5, wherein the first N transmissions comprise a first ten transmissions of episode data for the heart attack after implantation of the implantable medical device.

Example 7: the method of any of embodiments 1-6, wherein the set of bypass conditions includes a long-duration condition, and wherein the episode data satisfies the long-duration condition when a duration of the episode data for the heart episode received by the processing circuit exceeds a long-duration threshold.

Example 8: the method of any of embodiments 1-7, wherein the set of bypass conditions includes a short duration condition, and wherein the episode data satisfies the short duration condition when a duration of the episode data for the heart episode received by the processing circuit is less than a short duration threshold.

Example 9: the method of any of embodiments 1-8, wherein the set of bypass conditions includes a user input condition, and wherein the episode data satisfies the user input condition when the user provides user input that causes the processing circuit to bypass the algorithm for a bypass period of time.

Example 10: the method of any of embodiments 1-9, wherein the set of bypass conditions comprises a debilitating condition, and wherein the episode data satisfies the debilitating condition when transmission of the episode data for the heart attack occurs within a time window of at least one of the patient falling or exhibiting physical instability.

Example 11: the method of any one of embodiments 1-10, wherein the set of bypass conditions includes a blood pressure condition, and wherein the seizure data satisfies the blood pressure condition when transmission of the seizure data for the heart attack occurs within a time window in which a change in blood pressure of the patient exceeds a blood pressure threshold.

Example 12: the method of any one of embodiments 1 through 11, wherein determining to bypass the algorithm comprises: assigning a weight to each bypass condition in the set of bypass conditions; in response to determining that the episode data satisfies one or more of the bypass conditions, calculating an aggregate weight for the one or more bypass conditions satisfied by the episode data; determining whether the aggregate weight exceeds a weight threshold; and determining to bypass the algorithm based on the aggregate weight exceeding the weight threshold.

Example 13: the method of embodiment 12, wherein the weight assigned to each bypass condition is based on the health of the patient.

Example 14: the method of any one of embodiments 1-13, further comprising storing, by the processing circuitry, an indication of why the processing circuitry determined to bypass the algorithm based on satisfaction of one or more bypass conditions in the set of bypass conditions.

Example 15: a medical device system, comprising: receiving episode data for a heart episode; determining whether to bypass an algorithm configured to determine a likelihood that the episode data is a false indication of the heart episode based on one or more bypass conditions in a set of bypass conditions being met; and in response to bypassing the algorithm, storing the episode data as a true indication of the heart episode.

Example 16: the medical device system of embodiment 15 wherein the set of bypass conditions includes a time period condition, and wherein the episode data satisfies the time period condition when the episode data received by the processing circuit is a first transmission of episode data for a cardiac episode for a time period.

Example 17: the medical device system of embodiment 16, wherein the length of the time period is based on a health condition of the patient.

Example 18: the medical device system of any one of embodiments 15-17, wherein the set of bypass conditions includes an interval condition, and wherein the episode data satisfies the interval condition when the episode data received by the processing circuit is a first transmission of the episode data of the heart attack after a time interval has elapsed from a previous transmission of the episode data of the heart attack.

Example 19: the medical device system of any one of embodiments 15-18, wherein the set of bypass conditions includes an implantation condition, and wherein the episode data received by the processing circuit satisfies the implantation condition when the episode data is one of the first N transmissions of episode data for the heart attack after implantation of an implantable medical device of the medical device system.

Example 20: the medical device system of embodiment 19, wherein the first N transmissions comprise a first ten transmissions of episode data for the heart attack after implantation of the implantable medical device.

Example 21: the medical device system of any one of embodiments 15-20, wherein the set of bypass conditions includes a long-duration condition, and wherein the episode data satisfies the long-duration condition when a duration of the episode data for the heart episode received by the processing circuit exceeds a long-duration threshold.

Example 22: the medical device system of any one of embodiments 15-21, wherein the set of bypass conditions includes a short duration condition, and wherein the episode data satisfies the short duration condition when a duration of the episode data for the heart episode received by the processing circuit is less than a short duration threshold.

Example 23: the medical device system of any one of embodiments 15-22, wherein the set of bypass conditions includes a user input condition, and wherein the episode data satisfies the user input condition when the user provides user input that causes the processing circuit to bypass the algorithm for a bypass period of time.

Example 24: the medical device system of any one of embodiments 15-23, wherein the set of bypass conditions includes a frailty condition, and wherein the seizure data satisfies the frailty condition when transmission of the seizure data of the heart attack occurs within a time window of at least one of the patient falling or exhibiting physical instability.

Example 25: the medical device system of any one of embodiments 15-24, wherein the set of bypass conditions includes a blood pressure condition, and wherein the seizure data satisfies the blood pressure condition when transmission of the seizure data for the heart seizure occurs within a time window in which a change in blood pressure of the patient exceeds a blood pressure threshold.

Example 26: the medical device system of any one of embodiments 15-25, wherein the processing circuit is configured to determine to bypass the algorithm by: assigning a weight to each bypass condition in the set of bypass conditions; in response to determining that the episode data satisfies one or more of the bypass conditions, calculating an aggregate weight for the one or more bypass conditions satisfied by the episode data; determining whether the aggregate weight exceeds a weight threshold; and determining to bypass the algorithm based on the aggregate weight exceeding the weight threshold.

Example 27: the medical device system of embodiment 26, wherein the weight assigned to each bypass condition is based on a health condition of the patient.

Example 28: the medical device system of any one of embodiments 15-27, wherein the processing circuitry is further configured to store an indication of why the processing circuitry determined to bypass the algorithm based on satisfaction of one or more bypass conditions in the set of bypass conditions.

Example 29: a computer-readable medium includes receiving episode data; determining whether to bypass an algorithm configured to determine a likelihood that the episode data is a false indication of a heart episode based on one or more bypass conditions in a set of bypass conditions being met; and in response to bypassing the algorithm, storing the episode data as a true indication of the heart episode.

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

Claim (modification according to treaty 19)

1. A medical device system, the medical device system comprising processing circuitry configured to:

receiving episode data for a heart episode;

determining whether to bypass an algorithm configured to determine a likelihood that the episode data is a false indication of the heart attack based on meeting one or more bypass conditions in a set of bypass conditions, wherein the set of bypass conditions includes a time period condition, and wherein the episode data meets the time period condition when the episode data received by the processing circuit is a first transmission of episode data for the heart attack for a time period; and

In response to bypassing the algorithm, the episode data is stored as a true indication of the heart episode.

2. The medical device system of claim 1, wherein the length of the time period is based on a health condition of the patient.

3. The medical device system of claim 1, wherein the set of bypass conditions includes an interval condition, and wherein the episode data satisfies the interval condition when the episode data received by the processing circuit is a first transmission of the episode data of the heart attack after a time interval has elapsed from a previous transmission of the episode data of the heart attack.

4. The medical device system of claim 1, wherein the set of bypass conditions includes an implantation condition, and wherein the episode data satisfies the implantation condition when the episode data received by the processing circuit is one of a first N transmissions of episode data for the heart attack after implantation of an implantable medical device of the medical device system.

5. The medical device system of claim 4, wherein the first N transmissions comprise a first ten transmissions of episode data for the heart attack after implantation of the implantable medical device.

6. The medical device system of claim 1, wherein the set of bypass conditions includes a long-duration condition, and wherein the episode data satisfies the long-duration condition when a duration of the episode data for the heart episode received by the processing circuit exceeds a long-duration threshold.

7. The medical device system of claim 1, wherein the set of bypass conditions includes a short duration condition, and wherein the episode data satisfies the short duration condition when a duration of the episode data for the heart episode received by the processing circuit is less than a short duration threshold.

8. The medical device system of claim 1, wherein the set of bypass conditions includes a user input condition, and wherein the episode data satisfies the user input condition when the user provides user input that causes the processing circuit to bypass the algorithm for a bypass period of time.

9. The medical device system of claim 1, wherein the set of bypass conditions comprises a debilitating condition, and wherein the episode data satisfies the debilitating condition when transmission of the episode data for the heart attack occurs within a time window of at least one of the patient falling or exhibiting physical instability.

10. The medical device system of claim 1, wherein the set of bypass conditions includes a blood pressure condition, and wherein the seizure data satisfies the blood pressure condition when transmission of the seizure data for the heart attack occurs within a time window in which a change in blood pressure of the patient exceeds a blood pressure threshold.

11. The medical device system of claim 1, wherein the processing circuit is configured to determine to bypass the algorithm by:

a weight is assigned to each bypass condition in the set of bypass conditions,

in response to determining that the episode data satisfies one or more of the bypass conditions, calculating an aggregate weight for the one or more bypass conditions satisfied by the episode data,

determining whether the aggregate weight exceeds a weight threshold

Bypassing the algorithm is determined based on the aggregate weight exceeding the weight threshold.

12. The medical device system of claim 11, wherein the weight assigned to each bypass condition is based on a health condition of the patient.

13. A method of monitoring a patient, the method comprising:

receiving, by processing circuitry of the medical device system, episode data for a heart episode;

Determining, by processing circuitry and based on meeting one or more bypass conditions of a set of bypass conditions, an algorithm that bypasses a likelihood that the episode data is a false indication of the heart attack, wherein the set of bypass conditions includes a time period condition, and wherein the episode data meets the time period condition when the episode data received by the processing circuitry is a first transmission of episode data for the heart attack for a time period; and

the episode data is stored by the processing circuit as a true indication of the heart attack and in response to bypassing the algorithm.

14. A computer-readable medium comprising instructions that, when executed, cause a processing circuit to:

receiving episode data;

determining whether to bypass an algorithm configured to determine a likelihood that the episode data is a false indication of a heart attack based on meeting one or more bypass conditions in a set of bypass conditions, wherein the set of bypass conditions includes a time period condition, and wherein the episode data meets the time period condition when the episode data received by the processing circuit is a first transmission of episode data for the heart attack for a time period; and

Claims

receiving episode data for a heart episode;

determining whether to bypass an algorithm configured to determine a likelihood that the episode data is a false indication of the heart episode based on one or more bypass conditions in a set of bypass conditions being met; and

2. The medical device system of claim 1, wherein the set of bypass conditions includes a time period condition, and wherein the episode data satisfies the time period condition when the episode data received by the processing circuit is a first transmission of episode data for a cardiac episode for a time period.

3. The medical device system of claim 2, wherein the length of the time period is based on a health condition of the patient.

4. The medical device system of claim 1, wherein the set of bypass conditions includes an interval condition, and wherein the episode data satisfies the interval condition when the episode data received by the processing circuit is a first transmission of the episode data of the heart attack after a time interval has elapsed from a previous transmission of the episode data of the heart attack.

5. The medical device system of claim 1, wherein the set of bypass conditions includes an implantation condition, and wherein the episode data satisfies the implantation condition when the episode data received by the processing circuit is one of a first N transmissions of episode data for the heart attack after implantation of an implantable medical device of the medical device system.

6. The medical device system of claim 5, wherein the first N transmissions comprise a first ten transmissions of episode data for the heart attack after implantation of the implantable medical device.

7. The medical device system of claim 1, wherein the set of bypass conditions includes a long-duration condition, and wherein the episode data satisfies the long-duration condition when a duration of the episode data for the heart episode received by the processing circuit exceeds a long-duration threshold.

8. The medical device system of claim 1, wherein the set of bypass conditions includes a short duration condition, and wherein the episode data satisfies the short duration condition when a duration of the episode data for the heart episode received by the processing circuit is less than a short duration threshold.

9. The medical device system of claim 1, wherein the set of bypass conditions includes a user input condition, and wherein the episode data satisfies the user input condition when the user provides user input that causes the processing circuit to bypass the algorithm for a bypass period of time.

10. The medical device system of claim 1, wherein the set of bypass conditions comprises a debilitating condition, and wherein the episode data satisfies the debilitating condition when transmission of the episode data for the heart attack occurs within a time window of at least one of the patient falling or exhibiting physical instability.

11. The medical device system of claim 1, wherein the set of bypass conditions includes a blood pressure condition, and wherein the seizure data satisfies the blood pressure condition when transmission of the seizure data for the heart attack occurs within a time window in which a change in blood pressure of the patient exceeds a blood pressure threshold.

12. The medical device system of claim 1, wherein the processing circuit is configured to determine to bypass the algorithm by:

a weight is assigned to each bypass condition in the set of bypass conditions,

determining whether the aggregate weight exceeds a weight threshold

13. The medical device system of claim 12, wherein the weight assigned to each bypass condition is based on a health condition of the patient.

14. A method of monitoring a patient, the method comprising:

determining, by processing circuitry and based on meeting one or more bypass conditions of a set of bypass conditions, a likelihood that bypass is configured to determine that the episode data is a false indication of the heart episode; and

15. A computer-readable medium comprising instructions that, when executed, cause a processing circuit to:

receiving episode data;

determining whether to bypass an algorithm configured to determine a likelihood that the episode data is a false indication of a heart episode based on one or more bypass conditions in a set of bypass conditions being met; and