Computing system configured to facilitate multi-party determination of heart attack

Abstract

Techniques for facilitating multi-party determination of cardiac attacks are described. An example system includes a memory storing instructions and processing circuitry configured to execute those instructions to receive seizure data for a cardiac seizure from a medical device. The processing circuitry is configured to determine a region of the seizure data based on an input from a primary determiner and display a notification to a secondary determiner. The processing circuitry is further configured to display the region of seizure data to the secondary determiner, and to receive and transmit an input from the secondary determiner.

Description

[0001] This application claims the benefit of U.S. Provisional Patent Application Serial No. 63 / 371,482, filed on August 15, 2022, entitled "COMPUTING SYSTEM CONFIGURED TO FACILITATE MULTI-PARTYADJUDICATION OF CARDIAC EPISODES," which is hereby incorporated by reference in its entirety. Technical Field

[0002] The present disclosure relates generally to medical devices, and more particularly to review and determination of episode data collected by medical devices. Background Art

[0003] Medical devices can be used to monitor the physiological signals of patients. Such devices include implantable or wearable medical devices, and a variety of wearable health or fitness tracking devices. For example, some medical devices are configured to sense electrocardiogram (EGM) signals, such as electrocardiogram (ECG) signals, which indicate the electrical activity of the heart via electrodes. Some medical devices are configured to detect the occurrence of arrhythmias based on cardiac EGMs and in some cases based on data from additional sensors, commonly referred to as attacks. Example arrhythmia types include cardiac arrest (or pause), bradycardia, ventricular tachycardia, supraventricular tachycardia, wide QRS complex tachycardia, atrial fibrillation, atrial flutter, ventricular fibrillation, atrioventricular block, ventricular premature contraction and atrial premature contraction. The medical device can store the cardiac EGM and other data collected during the time period including the attack as attack data. The medical device can also store the attack data for a period of time in response to user input (e.g., input from a patient indicating that an arrhythmia attack may occur). Such acute health events involving cardiac arrhythmias may be associated with adverse treatment outcomes (eg, death) for the patients.

[0004] The computing system may obtain episode data from the medical device to allow a clinician or other user to review the episode. The clinician may diagnose the patient's medical condition based on the occurrence of an arrhythmia during the identified episode. In some examples, one or more decision clinicians or other decision makers may review the episode data to annotate the episode, including determining whether an arrhythmia detected by the medical device actually occurred, to prioritize the episode, and to generate a report for further review by a nursing clinician who assigns a medical device to the patient or is otherwise responsible for the care of a particular patient. Summary of the invention

[0005] In general, the present disclosure describes techniques for simplifying the determination of a heart attack between an adjudicator, such as a primary adjudicator and a secondary adjudicator. Heart attack data may be obtained from a medical device that measures and stores physiological signals, which may then be obtained by a computing system. For example, a medical device configured to sense EGM signals may detect a potential arrhythmic attack in a patient. The determination of a heart attack may include a human adjudicator reviewing attack data, such as one or more segments of cardiac EGM data, e.g., ECG data, stored on a display of a computing device by the medical device in response to detecting an attack or in response to user input. Based on the adjudicator's expertise in reviewing the attack data and determining a heart attack based on such data, the adjudicator may determine whether one or more arrhythmias or various types of other attacks have occurred, in some cases confirming, denying, or supplementing the attack detection by the medical device.

[0006] In some cases, a heart attack is determined by multiple determiners. For example, a primary determiner, such as a nurse, a nurse practitioner (NP), or an electrophysiologist (EP), may perform an initial determination of the attack data, and only perform an initial determination of the attack data in the case of some attacks. As an example, if the primary determiner is confident in the determination, the determination may be performed only once. If the primary determiner is unsure about a particular attack, a secondary determiner, such as a cardiologist, who may be more experienced, may be asked to review the attack and decide whether the attack detected by the medical device occurred.

[0007] However, the current workflow for a primary decider to send an ECG / EGM of interest to a secondary decider is inefficient and highly manual. In some cases, the current workflow involves printing out several pages of data and waiting outside the secondary decider's door or interrupting a meeting to get the secondary decider's attention and approval, sometimes multiple times a day. In other cases, the secondary decider may send an email via an unsecured messaging platform (e.g., WhatsApp). TM ) to review the ECG / EGM of interest, or the secondary determiner may need to access the patient's electronic health record (EHR) to review it. These interruptions and waiting periods are problematic for both the primary determiner and the secondary determiner. The highly manual and inefficient method described for sending the ECG / EGM of interest to the secondary determiner may force the primary determiner to neglect other important work-related responsibilities. For example, if the primary determiner needs to wait outside the secondary determiner's door for an extended period of time to share ECG / EGM data, the primary determiner may be unable to care for other patients.

[0008] Additionally, current methods for sharing ECG / EGM data may involve printing or saving an entire data collection session, which is relatively long (e.g., several minutes of data) when compared to the amount of data required to make a diagnosis (e.g., 20 seconds of data). Where printed reports are used to send ECG / EGM data, the secondary decider must flip through several pages of data to find an area of ​​interest and make a diagnosis, and where the data is uploaded to the patient's EHR, the secondary decider may need to scroll through all of the data for the entire episode record instead of the important portions. Since an excessive amount of data is transmitted to the secondary decider, the secondary decider's evaluation may be less efficient than if only the critical or most useful portions of the episode were displayed.

[0009] The techniques of the present disclosure described herein can provide specific improvements in the field of arrhythmia classification and determination. For example, a computing system configured in accordance with the present disclosure may include an operating server and one or more computing devices to improve the efficiency of review and reduce the overall burden of episode review. In examples where the techniques of the present disclosure involve accurately locating specific portions of data to be reviewed, the chances of misdiagnosing patients due to the burden of screening large amounts of data can be reduced. In addition, determiners may be able to analyze more episode data and therefore provide better care for more patients. As a result, patients may be more likely to receive appropriate care in a timely manner, which can lead to better patient treatment outcomes.

[0010] The medical device system may include a remote patient monitoring system. The remote patient monitoring system may notify a primary determiner of the episode data and associated diagnosis (e.g., cardiac arrest, atrial fibrillation, tachycardia). Based on the primary determiner's experience and confidence in the diagnosis, the primary determiner may determine that the episode data should be reviewed by a secondary determiner. According to the technology of the present disclosure, the system may use the remote patient monitoring system to send episode data to a secondary determiner based on input from the primary determiner.

[0011] In one example, the primary determiner may send the secondary determiner important portions of the episode data and questions. The questions may be typed by the primary determiner, or the primary determiner may select one or more questions from a list of predefined questions to further simplify the determination process. The primary determiner may also be prompted to assign a priority to the message sent to the secondary determiner to indicate the level of urgency, thereby informing the secondary determiner as to which data to examine first.

[0012] In another example, an artificial intelligence (AI) or machine learning (ML) model can be used to select the portion of the episode data that is most likely to contain the patient state being examined (e.g., atrial fibrillation or any other arrhythmia). Additionally, an AI or ML model can be used to select question options presented to the primary decider from a longer list to simplify question selection.

[0013] In another example, the model may be used to provide a confidence level regarding the detection of a cardiac event by a medical device. For example, a confidence output in the form of a percentage may be provided, such as 85% confidence indicating that an atrial fibrillation episode has occurred.

[0014] In some examples, the secondary determiner can receive a notification on his / her computing device (e.g., a smart phone) and can then access the episode data via a secure application or secure web browser. The secondary determiner can then determine whether a worrisome cardiac event (e.g., a tachyarrhythmia) has occurred and type or select an answer to the primary determiner's question from a drop-down menu. The secondary determiner's opinion can then be sent to a database and saved. By simplifying the communication process between the primary determiner and the secondary determiner, the technology of the present disclosure can facilitate efficient verification of suspected health episodes. Therefore, patient treatment outcomes can be improved.

[0015] In one example, a computing system is configured to execute instructions to: receive, at a server, episode data of a heart attack from a medical device, the computing system including a memory storing instructions and processing circuitry of one or more devices, the computing system including a server, a computing device of a primary determiner, and a computing device of a secondary determiner; identify, by the server, an area of ​​the episode data; provide a notification to the secondary determiner via the computing device of the secondary determiner; in response to the notification, the secondary determiner interacts with the computing device of the secondary determiner, and in response to the interaction, displays the area of ​​the episode data on a display of the computing device of the secondary determiner; receive input by the computing device of the secondary determiner; and transmit, by the computing device of the secondary determiner, to the server in response to the episode data, the input received from the secondary determiner.

[0016] In another example, a method of operating a computing system to facilitate adjudicating a cardiac event between a primary determiner and a secondary determiner includes: receiving, at a server, episode data of a cardiac attack from a medical device; identifying, by the server, an area of ​​the episode data; providing a notification to the secondary determiner via a computing device of the secondary determiner; in response to the notification, the secondary determiner interacting with the computing device of the secondary determiner, and in response to the interaction, displaying the area of ​​the episode data on a display of the computing device of the secondary determiner; receiving, by the computing device of the secondary determiner, input; and transmitting, by the computing device of the secondary determiner to the server, in response to the episode data, the input received from the secondary determiner.

[0017] In another example, a non-transitory computer-readable storage medium includes a program storing instructions that, when executed by processing circuitry of a computing system including a server, a computing device of a primary determiner, and a computing device of a secondary determiner, cause the processing circuitry to perform a method including: receiving, at the server, episode data of a heart attack from a medical device; identifying, by the server, an area of ​​the episode data; providing a notification to the secondary determiner via the computing device of the secondary determiner; in response to the notification, the secondary determiner interacting with the computing device of the secondary determiner, and in response to the interaction, displaying the area of ​​the episode data on a display of the computing device of the secondary determiner; receiving input by the computing device of the secondary determiner; and transmitting, by the computing device of the secondary determiner to the server in response to the episode data, the input received from the secondary determiner.

[0018] The present disclosure is intended to provide an overview of the subject matter described in the present disclosure. It is not intended to provide an exclusive or exhaustive explanation of the devices and methods described in detail in the following figures and descriptions. Further details of one or more examples are set forth in the following figures and descriptions. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a block diagram illustrating an example system configured to transmit physiological monitoring data to multiple computing devices in accordance with one or more of the techniques of this disclosure.

[0020] Figure 2 is a flow chart illustrating an example of a technique for heart attack determination, including operation of a software interface accessible by a primary determiner and a telephone application accessible by a clinician, and some examples of information that the software interface and the telephone application may require as input from both determiners.

[0021] Figure 3 is a diagram illustrating an example of cardiac EGM data of a heart attack.

[0022] Figure 4 An example user interface illustrating a magnified area including episode data.

[0023] Figure 5 is a conceptual diagram illustrating an example software interface page for a primary determiner to input information related to episode data.

[0024] Figure 6 is a conceptual diagram illustrating an example interface for a secondary decider on which the secondary decider's analysis may be performed.

[0025] Fig. 7Ais a conceptual diagram illustrating an example interface for a primary decider to make an initial decision based on episode data and decide whether to send the episode data to a secondary decider.

[0026] Figure 7B is exemplified by Fig. 7A Conceptual image of the pop-up interface resulting from a selection in the interface.

[0027] Figure 8 is a conceptual diagram illustrating an example interface and process by which a secondary determiner receives notification that new determined heart attack data is needed and securely accesses a computing device.

[0028] Fig. 9 is a conceptual diagram illustrating an example user interface for a secondary adjudicator to analyze heart attack data and perform an assessment.

[0029] Like reference numerals refer to like elements throughout the drawings and the specification. DETAILED DESCRIPTION

[0030] Various types of implantable and external medical devices detect heart attacks based on sensed cardiac EGM or ECG (hereinafter referred to as "cardiac EGM") and in some cases other physiological parameters. External devices that can be used to non-invasively sense and monitor cardiac EGM include wearable devices, such as patches, watches, or necklaces, having electrodes configured to contact the patient's skin. An example of a wearable physiological monitor configured to sense cardiac EGM is the SEEQ, commercially available from Medtronic Inc. of Dublin, Ireland. TM Mobile cardiac telemetry systems. These external devices facilitate relatively long-term monitoring of patients during normal daily activities and can periodically transmit collected data, such as detected arrhythmia episodes, to a remote patient monitoring system, such as Medtronic CareLink TM network.

[0031] Implantable medical devices (IMDs) also sense and monitor cardiac EGMs and detect arrhythmia episodes. Example IMDs that monitor cardiac EGMs include pacemakers and implantable cardioverter-defibrillators, which may be coupled to intravascular or extravascular leads, and pacemakers having a housing configured for implantation within the heart, which may be leadless. Some IMDs that do not provide therapy (e.g., implantable patient monitors) sense cardiac EGMs. An example of such an IMD is the Reveal LINQ II , commercially available from Medtronic. TM or LINQ II TMInsertable cardiac monitors (ICMs), which are inserted subcutaneously. Such IMDs can facilitate relatively long-term monitoring of patients during normal daily activities and can periodically transmit collected data, such as the onset of detected arrhythmia episodes, to a remote patient monitoring system, such as the Medtronic CareLink TM Although the techniques of the present disclosure are primarily discussed with respect to cardiac IMDs and cardiac health, these techniques may be applied to other devices, including other IMDs and / or wearable devices that may be used to monitor other physiological parameters (e.g., non-cardiac) indicative of patient health.

[0032] Such a web service may support centralized or clinical-based arrhythmia episode review, annotation, and reporting by uploading episode data from medical devices and distributing the episode data to various users. Episode data may include the reason why the medical device recorded the episode data, such as whether the episode was "device triggered" or "patient triggered", "device triggered" meaning that the medical device recorded the episode data in response to the detection of an arrhythmia, and "patient triggered" meaning that the medical device recorded the episode data in response to input from the patient or another user. Episode data may include an indication of one or more arrhythmias detected by the medical device during the episode, such as which detection triggered the medical device to record the episode data. Episode data may also include data collected by the medical device during a time period, which time period includes time before and after the moment when the medical device determines that one or more arrhythmias have occurred. Episode data may include a digitized cardiac EGM during the time period, a heart rate or other parameter derived from the EGM during the time period, and any other physiological parameter data collected by the medical device during the time period. In some cases, although the medical device collected episode data in response to detecting one or more arrhythmias, the review process may determine that the medical device erroneously detected one or more of the arrhythmias in the episode.

[0033] The IMD can interact with other devices. The IMD can communicate with external devices such as smart phones, and the external devices can communicate with a remote patient monitoring system. Additionally or alternatively, the IMD can communicate with a remote patient monitoring system, and the remote patient monitoring system can communicate with a computing device or other external devices. One or more servers (e.g., a cloud computing system) with storage and processing circuits can implement a remote patient monitoring system and be used to analyze data uploaded by the IMD. The data stored by the patient monitoring system can be accessed by a computing device and displayed to a primary determiner via a user interface. The primary determiner can then perform an initial determination of a cardiac event.

[0034] In some examples, the primary determiner may be confident in the determination, in which case the determination process may end.

[0035] In other examples, the primary determiner may not have confidence in the determination and may decide to request a secondary determiner to perform the secondary determination. In this case, the primary determiner can use the remote patient monitoring interface to select a portion of the episode data to send to the secondary determiner. The primary determiner can also choose to ask questions that will be sent along with the episode data. In some examples, the primary determiner can be assisted by an AI or ML model in making these selections.

[0036] Figure 1 is a block diagram illustrating an example computing system 2 that is configured to implement the disclosed techniques for facilitating multi-party determination of a heart attack. Figure 1 In the example shown, system 2 may include IMD 10 in communication with external device 12 and access point 90. External device 12 and access point 90 may also be in communication with network 92, which is in communication with server 94 and computing devices 100A-100N (collectively, "computing devices 100").

[0037] IMD 10 may be implanted in a patient. IMD 10 may correspond to an ICM or other IMD, such as other implantable monitors, implantable pacemakers, defibrillators, neurostimulators, or substance delivery devices. In some examples, system 2 may include multiple IMDs 10 implanted in multiple patients. Additionally or alternatively, to including IMD 10, system 2 may include an external medical device or any type of device configured to store attack data, for example, in response to detecting a heart attack in a patient.

[0038] System 2 may include external device 12, access point 90, network 92, server 94, and one or more other computing devices 100A-100N, which may be interconnected and may communicate with each other via network 92. External device 12 is a computing device configured for wireless communication with IMD 10. External device 12 may be configured to communicate with server 94 via network 92. External device 12 may take the form of a tablet or smart phone. In some examples, external device 12 may provide a user interface and allow a user to interact with IMD 10. In some examples, external device 12 may be used as a programmer for IMD 10. External device 12 may be a dedicated device for interacting with IMD 10, or may be a general-purpose device configured with software for interacting with IMD 10. The external device may be a smart phone or other computing device of a patient in which an IMD is implanted, or may be a tablet or other computing device used by a clinician to interact with the IMD in a clinic.

[0039] Although Figure 1Although not illustrated in the figures, the IMD 10 may include electrodes and other sensors to sense physiological signals, and may collect and store sensed physiological data based on these signals and detect events based on the data. Although the present disclosure primarily discusses the sensing device as an implantable medical device IMD 10, in some cases, the sensing device may be implemented as an external medical device or a wearable device rather than an IMD. Therefore, the techniques discussed herein may also be practiced by an external medical device or a wearable device, and the functionality attributed to the IMD 10 may be practiced by an external medical device or a wearable device and still fall within the scope of the present disclosure.

[0040] The external device 12 can be used to retrieve data from the IMD 10 and can transmit the data to the server 94 via the network 92. The retrieved data may include values ​​of physiological parameters measured by the IMD 10, indications of the onset of an arrhythmia or other disease detected by the IMD 10, episode data of the episode collected, and other physiological signals recorded by the IMD 10. The episode data may include EGM segments recorded by the IMD 10, for example, because the IMD 10 determines that the onset of an arrhythmia or another disease occurs during the segment, or in response to a request to record a segment from a patient or another user. The access point 90 can be configured to similarly facilitate communication between the IMD 10 and the server 94, but in some examples it is not necessary to include a user interface. The access point 90 may include a device connected to the network 92 via any of a variety of connections, such as telephone dial-up, digital subscriber line (DSL), or cable modem connections. In other examples, the access point 90 may be connected to the network 92 by different forms of connection, including wired connections or wireless connections. In some examples, access point 90 may be a user device, such as a tablet or smartphone, that may be co-located with the patient.

[0041] Server 94 may include a computing device configured to allow a user to interact with IMD 10 or data collected from IMD 10 via network 92. In some cases, server 94 may be configured to provide a secure storage site for data that has been collected from IMD 10 and / or external device 12. In some cases, server 94 may be configured to provide a cloud computing system. In some cases, server 94 may compile data in a web page or other document via computing device 100 for viewing by a trained professional such as a seizure determiner or other clinician. Figure 1 One or more aspects of the illustrated system may be used with the Medtronic CareLink TM It is implemented by the general network technologies and functions similar to those provided by Network.

[0042] In some examples, one or more of computing devices 100 may be a personal computer, tablet computer, smart phone, or other computing device. A clinician may access data collected by IMD 10 via computing device 100, such as when a patient is between clinician visits, to check on the status of a medical condition. Additionally, a decision maker may access data collected by IMD 10 via computing devices 100 to make a decision on an episode, according to one or more techniques described herein. Computing device 100, external device 12, and access point 90 may be configured to communicate with the patient via the computing device 100. Low Energy (BLE) or other wireless communication protocols to communicate with IMD 10 and with each other.

[0043] In by Figure 1 In the example shown, server 94 includes, for example, a storage device 96 and processing circuitry 98 for storing data retrieved from IMD 10. Figure 1 , but any of the computing devices in computing device 100 may similarly include a storage device and a processing circuit. Processing circuit 98 may include one or more processors configured to implement functions and / or process instructions for execution within server 94. For example, processing circuit 98 may be capable of processing instructions stored in storage device 96. Processing circuit 98 may include, for example, a microprocessor, 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, or a combination of any of the foregoing devices or circuits. Therefore, processing circuit 98 may include any suitable structure, whether hardware, software, firmware, or any combination thereof, to perform the functions attributed to processing circuit 98 herein. Processing circuit 98 of server 94 and / or processing circuit of computing device 100 may implement any of the techniques described herein for determining a heart attack.

[0044] Storage device 96 may include a computer-readable storage medium or a computer-readable storage device. In some examples, memory 96 includes one or more of short-term memory or long-term memory. Storage device 96 may include, for example, a random access memory (RAM), a dynamic random access memory (DRAM), a static random access memory (SRAM), a magnetic disk, an optical disk, a flash memory, or an erasable programmable read-only memory (EPROM) or an electrically erasable programmable read-only memory (EEPROM). In some examples, storage device 96 is used to store data indicating instructions for execution by processing circuit 98.

[0045] The disclosed techniques may provide a simplified step-by-step system, in some cases starting with a software interface provided by processing circuitry 98 of server 94 via one of computing devices 100, sending the EGM in question to computing device 100, and storing the results in storage device 96. The system will focus on ease of use and may include AI features for nurses to send EGMs to cardiologists. This includes: (1) an additional software menu provided by processing circuitry 98 of server 94 that allows the nurse to select which EGM episodes to send to one or more cardiologists in a list of cardiologists, and which questions to ask, from a predefined list or an open list; (2) the enlarged region of interest of the EGM based on nurse input or AI decision is sent to a phone-based / tablet-based application available to the cardiologist via another computing device 100 that obtains the alert; and the cardiologist logs into the application and is given a list view of all indicated episodes in which the cardiologist can click once to see the enlarged region of interest and answer questions. These results are sent back to server 94 and automatically stored for the nurse to see and read. Alert notifications are also sent to server 94. In some cases, the magnified regions of interest can be relatively short data selections (e.g., data corresponding to 10 second readings) selected from longer data readings (e.g., data corresponding to 15 minute readings). These magnified regions of interest can be determined by a nurse or AI decision based on analysis of the episode data, e.g., the entire episode data. This identification of regions of interest is advantageous because the cardiologist is able to view all relevant data on a phone or tablet screen without scrolling through excessive amounts of data. Thus, the cardiologist is able to analyze the data more efficiently and effectively.

[0046] Figure 2 is a flow chart illustrating an example of a technique for heart attack determination, including operation of a software interface accessible by a primary determiner and a telephone application accessible by a clinician, and some examples of information that the software interface and the telephone application may require as input from both determiners. Figure 2 The example may be composed of two computing devices (e.g., Figure 1 A process executed by a computing device 100). Figure 2Each box shown in can be associated with a different interface screen presented by the corresponding computing device. Input (such as clicks, etc.) from the user can be moved to the screen, and the opportunity for additional input (e.g., text fields) can be provided. In some examples, the server 94 can provide a software interface to visualize the patient's waveform, and save the clinician's notes about the patient. The above-mentioned waveforms and clinician's notes can be accessed by a primary determiner via one of the computing devices 100, and another computing device associated with the secondary determiner can execute a mobile-based application (for both phones and tablets) that can be downloaded on the clinician's phone and can send notifications.

[0047] The CareLink TM / Techniques performed by software interface 210, and techniques performed by phone application 220 may be performed by a second computing device of computing device 100. TM The techniques performed by the software interface 210 may include the execution of instructions by the processing circuitry of the first computing device and / or the processing circuitry 98 of the server 94. The techniques performed by the phone application 220 may include the execution of instructions by the processing circuitry of the second computing device and / or the processing circuitry 98 of the server 94.

[0048] CareLink TM / Software interface 210 can represent technology involving a first decision maker (e.g., a caregiver, a doctor, a paramedic, a technician, or a specialist). In some examples, the first decision maker can interact with CareLink by interacting with the first computing device in computing device 100. TM / Software interface communication. Tactile and visual sensors (e.g., cameras, tactile screens, buttons, and accelerometers) can receive the actions of the first determiner from the sensor as input or input data. The input data can be sent to CareLink TM / Software interface 210 is used for further analysis.

[0049] CareLink TM The software interface 210 may receive an indication from the primary determiner that the EGM should be reviewed by the secondary determiner (212). The indication that the EGM should be reviewed may include the primary determiner selecting an image, text, or icon indicating his / her intent to submit one or more EGMs to the secondary determiner for review. In some examples, to indicate that one or more EGMs should be reviewed, the CareLink TM / The software interface 210 may allow a user (eg, a primary determiner) to capture an image or upload a data file representing EGM measurements. CareLink TM / The software interface 210 may allow a user to select an area of ​​the EGM using either a manual 214A technique or an automatic 216A technique to indicate that the EGM is ready for review.

[0050] In some examples, manual 214A techniques may be used to select the EGM. For example, via a mouse or touch screen, CareLink TM The software interface may receive a selection of an area of ​​the EGM from the primary decision maker (222). The primary decision maker may use a mouse or a touch screen to select an area of ​​the EGM, i.e., select an area of ​​the EGM displayed on one of the computing devices 100A-100N. The selection may include touching the touch screen and dragging an area of ​​the EGM and releasing at the edge of the area.

[0051] In some cases, the primary determiner may choose to TM The primary decider may manually type questions about the event data into an input form of the software interface 210. In some examples, the primary decider may select from a list of AI-generated questions based on the event data and the specific arrhythmia detected.

[0052] In some examples, additionally or alternatively, automatic 216A techniques may be used to determine areas of the EGM for review. For example, CareLink TM The software interface may be configured to determine, using an AI (e.g., an ML model) a region of the EGM based on the portion most likely to include an arrhythmia (232). The AI ​​may compare and weight multiple inputs based on multiple regions of the EGM to generate a cost function. The AI ​​may minimize the cost function to arrive at a region of the EGM to select. The AI ​​may be configured to run on the server 94 and / or computing devices 100A-100N.

[0053] In some examples, the manual technique may switch to the automated technique 216B, and the automated technique may switch to the manual technique 214B. For example, after the primary determiner selects a region for the EGM, the primary determiner may request a CareLink TM / software interface to help generate questions for clinicians. Alternatively, after the AI ​​selects the parts of the EGM, the primary decider can TM / manually write the question into the input form of the software interface. In some examples, the primary determiner can choose to manually select the area of ​​the EGM and can also enter the question in the CareLink TM / manually write the question in the input form of the software interface. Alternatively, the primary determiner can decide to let the AI ​​select the area of ​​the EGM, and can also decide to manually write the question in the input form of the interface.

[0054] When the interface is configured for manual techniques, CareLink TM The software interface may be configured to receive input questions from the primary determiner for the secondary determiner (224). In some examples, the input questions may include questions manually entered into an input box of an input form. The input questions may include text or written characters for review by the secondary determiner.

[0055] When the interface is configured for automated technology, CareLink TM The software interface may be configured to receive a selection of input questions from the primary determiner for the secondary determiner (234). The selection may include selecting a question to be input by CareLink TM / Software interface using AI generated suggested questions. In some examples, selection may include highlighting text, selecting a checkbox, selecting a link, or otherwise providing input indicating the primary determiner's intent to select a question.

[0056] Whether the primary adjudicator uses manual or automated technology, CareLink TM The software interface may be configured to receive a selection from the primary determiner indicating the identity of the secondary determiner 219. For example, the primary determiner may select the identity of the secondary determiner by entering an email, selecting a name, selecting a contact, or providing another type of input indicating the primary determiner's intent to identify the secondary determiner.

[0057] Identifying the secondary arbitrator may cause the phone application 211 to execute instructions on one or more computing devices 100A-100N. The phone application 211 may be configured to display a notification (241). In some examples, the notification may be displayed on one or more of the computing devices 100A-100N based on the identification of the secondary arbitrator by the primary arbitrator.

[0058] Phone application 211 may also be configured to display an area of ​​the EGM in the main view (243). The display may include presenting an image of the area of ​​the EGM on a screen, display, or touch screen or computing device. The computing device may include a computing device in computing devices 100A-100N.

[0059] The phone application 211 can be configured to display input questions to the secondary adjudicator (244). In some examples, displaying the input questions can include displaying input questions received from the primary adjudicator. For example, the questions received or selected from the primary adjudicator can correspond to the questions displayed to the secondary adjudicator.

[0060] The phone application 211 may be configured to receive input from the secondary adjudicator as a response (245). In some examples, the response may include observations, comments, and direct responses to the input question. The phone application 211 may receive input from one of the computing devices 100A-100N via a touch screen, keyboard, voice-to-text, or another user interface.

[0061] In various examples, the phone application 211 can be configured to receive an indication from the secondary adjudicator to send (246). The indication to send can include input indicating the intent of the secondary adjudicator to send the input back to the primary adjudicator. In some examples, the indication can be received by selecting a button with the word "Send" written on it. In some examples, the indication can include receiving a voice command, selecting an icon, swiping on a touch screen, or receiving a different input from the user indicating the intent of the user to send the input.

[0062] In response to receiving the send instruction, CareLink TM The software interface may be configured to store the input (250) on a database accessible by the primary determiner. The input may include input received as a response from the secondary determiner to solve a question provided or selected by the primary determiner. The database may include the server 94 storing the input on a storage device 96.

[0063] In various examples, the CareLink protocol may be implemented in whole or in part on the server 94, the network 92, and the computing devices 100A-100N. TM / software interface and processing or instruction execution on the phone application 211.

[0064] Figure 3 is a diagram illustrating an example of cardiac EGM data 300 indicating a selection of a region including an episode in accordance with one or more techniques of the present disclosure. The EGM data 300 may include a plurality of data points acquired over time that indicate a state of the heart when signals are sensed by the IMD 10. A graphical representation of the EGM data 300 over a period of time may illustrate the presence of an episode. In some examples, the presence of an episode may be illustrated by an anomaly in the EGM data 300. Although a primary determiner may not be able to diagnose an episode with certainty, the presence of an anomaly in the illustration of the EGM data 300 may provide an indication on a region 310 on which to select for further review.

[0065] In some examples, selection of region 310 may be automated via artificial intelligence (AI). Processing circuitry 98 of server 94 may apply a machine learning model or other artificial intelligence analysis to the EGM, and in some cases to other episode data, to determine the likelihood of different arrhythmia classifications over time. In some examples, processing circuitry 98 may implement technology of commonly assigned U.S. patent application Ser. No. 16 / 845,996, filed on April 10, 2020, entitled “MACHINE LEARNING BASED DEPOLARIZATION IDENTIFICATION AND ARRHYTHMIA LOCALIZATION VISUALIZATION,” the entire contents of which are incorporated herein by reference. Processing circuitry 98 may determine likelihoods associated with arrhythmia classifications (e.g., Figure 3 The processing circuit 98 may cause one or more interfaces herein to present a magnified region 310 for review by an adjudicator. In some examples, a user (e.g., a primary adjudicator) may additionally or alternatively determine a region of interest that may be presented to another user (e.g., a secondary adjudicator). In this case, the primary adjudicator may select the region 310 of the EGM data 300 by clicking and dragging the region of interest or otherwise indicating the user's intent to send an input.

[0066] Example machine learning techniques that can be used to select region 310 can include various learning styles, such as supervised learning, unsupervised learning, and semi-supervised learning. Example types of algorithms include Bayesian algorithms, clustering algorithms, decision tree algorithms, regularization algorithms, regression algorithms, example-based algorithms, artificial neural network algorithms, deep learning algorithms, dimensionality reduction algorithms, etc. Various examples of specific algorithms include Bayesian linear regression, enhanced decision tree regression and neural network regression, back propagation neural network, convolutional neural network (CNN), long short-term network (LSTM), prior algorithm, K-means clustering, K-nearest neighbor (kNN), learning vector quantization (LVQ), self-organizing map (SOM), local weighted learning (LWL), ridge regression, least absolute shrinkage and selection operator (LASSO), elastic net and least angle regression (LARS), principal component analysis (PCA) and principal component regression (PCR).

[0067] Figure 4 is a conceptual diagram illustrating an example user interface including a magnified area 400 of seizure data, e.g., as shown with respect to Figure 3 For example, the enlarged area 400 may include Figure 3 The data points are shown in area 310. Figure 4 A portion of the EGM data 300 is illustrated plotted over time, with portions of the EGM 300 data not included in the region 310 omitted to simplify and increase efficiency of determination. Figure 4 Also illustrated are rate graphs, for example, plots of RR intervals over a period of time of an episode, which may increase the efficiency and speed of decision making.

[0068] In some examples, a user (eg, a primary determiner) can scroll the EGM data 310 by moving the highlighted portion 402, for example, using Figure 4 The bottom portion of the interface of the computing device 100A-100N serves as a scroll bar. The primary determiner can select or highlight a portion or area of ​​the EGM data 300 by selecting, dragging, and releasing his / her hand on the touch screen of the device of the computing device 100A-100N. In some examples, the user (e.g., the primary determiner) can pan or scroll to another portion of the EGM data 300 that contains the episode. The selection can be magnified on the display of the computing device used by the user. The area initially displayed as magnified can be selected by a processing circuit (e.g., processing circuit 98) and / or by applying a machine learning model as described above or by another user.

[0069] Figure 5 is a conceptual diagram illustrating an example user interface including an input form for receiving input from a primary determiner in accordance with one or more techniques of the present disclosure. Figure 4 The interface shown in FIG. 1 can present a review of the episode to a user (eg, a nurse who is another primary adjudicator). Figure 5 A list of questions 508 shown in FIG. 508 is provided to provide input regarding the decision. If a category is not included in the list, an input field 502 may allow the primary decider to enter another category.

[0070] Figure 5 Also included is a decision confidence selection (506), where the primary determiner can indicate via input a confidence level associated with the initial decision. Additionally, a comment input box 504 can allow the primary determiner to send specific comments about the episode data to the secondary determiner.

[0071] Figure 6 A sample interface showing a secondary adjudicator. Figure 6As shown, a list or notification of patients and episodes of patients can be presented to a secondary determiner (e.g., a cardiologist or other clinician) for further review. The secondary determiner can select patients and episodes of patients by pressing the touch screen of the computing device 100, selecting the display button 608 and / or the display button 610. When the display button is selected, the computing device 100 can then display an interface on the screen that includes a portion of the episode data selected by the primary determiner / AI and prompts the secondary determiner to select a response to the primary determiner's input query. In some examples, the data processing for selecting the episode area will appear in the form of a back-end AI algorithm or machine learning model deployment to run on the EGM and return the area in question, followed by additional digital processing and visualization on the computing device 100, for example, to show the area. The output is a view for nurses and clinicians and a relatively fast turnaround for determinations via the system 2. The secondary determiner can type a response in the comment box 606 and / or can select the "yes" button 604 or the "no" button 602.

[0072] Fig. 7A 700 is a conceptual diagram illustrating an example interface for a primary determiner to make an initial determination based on seizure data and decide whether to send the seizure data to a secondary determiner. Fig. 7A As shown, an episode, such as an episode of atrial fibrillation, may be flagged for investigation. The interface may indicate the confidence level associated with the episode having occurred via a confidence notification 710. The interface may additionally include a graphical representation of the episode data 704. The primary decider may use this information to determine whether the patient has experienced an arrhythmia associated with the flagged episode and select from detection confirmation options 708, or the primary decider may send this information to a secondary decider for further review by selecting a share button 702.

[0073] Figure 7B It is an example from Fig. 7A 750 . In some examples, the primary determiner may be able to select a priority 752 to indicate the urgency of recommending that the secondary determiner review the seizure data. In the receiving field 756, the primary determiner may enter the name of the desired recipient. The seizure data file may be attached to the message using the attach file button 758. The seizure data file may include magnified areas of interest. These areas may be selected using AI, primary determiner input, or a combination thereof. In some examples, the primary determiner may be prompted to send a personalized message along with the data in the message field 754. The primary determiner may send the message using the send button 760.

[0074] Figure 8802 is a conceptual diagram illustrating an interface and process by which a secondary determiner receives a notification that a new EGM determination is required and securely accesses a computing device 100 to review the EGM. In some examples, the secondary determiner may be notified via email. The secondary determiner may initiate a login on a touch screen device by selecting notification 802. In some examples, the secondary determiner may use his / her phone login credentials (e.g., Face ID) to access the data. Upon unlocking the device, the secondary determiner gains access to the data available in a web browser. In some examples, depending on user preferences, the secondary determiner may use a phone / tablet application instead of a web browser. The secondary determiner may then examine the data and evaluate the data.

[0075] Fig. 9 900 is a block diagram illustrating an example interface in which seizure data is accessed via a secure web browser. In some examples, the secondary determiner can use a virtual inspection tool 906 to assist in the assessment, for example, the secondary determiner can zoom in, zoom out, measure, highlight, etc., seizure data 908 (e.g., segments of seizure data identified by the primary determiner or AI model) for review. In some examples, the secondary determiner can select an assessment from a drop-down menu list 902. At the end of the inspection, the secondary determiner can select a "done" button 904, which can initiate the transfer of the secondary determiner's assessment to the database 250 of the system 2.

[0076] In some examples, the technology of the present disclosure includes a system including means for performing any of the methods described herein. In some examples, the technology of the present disclosure includes a computer-readable medium including instructions for causing a processing circuit to perform any of the methods described herein.

[0077] It should be understood that the various aspects disclosed herein may be combined in combinations different from those specifically presented in the specification and drawings. It should also be understood that, depending on the example, certain actions or events of any of the processes or methods described herein may be performed in a different order, may be added, merged, or omitted entirely (e.g., not all described actions or events may be required to perform these techniques). In addition, 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.

[0078] In one or more examples, the described techniques can be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions can be stored as one or more instructions or codes on a computer-readable medium and executed by a hardware-based processing unit. The computer-readable medium may include a non-transitory computer-readable medium that corresponds to a tangible medium, such as a data storage medium (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 can be accessed by a computer).

[0079] 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 circuits. Thus, the terms "processor" or "processing circuitry" as used herein may refer to any of the foregoing structures or any other physical structure suitable for implementing the described techniques. Additionally, these techniques may be fully implemented in one or more circuits or logic elements.

[0080] The present disclosure includes the following non-limiting examples.

[0081] Embodiment 1: A computing system, the computing system comprising a memory storing instructions and processing circuitry of one or more devices, the computing system comprising a server, a computing device of a primary determiner, and a computing device of a secondary determiner, the computing system being configured to execute instructions to: receive episode data of a heart attack from a medical device at the server; identify, by the server, an area of ​​the episode data; provide a notification to the secondary determiner via the computing device of the secondary determiner; in response to the notification, the secondary determiner interacts with the computing device of the secondary determiner, and in response to the interaction, displays the area of ​​the episode data on a display of the computing device of the secondary determiner; receive input by the computing device of the secondary determiner; and in response to the episode data, transmit the input received from the secondary determiner to the server via the computing device of the secondary determiner.

[0082] Embodiment 2: The computing system of embodiment 1, wherein the seizure data comprises electrocardiogram or electrocardiogram data.

[0083] Embodiment 3: A computing system according to any one or more of Embodiments 1 or 2, wherein the processing circuit is configured to apply the seizure data to a machine learning model to determine the region

[0084] Embodiment 4: The computing system of any one or more of Embodiments 1 to 3, wherein the server is configured to determine the region of the episode data based on input from a primary determiner.

[0085] Embodiment 5: The computing system of any one or more of Embodiments 1 to 4, wherein the computing device of the secondary determiner is configured to display the notification on a screen of the computing device of the secondary determiner.

[0086] Embodiment 6: The computing system of any one or more of Embodiments 1 to 5, wherein the server is configured to save the input received from the secondary arbitrator.

[0087] Embodiment 7: The computing system of any one or more of embodiments 1 to 6, wherein the computing device of the primary determiner is configured to receive an input question from the primary determiner, wherein the server is configured to cause the computing device of the secondary determiner to present the input question to the secondary determiner.

[0088] Embodiment 8: The computing system of embodiment 7, wherein the computing device of the primary determiner is configured to receive from the primary determiner a selection from an input question determined by applying the episode data to a machine learning model.

[0089] Embodiment 9: The computing system of any one or more of Embodiments 1 to 7, wherein the computing device of the primary determiner is configured to receive a selection from the primary determiner indicating the identity of the secondary determiner.

[0090] Embodiment 10: The computing system according to any one or more of embodiments 1 to 9, wherein in order to display the area, the computing device of the secondary determiner is configured to zoom in on the area.

[0091] Embodiment 11: A method of operating a computing system to facilitate determining a cardiac event between a primary determiner and a secondary determiner, the method comprising: receiving, at a server, episode data of a cardiac attack from a medical device; identifying, by the server, an area of ​​the episode data; providing a notification to the secondary determiner via the computing device of the secondary determiner; in response to the notification, the secondary determiner interacting with the computing device of the secondary determiner, and in response to the interaction, displaying the area of ​​the episode data on a display of the computing device of the secondary determiner; receiving input by the computing device of the secondary determiner; and transmitting, by the computing device of the secondary determiner to the server, in response to the episode data, the input received from the secondary determiner.

[0092] Embodiment 12: The method of embodiment 11, wherein the seizure data comprises electrocardiogram or electrocardiogram data.

[0093] Embodiment 13: The method according to any one or more of embodiments 11 or 12 further comprises applying the seizure data to a machine learning model by the processing circuit to determine the region.

[0094] Embodiment 14: The method according to any one or more of Embodiments 11 to 13, further comprising: determining, by the server, the region of the seizure data based on input from a primary determiner.

[0095] Embodiment 15: The method according to any one or more of embodiments 11 to 14, further comprising: displaying the notification of the secondary arbitrator on a screen of the computing device.

[0096] Embodiment 16: The method according to any one or more of embodiments 11 to 15, further comprising: saving the input received by the server from the secondary arbitrator.

[0097] Embodiment 17: The method according to any one or more of Embodiments 11 to 16, further comprising: receiving, by the computing device of the primary determiner, an input question from the primary determiner, wherein the server is configured to cause the computing device of the secondary determiner to present the input question to the secondary determiner.

[0098] Embodiment 18: The method according to Embodiment 17, further comprising: receiving, by the computing device of the primary determiner, from the primary determiner a selection from input questions determined by applying the episode data to a machine learning model.

[0099] Embodiment 19: The method of any one or more of Embodiments 11 to 17, further comprising: receiving, by the computing device of the primary determiner, a selection from the primary determiner indicating the identity of the secondary determiner.

[0100] Embodiment 20: The method according to any one or more of Embodiments 11 to 19, wherein displaying the area includes zooming in on the area.

[0101] Embodiment 21: A non-transitory computer-readable storage medium, the non-transitory computer-readable storage medium comprising program instructions, which, when executed by a processing circuit of a computing system comprising a server, a computing device of a primary determiner, and a computing device of a secondary determiner, causes the processing circuit to perform a method comprising: receiving, at the server, seizure data of a heart attack from a medical device; identifying, by the server, an area of ​​the seizure data; providing a notification to the secondary determiner via the computing device of the secondary determiner; in response to the notification, the secondary determiner interacting with the computing device of the secondary determiner, and in response to the interaction, displaying the area of ​​the seizure data on a display of the computing device of the secondary determiner; receiving input by the computing device of the secondary determiner; and transmitting, by the computing device of the secondary determiner, the input received from the secondary determiner to the server via the computing device of the secondary determiner in response to the seizure data.

[0102] Various examples have been described. These and other embodiments are within the scope of the following claims.

Claims

1. A computing system comprising a memory storing instructions and processing circuitry of one or more devices, the computing system comprising a server, a computing device of a primary arbitrator, and a computing device of a secondary arbitrator, the computing system being configured to execute instructions to: receiving, at the server, heart attack onset data from a medical device; identifying, by the server, a region of the seizure data; providing a notification to the secondary determiner via the computing device of the secondary determiner; In response to the notification, the secondary determiner interacts with the computing device of the secondary determiner, and in response to the interaction, displays the area of ​​the seizure data on a display of the computing device of the secondary determiner; receiving input by the computing device of the secondary determiner; as well as The input received from the secondary determiner is transmitted to the server by the computing device of the secondary determiner in response to the episode data.

2. The computing system of claim 1, wherein the seizure data comprises electrocardiogram or electrocardiographic data.

3. A computing system according to any one or more of claims 1 or 2, wherein the processing circuit is configured to apply the seizure data to a machine learning model to determine the region.

4. The computing system of any one or more of claims 1 to 3, wherein the server is configured to determine the region of the episode data based on input from a primary determiner.

5. The computing system of any one or more of claims 1 to 4, wherein the computing device of the secondary determiner is configured to display the notification on a screen of the computing device of the secondary determiner.

6. The computing system of any one or more of claims 1 to 5, wherein the server is configured to save the input received from the secondary arbitrator.

7. The computing system of any one or more of claims 1 to 6, wherein the computing device of the primary determiner is configured to receive an input question from the primary determiner, wherein the server is configured to cause the computing device of the secondary determiner to present the input question to the secondary determiner.

8. The computing system of claim 7, wherein the computing device of the primary determiner is configured to receive from the primary determiner a selection from an input question determined by applying the episode data to a machine learning model.

9. The computing system of any one or more of claims 1 to 8, wherein the computing device of the primary determiner is configured to receive a selection from the primary determiner indicating the identity of the secondary determiner.

10. The computing system of any one or more of claims 1 to 9, wherein in order to display the area, the computing device of the secondary determiner is configured to zoom in on the area.

11. A non-transitory computer-readable storage medium comprising program instructions, which, when executed by a processing circuit of a computing system comprising a server, a computing device of a primary arbitrator, and a computing device of a secondary arbitrator, causes the processing circuit to perform a method comprising: receiving, at the server, heart attack onset data from a medical device; identifying, by the server, a region of the seizure data; providing a notification to the secondary determiner via a computing device of the secondary determiner; In response to the notification, the secondary determiner interacts with the computing device of the secondary determiner, and in response to the interaction, displays the area of ​​the seizure data on a display of the computing device of the secondary determiner; receiving input by the computing device of the secondary determiner; as well as The input received from the secondary determiner is transmitted to the server by the computing device of the secondary determiner in response to the episode data.

Images