Coded heart rate in heartbeat marker display

Abstract

A method includes identifying locations of heartbeats and peaks of the heartbeats in electrocardiogram data using a machine learning model. The method further includes determining a change in the heart rate over time based at least in part on the location of the heartbeat and the peak. The method further includes displaying changes in the heart rate over time and the location of the peak on the graph with a single annotation.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to provisional application No. 63 / 345,973, filed on May 26, 2022, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present disclosure relates to devices, methods and systems for analyzing cardiac activity and cardiac events. Background Art

[0004] Monitoring devices for collecting biometric data are becoming increasingly common in diagnosing and treating patients' medical conditions. For example, mobile devices can be used to monitor a patient's cardiac data. Such cardiac monitoring can provide doctors with valuable information about the occurrence and regularity of various heart diseases and irregularities in a patient. For example, cardiac monitoring can be used to identify abnormal heart rhythms so that critical alerts can be provided to the patient, doctor, or other caregiver, and the patient can be treated. Summary of the invention

[0005] In Example 1, a method includes identifying a heartbeat and a location of a peak of the heartbeat in electrocardiogram (ECG) data using a machine learning model. The method also includes determining a change in heart rate over time based at least in part on the location of the heartbeat and the peak. The method also includes displaying the change in heart rate over time and the location of the peak in a single annotation on a graph.

[0006] In Example 2, according to the method of Example 1, the distance between the positions of the peaks on the graph is based on the time elapsed between two consecutive R waves in the ECG data.

[0007] In Example 3, the method of Example 2 wherein the distance is based on a peak of the R wave.

[0008] In Example 4, the method according to any of the preceding Examples, wherein the height of each of the individual annotations is based on changes in heart rate over time.

[0009] In Example 5, the method of Example 4, wherein the height of each of the individual annotations relative to each other is proportional to the change in heart rate associated with each of the individual annotations over time.

[0010] In Example 6, a method according to any of the preceding examples, wherein determining changes in heart rate over time is determined by a machine learning model.

[0011] In Example 7, a method according to any of the preceding Examples, wherein the change in heart rate over time is based on the time between a pair of consecutive heartbeats.

[0012] In Example 8, according to any of the preceding examples, the method, wherein the individual annotations are displayed in chronological order.

[0013] In Example 9, the method according to any of the preceding examples further includes displaying the ECG data on a graph.

[0014] In Example 10, the method of Example 9, wherein a single annotation is superimposed on the ECG data on the graph.

[0015] In Example 11, a method according to Example 9 or Example 10, wherein the position of the peak coincides with a peak in the ECG data on the graph.

[0016] In Example 12, the method according to any one of Examples 9-11, wherein the height of the single annotation is greater than the height of the peak in the ECG data.

[0017] In Example 13, a computer program product includes instructions for causing one or more processors to perform the steps of the method according to Examples 1-12.

[0018] In Example 14, a computer readable medium has stored thereon a computer program product according to Example 13.

[0019] In Example 15, a computer includes the computer readable medium according to Example 14.

[0020] In Example 16, a system includes a server having: a database, a first set of one or more processors, and a first computer-readable medium having a first set of computer-executable instructions embodied thereon. The first set of instructions is configured to be executed by the first set of one or more processors to cause the server to: identify heartbeats and locations of peaks of the heartbeats in ECG data using a machine learning model; determine changes in heart rate over time based at least in part on the locations of the heartbeats and peaks; and generate a second set of instructions to cause a remote computer to display the changes in heart rate over time and the locations of the peaks in a single annotation on a graph.

[0021] In Example 17, according to the system of Example 16, the change of heart rate over time is determined by a machine learning model.

[0022] In Example 18, according to the system of Example 16, the change in heart rate over time is based on the time between a consecutive pair of heartbeats.

[0023] In Example 19, the system of Example 18, wherein the time is converted to beats per minute.

[0024] In Example 20, according to the system of Example 16, the first set of instructions is configured to be executed by the first processor so that the first processor: combines the ECG data and the second set of instructions into a data packet for transmission to the remote computer.

[0025] In Example 21, the system according to Example 16 further includes a remote computing system having: a user interface (UI), a second set of one or more processors, and a second computer-readable medium on which a second set of computer-executable instructions are implemented. The second set of instructions is configured to be executed by the second set of one or more processors so that the remote computing system: after receiving a data packet including ECG data and the second set of instructions: displays the change of heart rate over time and the location of the peak value with a single annotation on the curve graph on the UI.

[0026] In Example 22, the system of Example 21, wherein the height of each of the individual annotations is based on changes in heart rate over time.

[0027] In Example 23, the system of Example 21, wherein the ECG data is displayed on a graph.

[0028] In Example 24, the system of Example 23, wherein a single annotation is superimposed on the ECG data on the graph.

[0029] In Example 25, a method includes using a machine learning model to identify heartbeats and locations of peaks of the heartbeats in ECG data. The method also includes determining changes in heart rate over time based at least in part on the locations of the heartbeats and the peaks. The method also includes causing the changes in heart rate over time and the locations of the peaks to be displayed on a graph as a single annotation.

[0030] In Example 26, the method of Example 25, wherein the height of each of the individual annotations is based on changes in heart rate over time.

[0031] In Example 27, the method of Example 25 is according to which a single annotation is superimposed on the ECG data on the graph.

[0032] In Example 28, the method of Example 27 is according to which the location of the peak coincides with a peak in the ECG data on the graph.

[0033] In Example 29, according to the method of Example 25, the change in heart rate over time is based on the time between a consecutive pair of heartbeats.

[0034] In Example 30, the method of Example 29, wherein the time is converted to beats per minute.

[0035] In Example 31, a method includes receiving an ECG data packet and metadata associated with the ECG data. The ECG data includes heartbeats with corresponding peak locations. The metadata includes determining a change in heart rate over time based at least in part on the heartbeats and the locations of the peaks. The method also includes displaying the change in heart rate over time and the locations of the peaks in a single annotation on a graph.

[0036] In Example 32, the method of Example 31, wherein the height of each of the individual annotations is based on changes in heart rate over time.

[0037] In Example 33, the method according to Example 31 further includes displaying the ECG data on a curve graph.

[0038] In Example 34, the method of Example 33 is according to which a single annotation is superimposed on the ECG data on the graph.

[0039] In Example 35, the method of Example 33 is used, wherein the single annotation coincides with a peak in the ECG data on the graph.

[0040] Although multiple examples are disclosed, other examples of the present disclosure will become apparent to those skilled in the art from the following detailed description. The detailed description shows and describes illustrative examples of the present disclosure. Therefore, the drawings and detailed description are to be considered illustrative rather than restrictive in nature. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A cardiac monitoring system according to certain examples of the present disclosure is shown.

[0042] Figure 2 A server, a remote computer, and a user interface are shown according to certain examples of the present disclosure.

[0043] Figure 3 A view of a report construction page is shown according to certain examples of the present disclosure.

[0044] Figure 4-7 Various cardiac data graphs according to certain examples of the present disclosure are shown.

[0045] Figure 8 A flow chart describing an illustrative method for creating and displaying annotations of heart rate changes over time and peak locations according to examples of the present disclosure is shown.

[0046] Fig. 9 A block diagram depicting an illustrative computing device is shown according to examples of the present disclosure.

[0047] Although the disclosed subject matter is applicable to various modifications and alternative forms, specific examples are shown by way of example in the accompanying drawings and are described in detail below. However, it is not the purpose of the present invention to limit the present disclosure to the specific examples described. On the contrary, the present disclosure is intended to cover all modifications, equivalents and alternatives that fall within the scope of the present disclosure defined by the appended claims. DETAILED DESCRIPTION

[0048] The present disclosure relates to devices, methods, and systems for facilitating analysis of cardiac activity and cardiac events (eg, abnormal heart rhythms or other problems).

[0049] A patient's electrocardiogram (ECG) data can be used to monitor cardiac activity and / or identify whether the patient has experienced a cardiac event. One type of cardiac activity measurement is called heart rate variation over time or HRt. Trends or patterns in a patient's heart rate variation over time can indicate certain cardiac activity or events.

[0050] Typically, in ECG analysis tools, changes in a patient's heart rate over time are displayed using only text. For example, if the change in a patient's heart rate over time is 150 beats per minute over a given time period, the display may display "150" in numerical form as part of or adjacent to the associated ECG data graph. However, identifying patterns or trends using only numerical text may be challenging. Therefore, certain examples of the present disclosure relate to systems, methods, and devices for encoding heart rate information in an ECG data graph via annotations.

[0051] Figure 1 Patient 10 and example system 100 are shown. System 100 includes a monitor 102 attached to patient 10 to detect cardiac activity of patient 10. Monitor 102 can generate electrical signals representing cardiac activity of patient 10. For example, monitor 102 can detect the patient's heartbeat (e.g., using infrared sensors, electrodes) and convert the detected heartbeat into electrical signals representing ECG data. Monitor 102 transmits the ECG data to mobile device 104 (e.g., mobile phone).

[0052] Mobile device 104 can include a program (e.g., mobile phone application) for receiving, processing and analyzing ECG data. For example, the program can analyze ECG data and detect cardiac events (e.g., irregular cardiac activity period) contained in the ECG data or mark it. Because ECG data can be continuously generated, the amount of ECG data may be difficult to store and process locally on mobile device 104. Therefore, mobile device 104 can periodically send ECG data blocks to another device or system, which can process, attach and archive ECG data blocks and metadata associated with ECG data blocks (e.g., time, duration, detected / marked cardiac events). In some cases, monitor 102 can be programmed to send ECG data directly to other devices or systems without using mobile device 104. In addition, in some cases, monitor 102 and / or mobile device 104 include buttons or touch screen icons that allow patient 10 to initiate events. Such instructions can be recorded and transmitted to other devices or systems. In other cases involving multi-day studies, ECG data and associated metadata are sent in larger blocks.

[0053] Cardiac Event Server

[0054] exist Figure 1 In the example shown, mobile device 104 sends ECG data (and associated metadata, if any) to cardiac event server 106 (hereinafter referred to as "server 106" for brevity). Server 106 includes multiple platforms, layers, or modules that work together to process and analyze ECG data so that cardiac events can be detected, filtered, prioritized, and ultimately reported to the patient's physician for analysis and treatment. Figure 1 In the example of , the server 106 includes one or more machine learning models 108 (e.g., deep neural networks), a cardiac event router 110, a reporting platform 112, and a notification platform 114. Figure 1 Only one server 106 is shown in the figure, but the server 106 may include multiple separate physical servers, and the various platforms / modules / layers may be distributed among the multiple servers. Each of the platforms / modules / layers may represent a separate program, application, and / or code block, where the output of one of the platforms / modules / layers is the input of another platform / module / layer. Each platform / module / layer may communicate between or among other platforms / modules / layers and systems and devices external to the server 106 using an application programming interface (API).

[0055] Server 106 applies machine learning model 108 to ECG data to determine various cardiac data and events. As an example, machine learning model 108 can identify heartbeats contained in ECG data and can determine information about changes in heart rate over time.

[0056] In some embodiments, the machine learning model 108 includes two paths, wherein the first path is a deep convolutional neural network and the second path is a deep fully connected neural network. The deep convolutional neural network receives one or more groups of heartbeats (e.g., a heartbeat string of 3-10 heartbeats), which are processed by a series of layers in the deep convolutional neural network. This series of layers may include a convolutional layer for performing convolution on the time series data in the heartbeat string; a batch normalization layer for normalizing the output of the convolutional layer (e.g., concentrating the results around the origin); and a nonlinear activation function layer for receiving the normalized value of the batch normalization layer. The heartbeat string then passes through a set of repeated layers, such as another convolutional layer, a batch normalization layer, and a nonlinear activation function layer. This set of layers can be repeated multiple times.

[0057] The deep fully connected neural network receives the RR interval data (e.g., the time interval between adjacent heartbeats) and processes it through a series of layers: a fully connected layer, a nonlinear activation function layer, another fully connected layer, another nonlinear activation function layer, and a regularization layer. The outputs of both paths are then fed to the fully connected layer. The resulting values ​​are passed through the fully connected layer and the softmax layer to produce a probability distribution of the heartbeat categories.

[0058] If the machine learning model 108 determines that the ECG data is closest to the labeled ECG data associated with the cardiac event, the machine learning model 108 can determine that the patient 10 has experienced the cardiac event. In addition, the machine learning model 108 can measure or determine certain features of the patient's 10 cardiac activity based on the ECG data. For example, the machine learning model 108 can determine the patient's 10 heart rate, duration, or heartbeat count during the cardiac event based on the ECG data. The machine learning model 108 can also determine the confidence level of each classification or identification of the cardiac event. The confidence level is an indication of the certainty or uncertainty in the accuracy of the classification or identification of the machine learning model. The server 106 stores the cardiac event (and associated metadata, such as information such as heart rate, duration, heartbeat count, etc.) in a database for storage. Subsequently, the server 106 can retrieve the cardiac event and associated information from the database.

[0059] In some cases, the mobile device 104 (or monitor 102) may initially classify a cardiac event based on the ECG data. The server 106 may then reclassify or confirm the cardiac event using the machine learning model 108. Doing so allows for a more computationally expensive analysis of the ECG data to be performed using the computing resources of the server 106 rather than the limited resources of the mobile device 104.

[0060] In some cases, once the ECG data is processed by the machine learning model 108, the ECG data may be available to a reporting platform 112. As will be described in more detail below, the reporting platform 112 may be accessed by a user of a clinic or laboratory 118 via a remote computer 116 (e.g., a client device such as a laptop, mobile phone, desktop computer, etc.).

[0061] In other cases, the cardiac event router 110 is used to determine which platform further processes the ECG data based on the classification associated with the cardiac event. For example, if the identified cardiac event is severe, the cardiac event router 110 can flag the ECG data or send it to the notification platform 114. The notification platform 114 can be programmed to immediately send a notification (along with the relevant ECG data and associated metadata) to the patient's physician / care team remote computer 116 and / or the patient 10 (e.g., to their computer system, email, mobile phone application).

[0062] Figure 2 A server 106 is shown communicatively coupled to a remote computer 116 (eg, via a network). Figure 2 In the example of , remote computer 116 includes a monitor showing a user interface 122 (hereinafter "UI 122" for brevity) displaying features of reporting platform 112 hosted by server 106. UI 122 includes multiple pages or screens for tracking and facilitating analysis of patient ECG data.

[0063] In some cases, the reporting platform 112 is a software as a service (SaaS) platform hosted by the server 106. To access the reporting platform 112, a user (e.g., a technician) interacts with the UI 122 to log into the reporting platform 112 via a web browser so that the user can use and interact with the reporting platform 112. When a user of the clinic or laboratory 118 is ready to analyze the patient's ECG data, the user can select the patient's profile through the UI 122.

[0064] The server 106 (e.g., via programming associated with the reporting platform 112) can initiate a process for sending data to the remote computer 116. The data includes ECG data and metadata associated with the ECG data. As described above, once ECG data from a monitored patient has been collected, the machine learning model 108 can determine certain features of the patient's 10 cardiac activity based on the ECG data, including estimating that a cardiac event has occurred, and associating or generating metadata for the determined event. The metadata may include information about the patient 10, the patient's 10 heart rate during the cardiac event, the duration of the cardiac event, the heartbeat count in the cardiac event, the confidence level of the machine learning model in identifying the cardiac event, and / or the heartbeat classification (e.g., normal, ventricular, supraventricular, unclassified). In some embodiments, the machine learning model 108 assigns a heartbeat classification to each heartbeat, and also assigns a cardiac event type (e.g., atrial fibrillation, ventricular tachycardia, flutter) to certain heartbeat groups and patterns. In order to distinguish heartbeats, a unique identifier (e.g., a unique number) can be assigned to each individual heartbeat.

[0065] Accessing, processing and displaying ECG data and metadata for one or more days can consume a lot of computing resources, network bandwidth resources and human resources. To help relieve the burden on these resources, server 106 (e.g., via reporting platform 112) can selectively send ECG data packets and metadata packets to remote computer 116.

[0066] The initial data packet may include: (1) a short strip of ECG data surrounding a detected cardiac event (e.g., a 60 second strip), (2) metadata associated with the strip, and (3) executable code (e.g., JavaScript code). In some cases, only the ECG data associated with the highest priority cardiac event is initially transmitted. After the initial data packet is sent from the server to the remote computer 116, additional data packets may be sent in response to selections made by the user in the UI 122.

[0067] Report Build Page

[0068] With the initial data packet received at the remote computer 116, the user has accessed (via the UI 122) Figure 3 1. The report construction page 200 is shown in FIG. This page is generated at the remote computer 116 based on the data packet and is selectively displayed via the UI 122. The report construction page 200 facilitates the analysis of cardiac events.

[0069] Figure 3A screen shot of a report construction page 200 is shown, which a user uses to view and analyze a patient's ECG data and metadata. The report construction page 200 includes a plurality of windows for displaying data, plots, icons, links, tags, indicators, and the like.

[0070] Window 202 displays a heart rate graph of multiple days of ECG data. This window 202 provides an initial visual insight into which time periods appear to contain abnormal heart rate activity. Figure 3 In the example shown, window 202 displays four days of ECG data, although a shorter or longer time period may be displayed by default and may be changed by the user.

[0071] Window 204 allows the user to view a shorter graph of ECG data. For example, window 204 may display ECG data associated with a detected cardiac event and ECG data before and after the detected event. This window 204 provides visual insight into the onset of the detected event, and whether the detected event may be an artifact, a subsequent event, etc.

[0072] Window 208 shows a shorter graph of ECG data (e.g., approximately 10 heartbeats) than the graphs of windows 202 and 204. Window 208 displays a closer view of a portion of the ECG data of windows 202 and 204. A user may use window 204 to select which shorter ECG data set to display in window 208. Each of windows 202, 204, and 208 may include a marker, indicator, icon, etc. to visually note the location of a detected cardiac event within the ECG data strip.

[0073] Heart rate variation over time and peak location encoded in a single annotation

[0074] As mentioned above, one type of cardiac activity measurement is called heart rate over time, which can indicate certain cardiac activities or events based on trends or patterns. Figure 4 A graph of ECG data is shown, which shows changes in heart rate over time, without coded labels (e.g., simply displayed as numbers in the text). Instead, Figure 5-7 Graphs of ECG data with coded annotations are shown. These graphs can be displayed on the UI 122 of the remote computer 116, for example, in one of the windows of the report construction page 200. As described in more detail below, the peak location and the change in heart rate over time are marked with a single annotation.

[0075] Figure 4 A graph 210 is shown with a curve 212 of ECG data. In this example, the ECG data includes six heartbeats. Each heartbeat is labeled with a heartbeat classification 214 for Figure 4The heartbeats in are shown as "N", indicating a normal heartbeat. Between each pair of heartbeats at the top of the graph 210 is an RR interval value 216 and a value 218 of the change in heart rate over time. The bottom value is the RR interval 216, which indicates the time (in milliseconds) that elapses between two consecutive R waves of the QRS portion of the ECG data. In other words, the RR interval measures the time between the two peaks of consecutive R waves. The upper value is the value 218 of the change in heart rate over time expressed in beats per minute. Figure 4 In the example of , the changes in heart rate over time are displayed using only text (e.g., 91, 92, 91, 93, 91, etc.). However, it may be challenging to identify patterns or trends in the changes in heart rate over time using only text.

[0076] Figure 5 A graph 220 is shown having a curve 222 of ECG data and annotations 224. The curve 222 of ECG data is shown by a line in darker shading (e.g., a continuous line), and the annotations 224 are shown by vertical lines in lighter shading. Figure 5 In the lower enlarged image of FIG. 1 , the annotation 224 is further identified by a dotted line. Figure 5 2 is shown as a line, but other types of annotations (such as bars) may be used and displayed on the graph 220.

[0077] Each annotation 224 represents the change in the patient's heart rate over time. In some cases, the change in heart rate over time is an instantaneous heart rate, meaning that the heart rate is based on the most recent consecutive pair of heartbeats. This heart rate calculation can be measured in milliseconds and converted to a heart rate in beats per minute. In some cases, the change in heart rate over time is determined by counting how many heartbeats occurred in the last 60 seconds of ECG data.

[0078] As mentioned above, Figure 1 The machine learning model 108 initially identifies the locations of heartbeats and peaks in the ECG data (e.g., the locations of peaks in time). Based on the locations of the identified heartbeats and peaks, the machine learning model 108 can determine changes in heart rate over time. Instead of or in addition to displaying the determined changes in heart rate over time using text on the graph 220, the changes in heart rate over time are visually shown using annotations 224.

[0079] Each determined change in heart rate over time can be displayed in a separate single annotation 224 on the graph 220. The height of each annotation 224 can indicate the change in heart rate over time. For example, a annotation 224 that is higher than another annotation 224 indicates a higher change in heart rate over time (e.g., a higher number of heart beats per minute). The relative height of the annotation 224 can be proportional to the change in the determined heart rate over time. For example, when the annotation 224 indicates a change in heart rate over time where the number of heart beats per minute is twice the change in heart rate over time of another heart rate, the annotation 224 can be displayed as twice as high (relative to another annotation). In some cases, the graph 220 includes a digital indicator along the Y axis of the graph 220, which shows how a given height is converted into heart beats per minute.

[0080] Because the positions of the annotations 224 indicate the times of the peaks, the distance between the annotations 224 on the graph 220 may represent the time elapsed between two consecutive R waves in the ECG data (eg, the distance between the peaks of the R waves within the QRS portion of the ECG data).

[0081] like Figure 5 As shown, the curve 222 and annotations 224 of the ECG data are displayed on the same curve graph 220 in chronological order, and the curve 222 and the annotations are superimposed on each other. Because the position of each annotation 224 indicates the position of the associated peak, the peaks in the ECG data coincide or align with the annotations 224. Therefore, the curve graph 220 can include annotations 224 for each heartbeat. In some cases, if the machine learning model 108 does not initially correctly identify the heartbeat, the annotations are not created and displayed.

[0082] like Figure 5 As shown, in some cases, the height of the annotation 224 is higher than the height of the peak of the associated ECG data. The base of each annotation 224 can start from the same vertical level (e.g., along Figure 5 ), while the depth and shape of the groove of the curve 222 of the ECG data varies based on the actual measured data.

[0083] Each annotation 224 can be aligned with the position of the peak of the heartbeat. Therefore, each single annotation 224 can indicate the determined change in heart rate over time and the peak position. Therefore, the peak position and the change in heart rate over time are encoded in a single annotation.

[0084] By displaying the peak location and the change in heart rate over time with a single annotation, a technician viewing the graph 220 can effectively see the pattern or trend of the change in heart rate over time. For example, when ECG data is displayed in 1 to 5 minute intervals, the single annotation visually provides information for the technician to interpret the data / values ​​represented and detect patterns or trends. More specifically, the sequence, disorder, and pattern of changes in heart rate over time can be easily observed and used to distinguish between heart rhythms such as normal sinus rhythm, atrial fibrillation, and sinus arrhythmia. Figure 5 In the example of , premature beats can be identified by the taller annotation 224. In addition, representing the change in heart rate over time and the peak position with a single annotation allows the user interface to be simpler and reduces the number of indicators on the interface.

[0085] Figure 6 Another graph 230 is shown with annotations 232 - each annotation representing the change in heart rate over time and the location of a peak. Figure 6 In the example of FIG. 2 , the height of the annotation 232 shows a trend that the patient's heart rate changes steadily over time. Such a trend indicates a sinus arrhythmia event.

[0086] Figure 7 Another graph 240 is shown with annotations 242 - each annotation represents the change in heart rate over time and the location of the peak. Figure 7 In the example of FIG. 2 , the height of the annotation 242 shows a trend in which the patient's heart rate changes chaotically over time. Such a trend indicates an atrial fibrillation event.

[0087] method

[0088] Figure 8 A block diagram of a method 300 for creating and displaying annotations of heart rate changes over time and peak locations is shown. The method 300 includes using a machine learning model to identify heart beats and locations of heart beat peaks in ECG data ( Figure 8 Method 300 also includes determining a change in heart rate over time based at least in part on the locations of the heartbeats and the peaks ( Figure 8 Method 300 also includes displaying the heart rate change over time and the location of the peak value with a single annotation on the curve graph ( Figure 8 306 in FIG.

[0089] Computing devices and systems

[0090] Fig. 9400 may include any type of computing device suitable for implementing aspects of the disclosed subject matter. Examples of computing devices include special-purpose computing devices or general-purpose computing devices, such as workstations, servers, laptops, desktops, tablets, handheld devices, smartphones, general-purpose graphics processing units (GPGPUs), etc. Each of the various components shown and described in the figure may include their own set of special-purpose computing device components, such as Figure 5 For example, mobile device 104, server 106, and remote computer 116 may each include their own set of components, such as Figure 5 shown and described below.

[0091] In some cases, computing device 400 includes a bus 410 that directly and / or indirectly couples one or more of the following devices: processor 420, memory 430, input / output (I / O) ports 440, I / O components 450, and power supply 460. Any number of additional components, different components, and / or combinations of components may also be included in computing device 400.

[0092] Bus 410 represents one or more buses (e.g., an address bus, a data bus, or a combination thereof). Similarly, in some cases, computing device 400 may include multiple processors 420, multiple memory components 430, multiple I / O ports 440, multiple I / O components 450, and / or multiple power supplies 460. In addition, any number or combination of these components may be distributed and / or replicated across multiple computing devices.

[0093] In some cases, memory 430 includes computer-readable media in the form of volatile and / or non-volatile memory, and may be removable, non-removable, or a combination thereof. Examples of media include random access memory (RAM); read-only memory (ROM); electrically erasable programmable read-only memory (EEPROM); flash memory; optical media; magnetic cassettes, tapes, disk storage, or other magnetic storage devices; data transfer; and / or any other medium that can be used to store information and can be accessed by a computing device. In some cases, memory 430 stores computer-executable instructions 470 for causing processor 420 to implement aspects of examples of components discussed herein and / or perform aspects of examples of methods and processes discussed herein. Memory 430 may include non-transitory computer-readable media storing computer-executable instructions 470.

[0094] Computer-executable instructions 470 may include, for example, computer code, machine usable instructions, etc., such as program components that are executable by one or more processors 420 (e.g., microprocessors) associated with computing device 400. Program components may be programmed using any number of different programming environments, including various languages, development toolkits, frameworks, etc. Some or all of the functionality contemplated herein may also or alternatively be implemented in hardware and / or firmware.

[0095] According to an example, for example, the instructions 470 may be configured to be executed by the processor 420 and, after execution, cause the processor 420 to perform certain processes. In some cases, the processor 420, the memory 430, and the instructions 470 are part of a controller, such as an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), etc. Such a device may be used to perform the functions and steps described herein.

[0096] The I / O components 450 may include presentation components configured to present information to a user, such as a display device, a speaker, a printing device, etc., and / or input components, such as a microphone, a joystick, a satellite dish, a scanner, a printer, a wireless device, a keyboard, a pen, a voice input device, a touch input device, a touch screen device, an interactive display device, a mouse, etc.

[0097] The devices and systems described herein may be communicatively coupled via a network, which may include a local area network (LAN), a wide area network (WAN), a cellular data network, or the Internet using an Internet service provider, etc.

[0098] Aspects of the present disclosure are described with reference to flowchart illustrations and / or block diagrams of methods, devices, systems, and computer program products. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions.

[0099] Various modifications and additions can be made to the exemplary examples discussed without departing from the scope of the disclosed subject matter. For example, while the examples described above refer to specific features, the scope of the present disclosure also includes examples with different combinations of features and examples that do not include all of the described features. Therefore, the scope of the disclosed subject matter is intended to include all such substitutions, modifications, and variations that fall within the scope of the claims, and all equivalents thereof.

Claims

1. A method comprising: Using a machine learning model to identify heartbeats and locations of peaks of the heartbeats in electrocardiogram (ECG) data; determining a change in heart rate over time based at least in part on the heartbeats and the locations of the peaks; as well as The change of the heart rate over time and the position of the peak value are displayed on the curve graph with a single mark.

2. The method according to claim 1, wherein: The distance between the locations of the peaks on the graph is based on the time elapsed between two consecutive R-waves in the ECG data. The method of claim 2 , wherein the distance is based on a peak value of the R-wave.

4. A method according to any one of the preceding claims, wherein: The height of each of the individual annotations is based on changes in the heart rate over time.

5. The method according to claim 4, wherein: The height of each of the single annotations relative to each other is proportional to the change in the heart rate associated with each of the single annotations over time.

6. A method according to any one of the preceding claims, wherein: Determining the change in heart rate over time is determined by a machine learning model.

7. A method according to any one of the preceding claims, wherein: The change in heart rate over time is based on the time between a pair of consecutive heart beats.

8. A method according to any preceding claim, wherein the individual annotations are displayed in chronological order.

9. The method according to any one of the preceding claims, further comprising: The ECG data is displayed on the graph.

10. The method of claim 9, wherein the single annotation is superimposed on the ECG data on the graph.

11. The method according to claim 9 or 10, wherein the position of the peak coincides with a peak in the ECG data on the graph.

12. The method according to any one of claims 9-11, wherein the height of the single annotation is greater than the height of a peak in the ECG data.

13. A computer program product comprising instructions for causing one or more processors to perform the steps of the method according to claims 1-12.

14. A computer readable medium having stored thereon a computer program product according to claim 13.

15. A computer comprising the computer readable medium according to claim 14.

Images