System for predicting medical procedure efficacy using heart rate variability features

Abstract

A method includes collecting, by a computing system, heart rate data of a patient from a medical device of the patient; determining, by the computing system, one or more heart rate variability features based on the heart rate data; applying, by the computing system, a model to the heart rate variability features and one or more clinical features of the patient; predicting, by the computing system, an effect of a medical procedure on the patient based on the application of the model to the heart rate variability features and the one or more clinical features; and outputting, by the computing system, the predicted effect of the medical procedure to a display device.

Description

[0001] This application claims the benefit of U.S. Provisional Patent Application Serial No. 63 / 365,188, filed on May 23, 2022, entitled “SYSTEMS USING HEART RATE VARIABILITY FEATURES FOR PREDICTION OF MEDICAL PROCEDURE EFFICACY,” the entire contents of which are incorporated herein by reference. Technical Field

[0002] The present disclosure relates to medical device systems, and more particularly to medical device systems for monitoring the efficacy of medical treatments. Background Art

[0003] In some cases, medical professionals may perform various medical procedures on a patient's heart-related tissue to treat various medical conditions. The various medical procedures may successfully or unsuccessfully address the various medical conditions. Summary of the invention

[0004] The apparatus, systems, and techniques disclosed herein as a whole relate to predictions of the effects of a therapy on a patient's cardiac tissue. In some examples, a computing system according to the present disclosure may predict the efficacy and / or effects of one or more medical procedures on a patient's cardiac tissue based on heart rate data. In some examples, the computing system may predict the effects of the medical procedure based on the application of a model to the patient's heart rate variability characteristics and clinical characteristics. In some examples, the computing system may output (e.g., to a medical professional) the predicted effects of the medical procedure. The medical procedure may be catheter ablation for atrial fibrillation (AF).

[0005] The devices, systems, and techniques of the present disclosure may provide one or more technical improvements that are superior to other medical surgery efficacy prediction techniques. In some examples, the present disclosure describes techniques for improving the prediction accuracy of the efficacy of medical surgery. The present disclosure can improve the prediction accuracy by using a combination of heart rate variability features and clinical features, which are proven to be predictions of the efficacy of medical surgery. In some examples, the present disclosure describes techniques for improving the prediction accuracy of surgery by using a weighted combination of multiple classification models to improve the overall accuracy of these techniques. In addition, the model for predicting the efficacy of surgery can be a machine learning model that is trained on a large number (thousands or millions) of instances of training data to provide a highly accurate prediction that exceeds conventional techniques for estimating the efficacy of surgery. In addition, in some examples, heart rate variability features can be determined based on cardiac signals sensed continuously (e.g., autonomously on a triggered or periodic basis) by an insertable cardiac monitor (ICM) or other implantable medical device (IMD), which can provide a more complete picture of the patient's condition than can be determined by a clinician using conventional clinical assessment techniques. AF episodes may occur infrequently and / or unpredictably, but an IMD that continuously senses cardiac signals may sense all AF episodes experienced by a patient.

[0006] In an example, the present disclosure describes a method comprising: collecting, by a computing system, heart rate data of a patient from a medical device of the patient; determining, by the computing system, one or more heart rate variability features based on the heart rate data; applying, by the computing system, a model to the heart rate variability features and one or more clinical features of the patient; predicting, by the computing system, an effect of a medical procedure on the patient based on the application of the model to the heart rate variability features and the one or more clinical features; and outputting, by the computing system, the predicted effect of the medical procedure to a display device.

[0007] In some examples, the present disclosure describes a computing system comprising: a memory configured to store heart rate data; a display device; and a processing circuit configured to: collect heart rate data of a patient from a medical device of the patient; determine one or more heart rate variability features based on the heart rate data; apply a model to the heart rate variability features and one or more clinical features of the patient; predict an effect of a medical procedure on the patient based on the application of the model to the heart rate variability features and the one or more clinical features; and output the predicted effect of the medical procedure to the display device.

[0008] In some examples, the present disclosure describes a computer-readable storage medium that includes instructions that, when executed, cause processing circuitry within a device to perform a method including the following steps: a computing system collecting heart rate data of a patient from a medical device of the patient; the computing system determining one or more heart rate variability characteristics based on the heart rate data; the computing system applying a model to the heart rate variability characteristics and one or more clinical characteristics of the patient; the computing system predicting an effect of a medical procedure on the patient based on the application of the model to the heart rate variability characteristics and the one or more clinical characteristics; and the computing system outputting the predicted effect of the medical procedure to a display device.

[0009] The details of one or more aspects of the present disclosure are set forth in the following drawings and description. Other features, objectives, and advantages of the techniques described in the present disclosure will be apparent from the description and drawings, and from the claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A conceptual diagram of a medical device system for predicting the effects of a medical procedure on a patient.

[0011] Figure 2 It is shown Figure 1 Block diagram of an exemplary configuration of an implantable medical device (IMD) of a system.

[0012] Figure 3 It is shown Figure 1 A block diagram of exemplary external devices of a system.

[0013] Figure 4 It is shown Figure 1 Block diagram of an exemplary health monitoring system (HMS) of a system.

[0014] Figure 5 It is shown by Figure 1 Conceptual diagram of an exemplary collection of heart rate data recorded by an IMD of the system.

[0015] Figure 6 is a conceptual diagram illustrating an exemplary neural network configured to predict the effects of a medical procedure.

[0016] Figure 7 is a conceptual diagram illustrating an exemplary process for inputting data into an exemplary model for predicting the effects of a medical procedure.

[0017] Figure 8 is a block diagram illustrating an exemplary process for training an exemplary model for predicting the effects of a medical procedure.

[0018] Fig. 9is a flow chart illustrating an exemplary process for predicting the effects of a medical procedure.

[0019] Fig.10 is a flow chart illustrating an exemplary process for generating a model for predicting the effects of a medical procedure. DETAILED DESCRIPTION

[0020] The medical devices, systems and techniques disclosed herein relate to prediction of the effects of a therapy on a patient's cardiac tissue. A medical professional may perform one or more medical procedures on a patient's cardiac tissue to treat one or more medical conditions experienced by the patient. A medical professional may perform one or more medical procedures on a patient to treat atrial fibrillation (AF). In some examples, the one or more medical procedures include cardiac ablation techniques such as, but not limited to, catheter ablation or pulmonary vein isolation (PVI). In some examples, a medical professional selects cardiac ablation over other therapeutic procedures (e.g., antiarrhythmic drug therapy) for patients who have not responded well to other therapeutic procedures, or vice versa.

[0021] A medical professional may select a medical procedure from a plurality of available medical procedures based on the patient's symptoms. For example, the patient may be highly symptomatic. In some examples, with respect to a patient experiencing AF, the patient may be experiencing paroxysmal AF (PAF) or non-paroxysmal AF (NPAF). In some examples, the efficacy of a medical procedure, such as short-term efficacy and / or long-term (e.g., greater than 12 months) efficacy, may be limited, and there may be additional risks to the patient's health due to undergoing the procedure. Therefore, a medical professional may wish to predict the effect of the medical procedure on the patient's health and / or the efficacy of the medical procedure on the patient's medical condition before performing the medical procedure on the patient.

[0022] Medical professionals can use existing scoring systems to predict the outcome of medical procedures on a patient's cardiac tissue. The scoring system may include risk predictors, including but not limited to thromboembolic risk predictors (e.g., CHADS2, CHA2DS2-VASc, etc.), APPLE scores, SUCCESS scores, MB-LATER scores, etc. However, existing scoring systems rely on monitoring technologies (e.g., 24-hour Holter monitoring), which may lack sufficient sensitivity and detection of medical conditions (e.g., AF recurrence) under certain conditions. For example, monitoring technologies show insufficient detection rates for subclinical AF recurrence.

[0023] Figure 11 is a conceptual diagram of a medical device system 100 for predicting the effects of a medical procedure on a patient 102. The medical device system 100 may include an implantable medical device (IMD) 106, an external device 108, a network 112, an electronic health record (EHR) system 114, and a health monitoring system (HMS) 116. Although the discussion below and elsewhere in this disclosure describes an implantable medical device (e.g., IMD 106), other exemplary medical device systems may include an external medical device that provides functionality that is the same or substantially similar to the functionality attributed to the IMD 106 herein.

[0024] IMD 106 may be configured to detect and record heart rate data from heart 104 of patient 102. In some examples, IMD 106 detects and records heart rate data by detecting and recording depolarization of one or more chambers (e.g., left ventricle (LV), right ventricle (RV), left atrium (LA), or right atrium (RA)) of heart 104. IMD 106 may detect and record the heart rate of patient 102 by detecting and recording QRS complexes corresponding to ventricular depolarization of heart 104. IMD 106 may determine RR intervals of ventricular depolarization of heart 104 based on the recorded QRS complexes. Each RR interval may represent the time between R waves of adjacent QRS complexes.

[0025] The external device 108 can be one or more computing devices, one or more computing systems, and / or a cloud computing environment. The IMD 106 can be configured to communicate with the external device 108 and transmit the recorded heart rate data 110 to the external device. The IMD 106 and the external device 108 can communicate wirelessly or via wired communication. The external device 108 can further communicate with a cloud network 112 and transmit information (e.g., heart rate data 110) between one or more EHR systems 114 and one or more HMS116 via the network 112. In some examples, the external device 108 determines the heart rate variability (HRV) characteristics and clinical characteristics of the patient 102 based on information from the IMD 106, the EHR system 114, and / or the HMS116.

[0026] The external device 108 may determine HRV features based in part on the heart rate data 110. The HRV features may serve as predictors of recurrence of medical conditions including, but not limited to, atrial fibrillation (AF). The HRV features may include, but are not limited to, one or more of the following: an average value of the recorded RR intervals (hereinafter referred to as "average"), a percentage of interval differences of consecutive RR intervals greater than a time threshold (pNNX), a mean square error (RMSSD) of consecutive RR intervals, a standard deviation (SDNN) of RR intervals, a triangular interpolation of interval histograms (TINN), a triangular index (TRI), an approximate entropy (APEn), a sample entropy (SamPEn), a geometric descriptor of a Poincare map of the heart rate data 110 (SD1, SD2, SD1:SD2 ratio, etc.), a scaling index (DFAα1) of short-term fluctuations in the heart rate data 110, or a scaling index (DFAα2) of long-term fluctuations in the heart rate data 110. pNNX may include a percentage of interval differences of consecutive RR intervals greater than 50 milliseconds (ms) (pNN50) or greater than 20 ms (pNN20). TRI may describe the integral of the density distribution of the heart rate data 110. APEn and SamPEn may represent the complexity of the heart rate data 110 (eg, the complexity of the recorded RR intervals).

[0027] The external device 108 may determine clinical characteristics of the patient 102 based at least in part on information received from the one or more EHR systems 114 and / or the one or more HMSs 116. The clinical characteristics may include, but are not limited to, the age of the patient 102, the presence of any illness in the patient 102, or the monitoring time of the patient 102 before the medical procedure. The illness may include any illness that may affect the cardiac health of the patient 102, including, but not limited to: PAF, hypertension, diabetes, coronary artery disease, lesions, or stroke. In some examples, the external device 108 receives a baseline characteristic from the network 112 for each of the clinical characteristics. For each of the clinical characteristics, the baseline characteristic may include an average value for patients who experience a recurrence of the medical condition and an average value for patients who do not experience a recurrence of the medical condition.

[0028] The external device 108 can determine one or more models and / or apply one or more models to one or more HRV features and one or more clinical features to predict the effect and / or efficacy of the medical procedure on the patient 102. The determination and application of one or more models are described in more detail below. In other examples, the network 112 and / or one or more other computing systems, computing devices, and / or cloud computing environments can be configured to determine the one or more models and / or apply the one or more models. In some examples, the external device 108 and / or the network 112 are further configured to output the predicted effect to the display device. The display device may be incorporated into the external device 108, or may be incorporated into another computing device or computing system that communicates with the external device 108 and / or the network 112.

[0029] The external device 108 may be configured to communicate with various other computing devices and / or computing systems via the network 112. The external device 108 and / or the network 112 may include or may be provided by the Medtronic Carelink TM The external device 108 may include one or more of a desktop computer, a laptop computer, a tablet computer, a smart watch, a personal computing device, etc. The external device 108 may communicate with the user according to one or more wireless communication protocols (e.g., according to or Low Energy (BLE) protocol) to wirelessly communicate with IMD 106 and / or network 112.

[0030] The network 112 can facilitate connections between the external device 108, one or more HMSs 116, and one or more EHR systems 114. The HMS 116 is implemented on the external device 108 and / or one or more other computing devices, one or more other computing systems, or a cloud computing environment. The HMS 116 can retrieve data about the patient 102 from one or more sources of the EHR via the network 112. In some examples, the EHR is stored in the EHR system 114. The EHR system 114 can be implemented on the external device 108 and / or one or more computing devices, one or more computing systems, or a cloud computing environment.

[0031] The EHR data may include data about historical (e.g., baseline) physiological parameter values, previous health events and treatments, disease states, comorbidities, demographics, height, weight, and body mass index (BMI) of patients (including patient 102). HMS 116 can use data from EHR (e.g., from EHR system 114) to configure one or more models implemented by medical device system 100 to predict the effects of medical procedures. In some examples, HMS 116 and / or EHR system 114 provide data from one or more EHRs to external device 108 for storage herein and use as part of determining and / or applying one or more models to predict the effects of medical procedures.

[0032] The network 112 may include one or more computing devices, such as one or more non-edge switches, routers, hubs, gateways, security devices (such as firewalls), intrusion detection, and / or intrusion prevention devices, servers, cellular base stations and nodes, wireless access points, bridges, cable modems, application accelerators, or other network devices. The network 112 may include one or more networks managed by a service provider and may thus form part of a large-scale public network infrastructure (e.g., the Internet). The network 112 may provide computing devices and systems (such as Figure 1 ) provide access to the Internet and may provide a communication framework that allows computing devices and systems to communicate with each other. In some examples, network 112 includes a dedicated network that provides a communication framework that allows Figure 1 The computing devices and computing systems shown in communicate with each other, but some of the data flows are isolated from devices outside the private network for security purposes. In some examples, Figure 1 The communication between the computing device and the computing system shown in is encrypted.

[0033] Figure 2 It is shown Figure 1 1 is a block diagram of an exemplary configuration of an IMD 106 of a medical device system 100. The IMD 106 may be an implanted cardiac device, including but not limited to an implantable cardiac monitor (ICM), such as the LINQ II insertable cardiac monitor available from Medtronic, Inc., an implantable pulse generator (IPG), an implantable cardioverter defibrillator (ICD), a cardiac resynchronization therapy (CRT) device, or the like. Figure 2In the example shown, IMD 106 includes switching circuitry 204, electrodes 202A-202B, sensor 206, communication circuitry 208, sensing circuitry 210, processing circuitry 212, memory 214, and power supply 216. The various circuits may be or include programmable or fixed function circuits that are configured to perform the functions attributed to the respective circuits.

[0034] Memory 214 may store computer-readable instructions that, when executed by processing circuit 212, cause IMD 106 to perform various functions. Memory 214 may be a storage device or other non-transitory medium. Memory 214 may include any volatile, non-volatile, magnetic, optical, or electrical medium, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), electrically erasable programmable ROM (EEPROM), flash memory, or any other digital medium.

[0035] In some examples, IMD 106 may include additional components (e.g., signal generation circuitry for delivering therapy signals, etc.). In some examples, where the functions of IMD 106 are performed by an external medical device, components of IMD 106 may be provided in one or more computing devices, one or more computing systems, and / or a cloud computing environment.

[0036] Electrodes 202A-202B (collectively referred to as "electrodes 202") are electrically connected to chambers of heart 104. Electrodes 202 may be electrically connected to switching circuitry 204 of IMD 106 via electrical connector 203. Each of electrodes 202 may be electrically connected to a different chamber of heart 104. Figure 2 The example shown includes two electrodes 202 , but other examples may include three or more electrodes 202 .

[0037] The switch circuit 204 can selectively couple the sensing circuit 210 to a selected combination of electrodes 202, for example, to sense electrical activity of the atria and / or ventricles of the heart 104. The sensing circuit 204 can include filters, amplifiers, analog-to-digital converters, or other circuits configured to sense cardiac electrical signals via the electrodes 202. In some examples, the sensing circuit 210 is configured to detect an event within the cardiac electrical signal, such as a depolarization, and provide an indication of the event to the processing circuit 212. In this manner, the processing circuit 212 can determine the heart rate data 110 based on the sensed cardiac electrical signal, and can store the determined heart rate data 110 to the memory 214.

[0038] The processing circuit 212 may include any one or more of the following: a microprocessor, a controller, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), discrete logic circuits, or any other processing circuit configured to provide the functionality attributed to the processing circuit 212 herein, and may be embodied as firmware, hardware, software, or any combination thereof.

[0039] Processing circuitry 212 may determine heart rate data 110 based on the sensed cardiac electrical signals from sensing circuitry 204 and may store the heart rate data 110 in memory 214. Processing circuitry 212 may represent heart rate data 110 as a QRS complex representing ventricular depolarization of a ventricle of heart 104. In some examples, processing circuitry 212 may transmit the QRS complex to external device 108 via communication circuitry 208.

[0040] Processing circuitry 212 may determine the presence of AF based on the sensed cardiac signals. Processing circuitry 212 may use one or more detection algorithms (e.g., TruRhythm TM ) is applied to the sensed cardiac signals to determine and record AF. In some examples, processing circuitry 212 may determine a cardiac event associated with an AF episode (e.g., Figure 5 The heart rate data 110 corresponding to the occurrence of AF episodes and flashbacks of AF episodes shown in the figure may be determined, and the determined heart rate data 110 may be stored in the memory 214.

[0041] The sensor 206 may include one or more sensing elements that convert patient physiological activity into electrical signals to sense the value of a corresponding patient parameter. The sensor 206 may include one or more accelerometers, optical sensors, chemical sensors, temperature sensors, pressure sensors, or any other type of sensor. The sensor 206 may output patient parameter values ​​that may be used by the processing circuit 212 to determine the heart rate data 110.

[0042] The communication circuit 208 (alternatively referred to as "telemetry circuit 312") supports wireless communication between the IMD 106 and the external device 108. The processing circuit 212 of the IMD 106 can receive an instruction from the external device 108 and via the communication circuit 208 to transmit the heart rate data 110 to the external device 108. In some examples, the processing circuit 212 automatically transmits the heart rate data 110 to the external device 108. The communication circuit 208 can communicate with the external device 108 via wired communication or through wireless communication technology. The wireless communication technology may include, for example, radio frequency (RF) communication technology via an antenna (not shown). The communication circuit 208 can transmit all heart rate data 110 determined by the processing circuit 212. In some examples, the communication circuit 208 can transmit the heart rate data 110 determined by the processing circuit 212 to correspond to an AF episode, for example, such as Figure 5 shown.

[0043] Figure 3 It is shown Figure 1 A block diagram of an exemplary external device 108 of the medical device system 100 is shown. Figure 2 As shown, the external device 108 includes a processing circuit 302, a memory 304, a communication circuit 306, and a user interface (UI) 308. The memory 304 may include one or more modules, including an application module 310 and a data module 312. The application module 310 may include a health monitoring module 312, which may include a rule engine module 314. The data 316 stored in the memory 304 may include sensory data 318, clinical data 320, and a model 322. In some examples, the data 312 may be stored separately in the EHR system 114 and / or the HMS 116.

[0044] The processing circuit 302 may include fixed function circuits and / or programmable processing circuits. The processing circuit 302 may include any one or more of a microprocessor, a controller, a GPU, a TPU, a digital signal processor (DSP), an ASIC, an FPGA, or an equivalent discrete or analog logic circuit. In some examples, the processing circuit 302 may include multiple components (such as any combination of one or more microprocessors, one or more controllers, one or more GPUs, one or more TPUs, one or more DSPs, one or more ASICs, or one or more FPGAs), as well as other discrete or integrated logic circuits. The functions attributed to the processing circuit 302 herein may be embodied as software, firmware, hardware, or any combination thereof. In some examples, the memory 304 includes computer-readable instructions that, when executed by the processing circuit 302, cause the external device 108 and the processing circuit 302 to perform various functions and / or processes attributed to the external device 108, the network 112, and / or the processing circuit 302 herein. Memory 304 may include any volatile, nonvolatile, magnetic, optical, or electronic media, such as RAM, ROM, NVRAM, EEPROM, flash memory, or any other digital media.

[0045] The processing circuit 302 may determine the HRV signature based on the received heart rate data 110 stored as the sensed data 318. The heart rate data 110 may include a time series of heart rate values ​​associated with episodes or other significant time periods determined by the IMD 106 as described above. The processing circuit 302 may determine the HRV signature by executing instructions from the memory 304 to execute a mathematical algorithm corresponding to each of the HRV signatures. For example, the processing circuit 302 may determine the HRV signature of the average by determining the average of the determined RR intervals.

[0046] In some examples, processing circuitry 302 is configured to determine and / or apply one or more models for predicting the effects of a medical procedure on patient 102. In some examples, the determination and / or application of the models may be implemented by one or more other computing devices, computing systems, and / or cloud computing environments connected to network 112 and / or external device 108. Processing circuitry of a computing device (e.g., processing circuitry 302) may apply one or more models to one or more HRV features and / or one or more clinical features stored in memory 304 and / or received by communication circuitry 306 from one or more EHR systems 114 and / or HMS 116.

[0047] The one or more models may be configured for one or more characteristics of the patient 102. The processing circuit 302 may determine the components of the one or more models (e.g., Figures 6 to 8). In some examples, the processing circuit 302 may determine one or more input values ​​(e.g., HRV features, clinical features) of the one or more models by training using one or more machine learning techniques. The one or more models may include a rule-based expert system and / or a trained ML model. In some examples, the one or more models may include a rule-based expert system, and the processing circuit 302 may determine the rules for the one or more rule-based expert systems, for example, by training using machine learning techniques. In some examples, the one or more models may include one or more trained ML models, and the processing circuit 302 may use machine learning techniques to define and train the one or more trained ML models. In some examples, the processing circuit 302 may automatically define the entirety of the trained ML model by training using machine learning techniques. In some examples, the trained ML model may not include any individual rules. Exemplary machine learning techniques may include, but are not limited to, supervised learning and semi-supervised learning. In some examples, the processing circuit 302 may use one or more algorithms including, but not limited to, Bayesian algorithms, clustering algorithms, decision tree algorithms, regularization algorithms, regression algorithms, instance-based algorithms, artificial neural network algorithms, deep learning algorithms, or dimensionality reduction algorithms to train the one or more models. In some examples, the processing circuit 302 can determine the model by training using machine learning techniques to select input features (e.g., HRV features, clinical features). During training using the ML model, the values ​​of one or more features (e.g., HRV features, clinical features) of the patient 102 are input and the predicted effect of the medical procedure is output. In some examples, the predicted effect is the likelihood of recurrence of the medical condition, such as the likelihood of recurrence of the medical condition within 12 months after the medical procedure is administered.

[0048] The memory 304 is configured to store information within the external device 108, for example for processing during operation of the external device 108. The memory 304 may be described as a computer-readable storage medium. In some examples, the memory 304 includes temporary or volatile memory, including but not limited to random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), or other forms of volatile memory known in the art. In some examples, the memory 304 also includes one or more memories configured for long-term storage of information, such as non-volatile storage elements. Examples of such non-volatile storage elements include magnetic hard disks, optical disks, floppy disks, flash memory, or various forms of electrically programmable memory (EPROM) or electrically erasable and programmable memory (EEPROM). In some examples, the memory 304 includes a storage device associated with the cloud.

[0049] The communication circuit 306 can facilitate communication between the processing circuit 302 of the external device 108 and the IMD 106, the network 112, one or more EHR systems 114, the HMS 116, and / or one or more other computing devices, computing systems, and / or cloud computing environments connected to the network 112. In some examples, the processing circuit 302 can transmit the trained ML model to one or more of the HMS 116, the network 112, or one or more other computing devices, computing systems, and / or cloud computing environments connected to the network 112. The communication circuit 306 can communicate with other devices and / or systems via wired and / or wireless communication technologies. The wireless communication technology may include, for example, RF communication technology via an antenna (not shown). The communication circuit 306 may include a radio transceiver configured for communication based on a wireless communication technology such as 3G, 4G, 5G, WiFi (e.g., 802.11 or 802.15 ZigBee), or Bluetooth Low Energy (BLE) protocol standard for communication.

[0050] UI 308 can be configured to receive input, for example, from patient 102 or another user. Examples of input are tactile input, audio input, dynamic input, or optical input. UI 308 can include a mouse, keyboard, voice response system, camera, button, control pad, microphone, presence-sensitive or touch-sensitive component (e.g., screen), or any other device for detecting input from a user.

[0051] The UI 308 may also be configured to generate output, for example, to the patient 102 or another user. Examples of output include tactile output, haptic output, audio output, or visual output. The UI 308 of the external device 108 may include a presence-sensitive screen, a sound card, a video graphics adapter card, a speaker, a cathode ray tube (CRT) monitor, a liquid crystal display (LCD), a light emitting diode (LED), or any other type of device for generating output to a user.

[0052] In some examples, such as Figure 3 As shown in FIG. 3 , the application 310 may be executed in a user space in the external device 108 . As part of the execution of the application 310 , the processing circuit 302 may apply the one or more models to predict the effects of the medical procedure on the patient 102 .

[0053] The applications 310 stored in the memory 304 may include a health monitoring module 312 (also referred to as a "health monitoring layer 312"), which includes a model engine module 314. The health monitoring module 312 can respond to receiving a user request to predict the effect of a particular medical procedure. The health monitoring module 312 can control the performance of any of the operations, such as predicting the effect of the medical procedure, and outputting the predicted effect to the user, for example, via the UI 308, in response to receiving a user request attributed to the external device 108.

[0054] The model engine module 314 applies one or more models (e.g., a trained ML model as discussed above) to the data of the patient 102. The data of the patient 102 may include HRV features (e.g., as determined based on the heart rate data 110) and / or data corresponding to clinical features of the patient 102. The external device 108 may receive the data of the patient 102 from the IMD 106, one or more EHR systems 114, the HMS 116, and / or the patient 102, for example, via the UI 308.

[0055] Figure 4 It is shown Figure 1 1 is a block diagram of an exemplary health monitoring system (HMS) 116 of the medical device system 100. The HMS 116 can be implemented in one or more computing devices (e.g., the external device 108), one or more computing systems, and / or a cloud computing environment, and can include hardware components (such as those of the external device 108), for example, processing circuits, memory, and communication circuits embodied in one or more physical devices. Figure 4 Provides an operational perspective of the HMS 116 when hosted as a cloud-based platform. Figure 4 In the example of FIG. 1 , the components of HMS 116 are arranged according to multiple logical layers that implement the techniques of the present disclosure. Each layer can be implemented by one or more modules including hardware, software, or a combination of hardware and software.

[0056] Computing devices and / or systems (such as external devices 108 and network 112) operate as clients that communicate with HMS 116 via interface layer 400. Computing devices and / or systems typically implement client software applications, such as desktop applications, mobile applications, and web applications. Interface layer 400 represents a collection or protocol interface of application programming interfaces (APIs) presented and supported by HMS 116 for client software applications. Interface layer 400 can be implemented with one or more web servers.

[0057] like Figure 4As shown, HMS116 also includes an application layer 402, which represents a collection of services 404 for implementing the functionality attributed to HMS116 in this article. The application layer 402 receives information from a client application, for example, receives heart rate data 110 and / or data about HRV features and / or clinical features from an external device 108 and / or a network 112, and further processes the information in response to the information according to one or more services in the service 404. The application layer 402 can be implemented as one or more discrete software services 402 implemented on one or more application servers (e.g., physical or virtual machines). That is, the application server provides a runtime environment for implementing the service 402. In some examples, the functional interface layer 400 and the functionality of the application layer 402 as described above can be implemented at the same server. The service 404 can communicate via a logical service bus 410. The service bus 410 generally represents a logical interconnection or interface set that allows different services 404 to send messages to other services such as through a publish / subscribe communication model.

[0058] The data layer 406 of HMS116 uses one or more data repositories 416 to provide persistence for information in the medical device system 100. The data repository 416 can generally be any data structure or software that stores and / or manages data. To name a few, examples of the data repository 416 include, but are not limited to, relational databases, multidimensional databases, mappings, and hash tables. The data repository 416 may include, but is not limited to, models 418, sensory data 420, and clinical data 422. The sensory data 420 may include data of the patient 102 and / or other patients corresponding to the HRV characteristics. The clinical data 422 may include data of the patient 102 and / or other patients corresponding to the clinical characteristics.

[0059] like Figure 4 As shown, each of services 408, 412, and 414 is implemented in a module form within HMS 116. Although shown as a separate module for each service, in some examples, the functionality of two or more services can be combined into a single module or component. Each of services 408, 412, and 414 can be implemented in software, hardware, or a combination of hardware and software. In addition, services 408, 412, and 414 can be implemented as independent devices, separate virtual machines or containers, processes, threads, or software instructions that are generally used to be implemented on one or more physical processors.

[0060] The health monitoring service 408 may monitor and record data about the patient 102. The data about the patient 102 may include, but is not limited to, the heart rate data 110, data about HRV characteristics of the patient 102, or data about clinical characteristics of the patient 102. The health monitoring service 408 may monitor and record data automatically or based on user input, such as through the external device 108 and the network 112. The health monitoring service 408 may receive data from one or more of the external device 108, the EHS system 114, or one or more other computing devices, computing systems, or cloud computing environments connected to the network 112 (e.g., via the network 112).

[0061] The records management service 414 can store the data recorded by the health monitoring service 408 in a data repository 416 (e.g., in a sensory data repository 420, in a clinical data repository 422, etc.). The rule configuration service 412 can determine the one or more models based on the data stored in the data repository 416. The rule configuration service 412 can train the ML model using information retrieved from the data repository 416. The data repository 416 can contain data about HRV features and clinical features of the patient 102 and / or other patients.

[0062] Each ML model may include one or more classification algorithms (also referred to as "classifiers"). Each of the one or more classifiers may be configured to generate a predicted effect of a medical procedure based on an input (e.g., data about patient 102). The classifier may include a single classifier that uses a single model to generate predictions, and / or an integrated classifier that can combine multiple models to generate predictions. A single classifier may include, but is not limited to, a support vector machine with a linear kernel (SVM), a polynomial kernel (SVMp), or a Gaussian kernel (SVMg). An integrated classifier may include, but is not limited to, classification and regression trees (CART) or K nearest neighbor analysis (KNN).

[0063] Each ML model in the ML model may include a weight value corresponding to each classifier in the classifiers included in the ML model. During application, the ML model may determine the predicted effect of the medical procedure based on the predicted effect of each classifier in the classifiers and the weight value assigned to each classifier in the classifiers of the ML model. For example, when applying the ML model, the processing circuit 302 may give a larger weight to a specific classifier based on the weight value assigned to the classifier. During training of the ML model, the rule configuration service 412 may assign a weight value to each classifier in the classifier. In some examples, where the predicted effect of the medical procedure is binary (e.g., recurrence of a medical condition or non-recurrence of a medical condition), the prediction of each classifier in the classifier is represented by a corresponding voting vector (e.g., a voting vector 1 for recurrence prediction or a voting vector 0 for non-recurrence prediction).

[0064] As part of training the ML model, the rule configuration service 412 can select one or more features from the HRV features and the clinical features (collectively referred to as "available features"). The ML model can include a plurality of time slots, each of the plurality of time slots being configured to accept features from the available features. The ML model can be configured to input data corresponding to each of the features included in the plurality of time slots into the classifier for each of the classifiers in the ML model to generate a corresponding predicted effect of the medical procedure.

[0065] As part of training the ML model, the rule configuration service 412 may include in separate stages one or more forward selection stages, one or more classification stages, and one or more backward selection stages. The forward selection stage may be configured to select features from the available features and determine optimal placement of the selected features in the plurality of time slots within the ML model. In some examples, the one or more forward selection stages may include application of a sequential forward floating search (SFFS) algorithm.

[0066] As part of the forward selection phase, the model configuration module 412 may select a first feature from the available features and place the first feature into a first time slot in the plurality of time slots. As part of the classification phase, the model configuration module 412 may determine a range of possible weight values ​​for each of the classifiers in the ML model. In some examples, the processing circuit 302 assigns equal weights to all classifiers in the ML model (also referred to as an "average voting method"). In some examples, the model configuration module 412 assigns weights to each of the classifiers based on the accuracy of the classifier (also referred to as an "accuracy-weighted voting method"). In some examples, the model configuration module 412 assigns weights to each of the classifiers based on a plurality of weight configurations with different weight steps (e.g., with a weight step of 0.1) (also referred to as an "optimal weighted voting method"). The model configuration module 412 may determine the range of possible weight values ​​based on one or more of an average voting method, an accuracy-weighted voting method, or an optimal weighted voting method.

[0067] The model configuration module 412 may apply input data from previous patients regarding the selected features to each combination of possible weight values ​​from a range of possible weight values ​​and a position of the selected features in each of the plurality of time slots to determine an optimal combination of weight values ​​and placement of the selected features within the ML model. In some examples, the optimal combination of selected features is a combination of weight values ​​and placement of the selected features that maximizes the accuracy of the ML model regarding the selected features. The model configuration module 412 may iteratively perform a forward selection phase and a classification phase to select features and place the features into available time slots in the plurality of time slots of the ML model until a threshold number of features are selected. The threshold number of selected features may be four or more features.

[0068] During the backward selection phase, the model configuration module 412 may remove selected features that reduce the accuracy of the ML model from the plurality of time slots. In some examples, during the backward selection phase, the model configuration module 412 iteratively removes each of the selected features in the ML model and determines the accuracy of the ML model without the removed features. If the model configuration module 412 determines that the removal of the feature increases the accuracy of the ML model, the model configuration module 412 may permanently remove the feature from the ML model and return to the backward selection phase and / or the forward selection phase. If the model configuration module 412 determines that the removal of the feature does not increase the accuracy of the ML model, the model configuration module 412 may leave the feature in the ML model and / or may designate the feature as a verified feature. In some examples, the model configuration module 412 performs a backward selection phase on the ML model based on determining that the ML model contains a threshold number of selected features.

[0069] The model configuration module 412 may train the ML model by iteratively applying a forward selection phase, a classification phase, and a backward selection phase, for example, until the ML model meets a threshold average accuracy for predicting an effect. Once the model configuration module 412 determines that the ML model is trained, the HMS 116 may store the ML model in a data repository 416, for example, in a model 418 of the data repository 416. In some examples, the HMS 116 may transmit the trained ML model to an external device 108 for storage in a memory 304 of the external device 108, for example, in a model engine module 314. The processing circuit 302 may then execute computer-readable instructions corresponding to the trained ML model stored in the model engine module 314 to apply the model to data about the patient 102 (e.g., data about HRV features and / or clinical features) to predict the effect of a particular medical procedure on the patient 102.

[0070] Figure 5 It is shown by Figure 11. Conceptual diagram of an exemplary set 500 of heart rate data 110 recorded by an IMD 106 of a medical device system 100. Figure 5 The description is made with heart rate data 110 represented as RR intervals over time and with AF as the medical condition. However, in other examples, other representations of heart rate data 110 may also be used for other types of medical conditions.

[0071] Figure 5 The medical condition (AF episode 508, such as Figure 5 508) and a flashback period 502 immediately before the occurrence. The flashback period 502 can be divided into a first flashback period 504 and a second flashback period 506. The first flashback period 504 can represent a first set number (e.g., 100, 200, 300, etc.) of RR intervals in the flashback period 502. The second flashback period 506 can represent a second set number (e.g., 100, 200, etc.) of RR intervals immediately before the AF episode 508. Figure 5 As shown, there may be short-term variations in the duration of the RR intervals in the flashback period 502 prior to the AF episode 508. For example, the RR intervals in the first flashback period 504 are relatively longer than the RR intervals in the second flashback period 506.

[0072] In some examples, the medical device system 100 determines the HRV features from the heart rate data 110 by determining the HRV features of one or more of the flashback period 502, the first flashback period 504, the second flashback period 506, and the AF episode 508. In some examples, the medical device system 100 determines the mean, pNNX, RMSSD, SDNN, TINN, TRI, APEn, SamPEn, SD1, SD2, SD1:SD2 ratio, DFAα1, and / or DFAα2 of one or more of the flashback period 502, the first flashback period 504, the second flashback period 506, or the AF episode 508. During the training of the ML model, the medical device system 100 may select the HRV features corresponding to any or all of the flashback period 502, the first flashback period 504, the second flashback period 506, or the AF episode 508.

[0073] Figure 6 is a conceptual diagram illustrating an exemplary neural network 600 configured to predict the effects of a medical procedure. Figure 6A model including a neural network 600 is described, but other exemplary models described herein may include other ML and / or non-ML techniques and models. The neural network 600 may include an input layer 602, a hidden layer 604, and an output layer 606. The neural network 600 may be stored in a memory of one or more computing devices, computing systems, and / or cloud computing environments (e.g., in model 322 and / or model 418).

[0074] Input layer 602 includes inputs 608A to 608D (collectively referred to as "inputs 608"). Each of inputs 608 can represent a source of data input into neural network 600. In some examples, each of inputs 608 can represent a different HRV feature or clinical feature. In some examples, each of inputs 608 can represent a combination of HRV features and / or clinical features, such as Figure 7 Described in more detail in .

[0075] The input layer 602 may be connected to the hidden layer 604, and the input 608 may be transmitted to the hidden layer 604. The hidden layer 604 may include layers 610A to 610N (collectively referred to as "layers 610"), each of which includes one or more nodes 612. The hidden layer 604 may weight and / or aggregate the input 608 to produce an output (e.g., a predicted effect of a medical procedure) based on the input data. The structure of the hidden layer 604 (e.g., the number of layers 610, the number of nodes 612, the deployment of paths between nodes 612) and / or the function of the hidden layer 604 (e.g., how the input 608 is aggregated, how the input 608 is weighted) may vary based on the desired output. In some examples, one or more computing devices, computing systems, and / or cloud computing environments (e.g., external device 108, HMS 116, etc.) can determine and / or adjust the number of layers 610, the structure of each layer 610, the weighting of each input in input 608, and / or the manner in which input 608 is aggregated via one or more ML training techniques, for example, as previously discussed herein.

[0076] Hidden layer 604 may determine outputs 614A-614B (collectively, "outputs 614") of output layer 606 based on input 608 and the functions performed by hidden layer 604. Output 614 may include, but is not limited to, the probability of one or more medical conditions occurring within a specific time period. For example, output 614A may correspond to the probability of an AF episode occurring within a specific time period after a medical procedure, and output 614B may correspond to the probability of another condition occurring within a specific time period after a medical procedure.

[0077] Figure 7 is a conceptual diagram illustrating an exemplary process for inputting data into an exemplary model for predicting the effects of a medical procedure. Figure 7 The exemplary model is shown as ML model 710, but other examples may include rule-based models (eg, rule-based expert systems).

[0078] The input data 702 of the ML model 710 may be represented as multiple arrays 704A-704B (collectively, "multiple arrays 704"). Each of the multiple arrays 704 may store a plurality of inputs 706A-706B (collectively, "inputs 706"). Each of the inputs 706 may represent an HRV feature or a clinical feature. Each of the multiple arrays 704 may store the value of the input 706 and the position of the value of the input 706 within a corresponding tensor representation in tensor representations 712A-712B (collectively, "tensor representations 712").

[0079] The location of a particular value within the corresponding tensor representation 712 may be represented by a label (e.g., labels A1 to A4, B1 to B4) stored in the multi-way array 704 and a port 708. Each of the plurality of labels may have a corresponding value of a feature represented by a corresponding input in the inputs 706. Each of the ports 708 may represent a data input point (e.g., input 608) into the classifier 714. For each combination of inputs 706A and 706B stored in the multi-way array 704, the corresponding tensor representation 712 may represent the combination of values ​​of the inputs 706 via a vector. As shown in FIG. Figure 7 As shown, the combination of inputs 706 and the placement of the combination of inputs 706 within tensor representation 712B may be different depending on the desired output.

[0080] The multi-way array 704 can be represented as tensor representations 712, which can be input into a classifier 714 of the ML model 710 to generate corresponding outputs 716A-716B (collectively, "outputs 716"). Each of the outputs 716 can each represent the likelihood of a particular predicted effect of a medical procedure. Figure 7 The tensor representation 712 shown in is a third-order tensor, but other examples may include first-order, second-order, or fourth-order or higher-order tensors as inputs to the exemplary model.

[0081] Figure 8 is a block diagram illustrating an exemplary process for training an exemplary model for predicting the effects of a medical procedure. Figure 8 The example processes described are primarily described with reference to a computing system, but may be performed using one or more computing devices, computing systems, and / or cloud computing environments (e.g., external device 108, HMS 116, etc.). The computing system may generate an ML model 804 (e.g., with randomly assigned weights and / or structure).

[0082] The computing system can input the training data 802 into the ML model to generate predictions 806. The training data 802 may include corresponding values ​​of one or more HRV features and / or clinical features. In some examples, the corresponding values ​​of the one or more features may include, for example, sensory data of the one or more features from the patient 102 and / or one or more other persons. The corresponding values ​​may be organized into training instances of a training set of the training data 802. In some examples, each training instance may correspond to corresponding values ​​of HRV features and clinical features of a single person after a medical procedure. In some examples, each training instance may correspond to aggregate values ​​of HRV features and clinical features of multiple similar individuals who have undergone medical procedures. In some examples, multiple training instances may correspond to a single individual, and each of the multiple training instances corresponds to corresponding values ​​of HRV features and clinical features of the individual after a corresponding medical procedure in multiple medical procedures that the individual has undergone. In some examples, after the computing system receives a corresponding determined effect of a medical procedure (e.g., via IMD 106, UI 308 of external device 108, etc.), the computing system generates one or more training instances of a set of training instances based on one or more heart rate variability features and one or more clinical features.

[0083] The computing system may perform a comparison 808 between the prediction 806 and a target output 810. The target output 810 may include a determined effect of the medical procedure corresponding to the training instance of the training data 802. The computing system may determine error data 812 between the prediction 806 and the target output 810 based on the comparison 808. In some examples, the computing system may, for each training instance in the training set, modify the model to change the likelihood predicted by the model for the particular predicted effect associated with the particular value, based on the particular value and the particular determined effect of the medical procedure, in response to subsequent values ​​of the one or more of the one or more heart rate variability features or the one or more clinical features applied to the model.

[0084] Based on the error data 812, the computing system may apply a training algorithm 814 (also referred to as a “learning algorithm 814”) to adjust the weights and / or structure of the ML model 804. The computing system may then transmit the adjustments 816 to the ML model 804 and adjust the ML model 804 based on the adjustments 816. The computing system may then input subsequent data from the training data 802 and perform the process until the prediction 806 differs from the target output 810 by less than a predetermined amount (e.g., less than a predetermined percentage).

[0085] Fig. 9 is a flow chart illustrating an exemplary process for predicting the effects of a medical procedure. Figure 1In some examples, an IMD (e.g., IMD 106) of medical device system 100 may collect heart rate data 110 from heart 104 of patient 102 (902). In some examples, an IMD (e.g., IMD 106) of medical device system 100 may collect heart rate data 110 via one or more electrodes (e.g., electrodes 202) electrically connected to the patient's heart 104. IMD 106 may collect heart rate data 110 by monitoring and recording heart rate data 110, for example, based on information about Figure 2 In some examples, heart rate data 110 is collected as QRS complexes corresponding to ventricular depolarization of heart 104. In some examples, IMD 106 identifies R waves within the collected QRS complexes.

[0086] The medical device system 100 may determine a HRV (HRV) characteristic (904) based on the heart rate data 110. The external device 108, the HMS 116, and / or one or more computing devices, computing systems, and / or cloud computing environments connected to the network 112 of the medical device system 110 may be configured to determine the HRV characteristic. The HRV characteristic may include, but is not limited to: mean, pNNX, RMSSD, SDNN, TINN, TRI, APEn, SamPEn, SD1, SD2, SD1:SD2 ratio, DFAα1, and / or DFAα2. The HRV characteristic may be determined for one or more of the flashback period 502, the first flashback period 504, the second flashback period 506, or the AF episode 508, for example, as Figure 5 In some examples, the HRV signature is further stored in the external device 108 , the HMS 116 , the EHS system 114 , and / or one or more computing devices, computing systems, and / or cloud computing environments connected to the network 112 .

[0087] The medical device system 100 may apply the model to the HRV features and the clinical features to predict the effect of the medical procedure (906). The effect of the medical procedure may include the efficacy of the procedure and the likelihood of recurrence of the target medical condition. In some examples, the predicted effect of the medical procedure includes the predicted recurrence and / or non-recurrence of the target medical condition (e.g., AF) within a set period of time (e.g., within 12 months) after the medical procedure is performed. The medical device system 100 may apply the model by inputting data of the patient 102 corresponding to the features from the HRV features and / or clinical features set in the model, and outputting a prediction result based on the application of the model. In some examples, the medical device system 100 may input the values ​​determined for the one or more HRV features and the one or more clinical features into the model, and use the model and based on the input determined values ​​to generate multiple possible effects of the medical procedure. The medical device system 100 may use the model to determine the corresponding likelihood of occurrence of each of the multiple possible effects, and select a predicted effect from the multiple possible effects. The medical device system 100 may select a predicted effect from the multiple possible effects based on the corresponding likelihood of occurrence. In some examples, the medical device system 100 may select the possible effect with the highest likelihood of occurrence as the predicted effect.

[0088] The medical device system 100 may output the predicted effect to a user (908). In some examples, the user includes a medical professional and / or a patient 102. The medical device system 100 may output the predicted effect to a user interface (e.g., UI 308) of the external device 108 or to one or more separate display devices connected to the network 112. The information output to the user may include, but is not limited to, the predicted effect (e.g., recurrence / non-recurrence of a medical condition), features of the medical device system 100 used to determine the predicted effect, the likelihood of the predicted effect (e.g., in percentages), the prediction of each of the one or more classifiers used by the medical device system 100 to determine the predicted effect, and the like.

[0089] Fig.10 is a flow chart illustrating an exemplary process for generating a model for predicting the effects of a medical procedure. Specifically, Fig.10 An exemplary process for generating a model by training an ML model is described. The medical device system 100 can generate a model by applying a forward selection phase 1000 and a backward selection phase 1002 to select features for the model. The forward selection phase 1000 can include a classification phase.

[0090] In the forward selection stage 1000, the medical device system 100 may select a first feature from a plurality of features (1004). The plurality of features may include HRV features and / or clinical features. The HRV features may include HRV features of the flashback period 502, the first flashback period 504, the second flashback period 506, or the AF episode 508, for example, Figure 5 As described in. The medical device system 100 may apply forward selection regression to the first feature (1006). Forward selection regression may include an SFFS algorithm. As part of forward selection regression, the medical device system 100 may apply a classification stage to select a weight value from a range of weight values ​​for each classifier in one or more classifiers in the model. The weight value may indicate how much weight the medical device system 100 should give to each of the predictive effects of the classifier when determining the overall predictive effect. The medical device system 100 may generate the weight value range using one or more methods including but not limited to an average voting method, an accuracy weighted voting method, or an optimal weighted voting method. The medical device system 100 may select a weight value that maximizes the accuracy of the prediction of the classifier for each classifier in the classifier. As part of applying forward selection regression to the first feature, the medical device system 100 may determine the optimal placement of the first feature in a plurality of feature time slots of the model, wherein the optimal placement of the first feature may be a time slot in the plurality of time slots that maximizes the accuracy of the model. The medical device system 100 may determine the weight values ​​of the classifier and the optimal placement of the first feature by using data from previous patients as input to the model and comparing the predicted effect of the model with the actual effect of the medical procedure on the previous patient.

[0091] The medical device system 100 may determine (e.g., based on the results of the forward selection regression) whether the first feature increases the accuracy of the model (1008). If the first feature does not increase the accuracy (the "no" branch of 1008), the medical device system 100 may reject the first feature and select a new feature from the plurality of features (1004). If the first feature increases the accuracy (the "yes" branch of 1008), the medical device system 100 may position the first feature within the model, e.g., at an optimal placement within the model (1010).

[0092] The medical device system 100 may determine whether the model includes a minimum number of features (1012). If the model does not include a minimum number of features (the "no" branch of 1012), the medical device system 100 may iteratively perform the forward selection phase 1000 (e.g., steps 1004 to 1010) until the model includes the minimum number of features. If the model includes the minimum number of features (the "yes" branch of 1012), the medical device system 100 may proceed to the backward selection phase 1002 (e.g., step 1014).

[0093] During the backward selection phase 1002, the medical device system 100 may select a second feature within the model (1014). The medical device system 100 may apply backward selection regression to the second feature (1016). As part of applying the backward selection regression, the medical device system 100 may remove the second feature from the model and determine the accuracy of the model without the second feature. Based on determining that removing the second feature increases the accuracy of the model (the "yes" branch of 1018), the medical device system 100 removes the second feature from the model (1020) and selects a new feature within the model (1014) to apply the backward selection phase 1002. Based on determining that removing the second feature does not increase the accuracy of the model (the "no" branch of 1018), the medical device system 100 repositions the second feature within the model and selects a new, different feature within the model (1014) to apply the backward selection phase 1002. The medical device system 100 may also designate the second feature as a validated feature.

[0094] The medical device system 100 may determine whether the model satisfies a threshold accuracy condition (1022). In some examples, the threshold accuracy condition may be predetermined. In some examples, the threshold accuracy condition is the maximum achievable accuracy of the model. If the medical device system 100 determines that the model satisfies the threshold accuracy condition (the "yes" branch of 1022), the medical device system 100 may complete the model generation process. If the medical device system 100 determines that the model does not satisfy the threshold accuracy condition (the "no" branch of 1022), the medical device system 100 may select a new feature from a plurality of features (1004) and repeat the forward selection phase 1000 and the backward selection phase 1002. The medical device system 100 may repeat the above exemplary process until the model satisfies the threshold accuracy condition.

[0095] The devices, systems and techniques of the present disclosure provide improvements over other prediction systems. The incorporation of HRV features and clinical features from medical devices enables improved prediction of recurrence of medical conditions in a patient's heart before performing a medical procedure. In some examples, the present disclosure further describes the generation of models used in predicting the effects of medical procedures. These models can incorporate portions of HRV features and clinical features to increase the accuracy of predictions of the effects of medical procedures.

[0096] The technology of the present disclosure can be implemented in a wide range of computing devices, medical devices, or any combination thereof. Any of the units, modules, or components can be implemented together or individually as discrete but interoperable logic devices. Describing different features as modules or units is intended to highlight different functional aspects, and does not necessarily imply that such modules or units must be implemented by separate hardware or software components. On the contrary, the functions associated with one or more modules or units can be performed by separate hardware or software components, or integrated in common or separate hardware or software components.

[0097] The present disclosure contemplates a computer-readable storage medium including instructions that cause a processor to perform any of the functions and techniques described herein. The computer-readable storage medium may take the exemplary form of any volatile, non-volatile, magnetic, optical, or electrical medium such as RAM, ROM, NVRAM, EEPROM, or tangible flash memory. The computer-readable storage medium may be referred to as non-transient. The server, client computing device, or any other computing device may also include a more portable type of removable memory to enable easy data transfer or offline data analysis.

[0098] The techniques described in this disclosure, including those attributed to various modules and various component parts, may be implemented at least in part in hardware, software, firmware, or any combination thereof. For example, various aspects of these techniques may be implemented within one or more processors, including one or more microprocessors, DSPs, ASICs, FPGAs, or any other equivalent integrated discrete logic circuits or other processing circuits, as well as any combination of such components, remote servers, remote client devices, or other devices. The term "processor" or "processing circuit" may generally refer to any of the foregoing logic circuits, alone or in combination with other logic circuits, or any other equivalent circuits.

[0099] Such hardware, software, firmware may be implemented in the same device or in separate devices to support the various operations and functions described in this disclosure. In addition, any of the described units, modules or components may be implemented together or individually as discrete but interoperable logic devices. Describing different features as modules or units is intended to highlight different functional aspects, and does not necessarily imply that such modules or units must be implemented by separate hardware or software components. On the contrary, the functions associated with one or more modules or units may be performed by separate hardware or software components, or integrated in common or separate hardware or software components. For example, any module described herein may include a circuit configured to perform the features attributed to the particular module, such as a fixed-function processing circuit, a programmable processing circuit, or a combination thereof.

[0100] The techniques described in the present disclosure may also be embedded or encoded in an article comprising a computer-readable medium encoded with instructions. The instructions embedded or encoded in the article comprising a coded computer-readable storage medium may cause one or more programmable processors or other processors to implement one or more of the techniques described herein, such as when the instructions included or encoded in the computer-readable storage medium are implemented by one or more processors. Exemplary computer-readable storage media may include random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash memory, hard disk, compact disk ROM (CD-ROM), floppy disk, cassette, magnetic media, optical media, or any other computer-readable storage device or tangible computer-readable medium. Computer-readable storage media may also be referred to as storage devices.

[0101] In some examples, computer-readable storage media include non-transitory media. The term "non-transitory" may indicate that the storage media is not embodied in a carrier wave or propagating signal. In some examples, non-transitory storage media may store data that may change over time (e.g., in RAM or cache).

[0102] It should be noted that the medical device system 100 and the techniques described herein may not be limited to use in human patients. In alternative examples, the medical device system 100 may be implemented in non-human patients, such as primates, canines, equines, pigs, and felines. These other animals may undergo clinical or research treatments that may benefit from the disclosed subject matter. Various embodiments are described herein, such as the following embodiments.

[0103] Embodiment 1: A computing system comprising: a memory configured to store heart rate data; a display device; and a processing circuit configured to: collect the patient's heart rate data from the patient's medical device; determine one or more heart rate variability features based on the heart rate data; apply a model to the one or more heart rate variability features and one or more clinical features of the patient; predict the effect of a medical procedure on the patient based on the application of the model to the one or more heart rate variability features and the one or more clinical features; and output the predicted effect of the medical procedure to the display device.

[0104] Embodiment 2: The computing system of embodiment 1, wherein the heart rate data comprises a plurality of time intervals corresponding to time periods between electrical signals recorded by the medical device, the electrical signals corresponding to depolarization of a first chamber of the patient's heart.

[0105] Embodiment 3: The computing system of Embodiment 2, wherein the electrical signals include QRS complexes detected by the medical device, and wherein the time period includes the time between R waves of adjacent QRS complexes.

[0106] Embodiment 4: A computing system according to any one of embodiments 1 to 3, wherein the one or more heart rate variability characteristics include: an average value of the multiple time intervals; a mean square error of adjacent time intervals in the multiple time intervals; a standard deviation of the multiple time intervals; or a percentage of the multiple time intervals that meet a threshold time condition.

[0107] Embodiment 5: A computing system according to any one of embodiments 1 to 4, wherein the one or more clinical characteristics of the patient include one or more of the following: the patient's age; the presence of a disease in the patient; or the length of the patient's monitoring period prior to a past medical procedure.

[0108] Embodiment 6: A computing system according to embodiment 5, wherein the disease includes one or more of the following: paroxysmal atrial fibrillation; hypertension; diabetes; coronary artery disease; lesions; or stroke.

[0109] Embodiment 7: The computing system of any one of Embodiments 5 and 6, wherein the past medical procedure comprises a cardiac ablation procedure.

[0110] Embodiment 8: The computing system of any one of Embodiments 1 to 7, wherein the medical device comprises an implantable cardiac monitor (ICM).

[0111] Embodiment 9: The computing system of any one of Embodiments 1 to 8, wherein the effect of the medical procedure on the patient comprises a recurrence of an episode of atrial fibrillation (AF) experienced by the patient after the medical procedure was performed on the patient.

[0112] Embodiment 10: The computing system of Embodiment 9, wherein the predicted effect of the medical procedure comprises the probability of the recurrence of the AF episode within a set period of time after the medical procedure is performed on the patient.

[0113] Embodiment 11: The computing system of embodiment 10, wherein the set period includes 12 months after the medical procedure is performed.

[0114] Embodiment 12: The computing system of any one of Embodiments 1 to 11, wherein the medical procedure comprises a cardiac ablation procedure.

[0115] Embodiment 13: A computing system according to any one of embodiments 1 to 12, wherein in order to apply the model, the processing circuit is further configured to determine the model, and wherein in order to determine the model, the processing circuit is further configured to: select a first feature among the one or more heart rate variability features and the one or more clinical features for a prediction module; determine a weight value of the first feature based on multiple classifier modules; and generate a second prediction module including the first feature and the weight value.

[0116] Embodiment 14: A computing system according to embodiment 13, wherein to select the first feature, the processing circuit is configured to apply a sequential forward floating search (SFFS) to the one or more heart rate variability features and the one or more clinical features, and wherein to apply the SFFS, the processing circuit is configured to: select the first feature from the one or more heart rate variability features and the one or more clinical features; apply forward selection regression to the prediction module and the first feature; and position the first feature in the prediction module at a position that maximizes the accuracy of the prediction module.

[0117] Embodiment 15: A computing system according to any one of embodiments 13 and 14, wherein, to generate the second prediction module, the processing circuit is further configured to: select a second feature from multiple existing features in the prediction module; apply backward selection regression to the prediction module and the second feature; and remove the second feature from the prediction module based on determining that removing the second feature will increase the accuracy of the prediction module.

[0118] Embodiment 16: A computing system according to any one of Embodiments 13 to 15, wherein in order to determine the weight value, the processing circuit is configured to: apply a weighted voting system to multiple weight vectors and multiple corresponding voting vectors, wherein each weight vector and corresponding voting vector corresponds to one classifier module among the multiple classifier modules; and determine the accuracy of the prediction module associated with each of the multiple weight vectors and the multiple corresponding voting vectors.

[0119] Embodiment 17: A computing system according to Embodiment 16, wherein at least one classifier module among the plurality of classifier modules comprises a machine learning model.

[0120] Embodiment 18: The computing system of any one of Embodiments 13 to 17, wherein the plurality of classifier modules comprises at least five classifier modules.

[0121] Embodiment 19: A computing system according to any one of Embodiments 1 to 18, wherein the processing circuit is configured to generate the model, and wherein in order to generate the model, the processing circuit is configured to: select a training set comprising a set of training instances, each training instance comprising an association between a corresponding value of the one or more heart rate variability characteristics or one or more of the one or more clinical characteristics and a determined effect of the medical procedure; and for each training instance in the training set, in response to subsequent values ​​of the one or more heart rate variability characteristics or one or more of the one or more clinical characteristics applied to the model, modify the model to change the likelihood predicted by the model for the specific predicted effect associated with the specific value based on the specific value and the specific determined effect of the medical procedure.

[0122] Embodiment 20: The computing system of Embodiment 19, wherein the corresponding values ​​include sensed values ​​of one or more of the one or more heart rate variability characteristics or the one or more clinical characteristics from one or more other persons.

[0123] Embodiment 21: A computing system according to any one of embodiments 19 and 20, wherein the processing circuit is configured to generate one or more training instances of the training instance set based on the one or more heart rate variability features and the one or more clinical features after the computing system receives the corresponding determined effect of the medical procedure.

[0124] Embodiment 22: A computing system according to any one of embodiments 1 to 21, wherein in order to predict the effect of the medical procedure on the patient based on the application of the model to the one or more heart rate variability characteristics and the one or more clinical characteristics, the processing circuit is configured to: input determined values ​​of the one or more heart rate variability characteristics and the one or more clinical characteristics into the model; use the model and generate multiple possible effects of the medical procedure based on the input determined values; use the model to determine a corresponding likelihood of occurrence of each corresponding possible effect in the multiple possible effects; and select a predicted effect of the medical procedure from the multiple possible effects based on the corresponding likelihood of occurrence.

[0125] Embodiment 23: A method, comprising: a computing system collecting heart rate data of a patient from a medical device of the patient; the computing system determining one or more heart rate variability characteristics based on the heart rate data; the computing system applying a model to these heart rate variability characteristics and one or more clinical characteristics of the patient; the computing system predicting the effect of a medical procedure on the patient based on the application of the model to these heart rate variability characteristics and the one or more clinical characteristics; and the computing system outputting the predicted effect of the medical procedure to a display device.

[0126] Embodiment 24: A method according to Embodiment 23, wherein the heart rate data includes multiple time intervals corresponding to electrical signals recorded by the medical device, which electrical signals correspond to depolarization of the first chamber of the patient's heart.

[0127] Embodiment 25: The method of Embodiment 24, wherein the electrical signals include QRS complexes detected by the medical device, and wherein the time period includes the time between R waves of adjacent QRS complexes.

[0128] Embodiment 26: A method according to any one of embodiments 24 and 25, wherein the one or more heart rate variability characteristics include one or more of the following: an average value of multiple time intervals; a mean square error of adjacent time intervals in the multiple time intervals; or a standard deviation of the multiple time intervals.

[0129] Embodiment 27: A method according to any one of embodiments 24 to 26, wherein the one or more heart rate variability characteristics include a percentage of the multiple time intervals that meet a threshold time condition.

[0130] Embodiment 28: A method according to Embodiment 27, wherein the threshold time condition is between 10 milliseconds (ms) and 70 ms.

[0131] Embodiment 29: A method according to any one of Embodiments 23 to 28, wherein the one or more clinical characteristics of the patient include one or more of the following: the patient's age; the presence of a disease in the patient; or the length of the patient's monitoring period prior to a past medical procedure.

[0132] Embodiment 30: The method according to embodiment 29, wherein the disease comprises one or more of the following: paroxysmal atrial fibrillation; hypertension; diabetes; coronary artery disease; lesions; or stroke.

[0133] Example 31: A method according to any one of Examples 29 and 30, wherein the past medical procedure includes a cardiac ablation procedure.

[0134] Embodiment 32: The method according to any one of Embodiments 23 to 31, wherein the medical device comprises an implantable cardiac monitor (ICM).

[0135] Embodiment 33: The method of any one of Embodiments 23 to 32, wherein the effect of the medical procedure on the patient comprises a recurrence of an episode of atrial fibrillation (AF) experienced by the patient after the medical procedure was performed on the patient.

[0136] Embodiment 34: The method according to Embodiment 33, wherein the predicted effect of the medical procedure includes the probability of the recurrence of the AF episode within a set period of time after the medical procedure is performed on the patient.

[0137] Embodiment 35: A method according to Embodiment 34, wherein the set period includes 12 months after performing the medical procedure.

[0138] Embodiment 36: A method according to any one of embodiments 23 to 35, wherein the medical procedure comprises a cardiac ablation procedure.

[0139] Embodiment 37: According to the method described in any one of Embodiments 23 to 36, the method further comprises determining the model by at least the following steps: selecting, by the computing system, a first feature among the one or more heart rate variability features and the one or more clinical features for a prediction module; determining, by the computing system, a weight value of the first feature based on a plurality of classifier modules; and generating, by the computing system, a second prediction module including the first feature and the weight value.

[0140] Embodiment 38: A method according to Embodiment 37, wherein selecting the first feature includes applying, by the computing system, a sequential forward floating search (SFFS) to the one or more heart rate variability features and the one or more clinical features, wherein applying the SFFS includes: selecting, by the computing system, the first feature from among the one or more heart rate variability features and the one or more clinical features; applying, by the computing system, a forward selection regression to the prediction module and the first feature; and positioning, by the computing system, the first feature at a position in the prediction module that maximizes the accuracy of the prediction module.

[0141] Embodiment 39: A method according to any one of embodiments 37 and 38, wherein generating the second prediction module further comprises: selecting, by the computing system, a second feature from a plurality of existing features in the prediction module; applying, by the computing system, backward selection regression to the prediction module and the second feature; and removing, by the computing system, the second feature from the prediction module based on determining that removing the second feature will increase the accuracy of the prediction module.

[0142] Embodiment 40: A method according to any one of Embodiments 37 to 39, wherein determining the weight value comprises: applying, by the computing system, a weighted voting system to a plurality of weight vectors and a plurality of corresponding voting vectors, wherein each weight vector and the corresponding voting vector corresponds to a classifier module among the plurality of classifier modules; and determining the accuracy of the prediction module associated with each of the plurality of weight vectors and the plurality of corresponding voting vectors.

[0143] Embodiment 41: A method according to any one of Embodiments 37 to 39, wherein determining the weight value comprises: applying one or more classifier modules among the plurality of classifier modules to the one or more heart rate variability features and the one or more clinical features; and determining the accuracy of the prediction module associated with each of the plurality of weight vectors and the plurality of corresponding voting vectors.

[0144] Embodiment 42: The method according to claim 41, wherein at least one classifier module among the plurality of classifier modules comprises a machine learning model.

[0145] Embodiment 43: The method according to any one of Embodiments 37 to 42, wherein the plurality of classifier modules comprises at least five classifier modules.

[0146] Embodiment 44: According to the method described in any one of Embodiments 23 to 43, the method further includes generating the model by the computing system, and wherein generating the model includes: selecting, by the computing system, a training set comprising a set of training instances, each training instance comprising an association between corresponding values ​​of the one or more heart rate variability features or one or more of the one or more clinical features and a determined effect of the medical procedure; and for each training instance in the training set, in response to subsequent values ​​of the one or more heart rate variability features or one or more of the one or more clinical features applied to the model, modifying, by the computing system, the model to change the likelihood predicted by the model for the specific predicted effect associated with the specific value based on the specific value and the specific determined effect of the medical procedure.

[0147] Embodiment 45: The method according to Embodiment 44, wherein the corresponding values ​​include sensed values ​​of one or more of the one or more heart rate variability characteristics or the one or more clinical characteristics from one or more other persons.

[0148] Embodiment 46: According to the method described in any one of Embodiments 44 and 45, the method further includes, after the computing system receives the corresponding determined effect of the medical procedure, generating one or more training instances of the training instance set based on the one or more heart rate variability features and the one or more clinical features by the computing system.

[0149] Embodiment 47: A method according to any one of Embodiments 23 to 46, wherein predicting the effect of the medical procedure on the patient based on the application of the model to these heart rate variability characteristics and the one or more clinical characteristics includes: the computing system inputting the determined values ​​of the one or more heart rate variability characteristics and the one or more clinical characteristics into the model; the computing system using the model and generating multiple possible effects of the medical procedure based on the input determined values; the computing system using the model to determine the corresponding likelihood of occurrence of each corresponding possible effect among the multiple possible effects; and the computing system selecting the predicted effect of the medical procedure from the multiple possible effects based on the corresponding likelihood of occurrence.

[0150] Embodiment 48: A computer-readable storage medium comprising instructions which, when executed, cause a processing circuit within a device to perform a method according to any one of Embodiments 23 to 47.

[0151] Various embodiments have been described herein. Any combination of the described operations or functions is contemplated. These and other embodiments are within the scope of the following claims.

Claims

1. A computing system, comprising: a memory configured to store heart rate data; Display device; and A processing circuit, the processing circuit being configured to: collecting heart rate data of the patient from a medical device of the patient; determining one or more heart rate variability characteristics based on the heart rate data; applying a model to the one or more heart rate variability characteristics and one or more clinical characteristics of the patient; predicting an effect of a medical procedure on said patient based on said application of said model to said one or more heart rate variability features and said one or more clinical features; as well as The predicted effect of the medical procedure is output to the display device.

2. The computing system of claim 1, wherein the heart rate data comprises a plurality of time intervals corresponding to time periods between electrical signals recorded by the medical device, the electrical signals corresponding to depolarization of a first chamber of the patient's heart.

3. The computing system of claim 2, wherein the electrical signal comprises a QRS complex detected by the medical device, and wherein the time period comprises a time between R waves of adjacent QRS complexes.

4. The computing system of any one of claims 1 to 3, wherein the one or more heart rate variability features include: an average value of the plurality of time intervals; a mean square error of adjacent time intervals in the plurality of time intervals; a standard deviation of the plurality of time intervals; or A percentage of the plurality of time intervals that meet a threshold time condition.

5. The computing system of any one of claims 1 to 4, wherein the one or more clinical characteristics of the patient include one or more of the following: the patient's age; The presence of a disorder in the patient; or The length of the patient's monitoring period prior to the patient's past medical procedure.

6. The computing system of claim 5, wherein the condition comprises one or more of: Paroxysmal atrial fibrillation; hypertension; diabetes; Coronary artery disease; lesions; or Stroke.

7. The computing system of any one of claims 5 and 6, wherein the past medical procedure comprises a cardiac ablation procedure.

8. The computing system of any one of claims 1 to 7, wherein the effect of a medical procedure on the patient comprises a recurrence of an episode of atrial fibrillation (AF) experienced by the patient after the medical procedure was performed on the patient.

9. The computing system of claim 8, wherein the predicted effect of the medical procedure comprises a probability of the recurrence of the AF episode within a set period of time after the medical procedure is performed on the patient.

10. The computing system of any one of claims 1 to 9, wherein to apply the model, the processing circuit is further configured to determine the model, and wherein to determine the model, the processing circuit is further configured to: selecting a first feature of the one or more heart rate variability features and the one or more clinical features for a prediction module; Determining a weight value of the first feature based on a plurality of classifier modules; and A second prediction module including the first feature and the weight value is generated.

11. The computing system of claim 10, wherein to select the first feature, the processing circuit is configured to apply a sequential forward floating search (SFFS) to the one or more heart rate variability features and the one or more clinical features, and wherein to apply the SFFS, the processing circuit is configured to: selecting a first feature from the one or more heart rate variability features and the one or more clinical features; applying forward selection regression to the prediction module and the first feature; and The first feature is positioned within the prediction module at a location that maximizes the accuracy of the prediction module.

12. The computing system according to any one of claims 10 and 11, wherein to generate the second prediction module, the processing circuit is further configured to: selecting a second feature from a plurality of existing features in the prediction module; applying backward selection regression to the prediction module and the second feature; and Based on determining that removing the second feature would increase the accuracy of the prediction module, the second feature is removed from the prediction module.

13. The computing system of any one of claims 10 to 12, wherein to determine the weighted value, the processing circuit is configured to: applying a weighted voting system to a plurality of weight vectors and a plurality of corresponding voting vectors, wherein each weight vector and corresponding voting vector corresponds to a classifier module in the plurality of classifier modules; and An accuracy of the prediction module associated with each of the plurality of weight vectors and the plurality of corresponding voting vectors is determined.

14. The computing system of any one of claims 10 to 13, wherein the plurality of classifier modules comprises at least five classifier modules.

15. The computing system of any one of claims 1 to 14, wherein the processing circuit is configured to generate the model, and wherein to generate the model, the processing circuit is configured to: selecting a training set comprising a set of training instances, each training instance comprising an association between a corresponding value of one or more of the one or more heart rate variability features or the one or more clinical features and a determined effect of the medical procedure; and For each training instance in the training set, in response to subsequent values ​​of the one or more heart rate variability features or one or more of the one or more clinical features applied to the model, the model is modified to change the likelihood predicted by the model for the specific predicted effect associated with the specific value based on the specific value and the specific determined effect of the medical procedure.

Images