Wearable defibrillation apparatus configured to apply a machine learning algorithm

Abstract

In some examples, an apparatus configured to be worn by a patient for cardiac defibrillation comprises sensing electrodes configured to sense a cardiac signal of the patient, defibrillation electrodes, therapy delivery circuitry configured to deliver defibrillation therapy to the patient via the defibrillation electrodes, communication circuitry configured to receive data of at least one physiological signal of the patient from at least one sensing device separate from the apparatus, a memory configured to store the data, the cardiac signal, and a machine learning algorithm, and processing circuitry configured to apply the machine learning algorithm to the data and the cardiac signal to probabilistically-determine at least one state of the patient and determine whether to control delivery of the defibrillation therapy based on the at least one probabilistically-determined patient state.

What is claimed is: 
     
         1 . A system for cardiac defibrillation, the system comprising:
 an apparatus configured to deliver defibrillation therapy, wherein the apparatus is configured to be worn by a patient, wherein the apparatus comprises:
 processing circuitry comprising a first graphics processing unit (GPU); 
 sensing electrodes configured to sense a cardiac signal of the patient; 
 defibrillation electrodes; 
 therapy delivery circuitry configured to deliver defibrillation therapy to the patient via the defibrillation electrodes; and 
 a memory configured to store the cardiac signal and a machine learning algorithm; and 
   a computing system communicatively coupled to the apparatus, the computing system comprising a second GPU,   wherein the first GPU is configured to apply the machine learning algorithm to the cardiac signal, and the processing circuitry is configured to determine whether to control delivery of the defibrillation therapy based on a result of the application of the machine learning algorithm to the cardiac signal, and   wherein the second GPU is configured to update the machine learning algorithm based on the cardiac signal and population data, wherein the population data comprises data of cardiac signals from a plurality of other patients.   
     
     
         2 . The system of  claim 1 , wherein the plurality of other patients comprises a subset of the other patients having one or more characteristics that match respective characteristics of the patient. 
     
     
         3 . The system of  claim 1 , further comprising an implantable cardioverter defibrillator (ICD) configured to store and execute a tachyarrhythmia detection algorithm, wherein the computing system is configured to configure the tachyarrhythmia detection algorithm for the patient based on cardiac signals classified by the machine learning algorithm. 
     
     
         4 . The system of  claim 1 , wherein the second GPU comprises at least one of a greater number of parallel cores or a greater clock speed than the first GPU. 
     
     
         5 . The system of  claim 4 , wherein the second GPU executes a more computationally complex version of the machine learning algorithm than the first GPU. 
     
     
         6 . The system of  claim 1 , wherein the processing circuitry of the apparatus is configured to control the therapy delivery circuitry to deliver the defibrillation therapy based on a result of the application of the machine learning algorithm to the data and the cardiac signal. 
     
     
         7 . A system for determining a treatable tachyarrhythmia state of a patient, the system comprising an apparatus configured to be worn by the patient and a sensing device separate from the apparatus, the apparatus comprising:
 sensing electrodes configured to sense a cardiac signal of the patient;   communication circuitry configured to receive data of at least one physiological signal of the patient from the sensing device via wireless communication;   a memory configured to store the data, the cardiac signal, and a machine learning algorithm; and   processing circuitry configured to apply the machine learning algorithm to the data and the cardiac signal to determine the treatable tachyarrhythmia state of the patient,   wherein the processing circuitry of the apparatus is configured to request the data as a master from the sensing device as a slave according to a master/slave relationship.   
     
     
         8 . The system of  claim 7 , wherein the processing circuitry is configured to make a preliminary determination of the treatable tachyarrhythmia state based on the cardiac signal, and request the data from the sensing device based on the preliminary determination. 
     
     
         9 . The system of  claim 7 , wherein the sensing device comprises a subcutaneously implantable cardiac monitor comprising a plurality of sensing electrodes to sense the physiological signal, wherein the cardiac signal comprises a first cardiac signal and the physiological signal comprises a second cardiac signal. 
     
     
         10 . The system of  claim 7 , wherein the apparatus comprises defibrillation electrodes configured to deliver defibrillation therapy to the patient, wherein the processing circuitry is configured whether to control delivery of the defibrillation therapy to the patient based on the treatable tachyarrhythmia state of the patient. 
     
     
         11 . The system of  claim 7 , wherein the processing circuitry of the apparatus comprises a graphics processing unit (GPU) configured to apply the machine learning algorithm to the data and the cardiac signal to determine the treatable tachyarrhythmia state of the patient. 
     
     
         12 . A method comprising:
 sensing, via sensing electrodes of an apparatus worn by a patient, a cardiac signal of the patient;   storing, by a memory of the apparatus, the cardiac signal and a machine learning algorithm;   applying, by a first graphics processing unit (GPU) included in processing circuitry of the apparatus, the machine learning algorithm to the cardiac signal;   determining, by the processing circuitry of the apparatus, whether to control delivery of defibrillation therapy based on a result of applying the machine learning algorithm to the cardiac signal; and   updating, by a second GPU included in a computing system communicatively coupled to the apparatus, the machine learning algorithm based on the cardiac signal and population data, wherein the population data comprises data of cardiac signals from a plurality of other patients.   
     
     
         13 . The method of  claim 12 , wherein the plurality of other patients comprises a subset of the other patients having one or more characteristics that match respective characteristics of the patient. 
     
     
         14 . The method of  claim 12 , further comprising:
 configuring, by the computing system, a tachyarrhythmia detection algorithm for the patient based on cardiac signals classified by the machine learning algorithm; and   storing and executing, by an implantable cardioverter defibrillator (ICD), the tachyarrhythmia detection algorithm.   
     
     
         15 . The method of  claim 12 , wherein the second GPU comprises at least one of a greater number of parallel cores or a greater clock speed than the first GPU. 
     
     
         16 . The method of  claim 15 , further comprising:
 executing, by the second GPU, a more computationally complex version of the machine learning algorithm than applied by the first GPU.   
     
     
         17 . The method of  claim 12 , further comprising:
 controlling, by the processing circuitry of the apparatus, therapy delivery circuitry of the apparatus to deliver the defibrillation therapy based on a result applying the machine learning algorithm to the cardiac signal.   
     
     
         18 . A method comprising:
 sensing, via sensing electrodes of an apparatus worn by a patient, a cardiac signal of the patient;   requesting, by processing circuitry of the apparatus, data of at least one physiological signal of the patient as a master from a sensing device as a slave according to a master/slave relationship, the sensing device being separate from the apparatus;   receiving, by communication circuitry of the apparatus, the data of at least one physiological signal of the patient from the sensing device;   storing, by a memory of the apparatus, the data, the cardiac signal, and a machine learning algorithm; and   applying, by processing circuitry of the apparatus, the machine learning algorithm to the data and the cardiac signal to determine a treatable tachyarrhythmia state of the patient.   
     
     
         19 . The method of  claim 18 , further comprising:
 making, by the processing circuitry of the apparatus, a preliminary determination of the treatable tachyarrhythmia state based on the cardiac signal; and   requesting, by the processing circuitry of the apparatus, the data from the sensing device based on the preliminary determination.   
     
     
         20 . The method of  claim 18 , wherein the sensing device comprises a subcutaneously implantable cardiac monitor comprising a plurality of sensing electrodes to sense the physiological signal, wherein the cardiac signal comprises a first cardiac signal and the physiological signal comprises a second cardiac signal. 
     
     
         21 . The method of  claim 18 , further comprising:
 controlling, by the processing circuitry of the apparatus, delivery of defibrillation therapy to the patient via defibrillation electrodes of the apparatus based on the treatable tachyarrhythmia state of the patient.   
     
     
         22 . The method of  claim 18 , further comprising:
 applying, by a graphics processing unit (GPU) included in the processing circuitry of the apparatus, the machine learning algorithm to the data and the cardiac signal to determine the treatable tachyarrhythmia state of the patient.