Abstract

Introduction: Sudden Cardiac Arrest (SCA) is an unexpected life-threatening loss of cardiac function potentially leading to sudden cardiac death (SCD). It accounts for a half of cardiac mortality, posing a major public health problem. While SCA can be treated with implantable cardioverter defibrillators (ICD), most (80%) SCDs occur in relatively low risk patients, for whom risk benefit ratio of an ICD is unfavorable. Therefore, novel methods to identify high risk individuals and the time on which their risk is high may facilitate prevention of SCD. Methods : Long (~24h) ECG recordings from individuals who had an SCA on record (n=20), patients with other arrhythmias (n=84) and from healthy individuals (n=17) from PhysioNet databases were analyzed to extract inter beat intervals (IBI). For each step in the IBI series, 120 last IBIs were used to calculate 19 indices that quantify short term heart rate variability (HRV). An artificial intelligence model named temporal convolutional network (TCN) was used to continuously assess the risk of a future VF event based on the current HRV estimate combined with few hours of history of previous HRV estimates. Training and testing of the TCN was done using Leave One Out testing done twice. Patients being classified at any point in the record as high risk were considered high risk. Results : Only patients from the SCA population, and none from the other arrythmia and healthy patients, were classified as high risk (PPV=100%). On average, sensitivity and specificity were 62.5% and 100% respectively Conclusions : In this preliminary retrospective analysis, artificial intelligence based HRV analysis identified risk for a SCA event in the following 24 hours with high specificity. Larger cohort and prospective testing are needed to assess the clinical utility of such systems.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call