Artificial intelligence for ventricular arrhythmia capability using ambulatory electrocardiograms

Abstract

Lay AbstractQuestionCan artificial intelligence (AI) be used to predict if a person is at risk of a lethal heart rhythm, based solely on an electrocardiogram (an electrical heart tracing)?FindingsIn a study of 270 adults (of which 159 had lethal arrhythmias), the AI was correct in 4 out of every 5 cases. If the AI said a person was at risk, the risk of lethal event was three times higher than normal adults.MeaningIn this study, the AI performed better than current medical guidelines. The AI was able accurately determine the risk of lethal arrhythmia from standard heart tracings over a year away which is a conceptual shift in what an AI model can see and predict. This method shows promise in better allocating implantable shock box pacemakers (ICDs) that saves lives.Scientific AbstractAimCurrent clinical practice guidelines for implantable cardioverter defibrillators (ICDs) are insufficiently accurate for ventricular arrhythmia (VA) risk stratification leading to significant morbidity and mortality. Artificial intelligence offers novel risk stratification lens through which VA capability can be determined from electrocardiogram in normal sinus rhythm. The aim was to develop and test a deep neural network for VA risk stratification using routinely collected ambulatory electrocardiograms.MethodsA multicentre case-control study was undertaken to assess VA-ResNet-50, our open source ResNet-50 based deep neural network. VA-ResNet-50 was designed to read pyramid samples of 3-lead 24-hour ambulatory electrocardiograms to decide if a heart is capable of VA based on the electrocardiogram alone. Consecutive adults with VA from East Midlands, UK, who had ambulatory electrocardiograms as part of their NHS care between 2014 and 2022 were recruited and compared to all comer ambulatory electrocardiograms without VA.ResultsOf 270 patients, 159 heterogeneous patients had a composite VA outcome. The mean time difference between the electrocardiogram and VA was 1.6 years (⅓ ambulatory electrocardiogram before VA). The deep neural network was able to classify electrocardiograms for VA capability with an accuracy of 0.76 (CI 95% 0.66 - 0.87), F1 score of 0.79 (0.67 - 0.90), AUC of 0.8 (0.67 - 0.91) and RR of 2.87 (1.41 - 5.81).ConclusionAmbulatory electrocardiograms confer risk signals for VA risk stratification when analysed using VA-ResNet-50.Pyramid samplingfrom the ambulatory electrocardiograms is hypothesised to capture autonomic activity. We encourage groups to build on this open-source model.