Assessment of the Risk of Sudden Cardiac Death Using Machine Learning Methods

The work is devoted to the detection of the predictor of sudden cardiac death-atrial fibrillation. Public databases of digitized electrocardiograms were used. Two approaches were applied: machine learning and digital biomarkers. It was found that using the category boost method, atrial fibrillation can be detected against other forms of arrhythmia and normal sinus rhythm with an efficiency of 99%. Orthogonal wavelets obtained from two-second samples of digitized electrocardiograms designed to study severe forms of arrhythmia were used as digital biomarkers. High selectivity of wavelets to atrial fibrillation was shown.