Evidential Deep Learning Model for Atrial Fibrillation Detection from Holter Recordings

Deep learning (DL) models have shown promising performances for detecting atrial fibrillation (AF) and atrial flutter (AFL) from electrocardiograms (ECGs) but often suffer from overconfidence and poor probability calibration.Evidential DL (EDL) addresses this by using evidence to parameterize a Dirichlet distribution for uncertainty estimation.The main objective of this study was to develop an EDL model for AF and AFL detection from 2-lead Holter ECG recordings, aiming to estimate uncertainty without incurring additional computational costs compared to traditional softmax-based DL models.In this study, we developed an evidential residual-based DL model, treating predicted probabilities as subjective opinions.The model was trained and tested on a comprehensive dataset of 661 Holter recordings.Our experiments showed that the EDL model achieved recalls of 0.953, 0.838, and 0.934 for detecting AF, AFL, and Non-AF, respectively.The corresponding AUC scores were about 0.980 for AF and Non-AF, and 0.972 for AFL.In terms of confidence estimation, the EDL model exhibited superior performance with an expected calibration error of 0.09, compared to 0.16 for the softmax-based model.These results indicate that EDL models offer enhanced calibration and effectiveness in detecting AF compared to standard softmax models.