A Lightweight Unidimensional Deep Learning Model for Atrial Fibrillation Detection

Continuous rhythm monitoring using wearable devices is a potential tool for early identification of atrial fibril-lation (AF), the most frequent cardiac arrhythmia (with 0,51% worldwide prevalence, increasing with time), and is also a tool for remote monitoring patients after cardiac surgery. However, AF detection directly through wearable devices is limited by the computational complexity of the classifier model. In this work we propose a lightweight AF classifier model based on the VGG-11 architecture (Lite VGG-11), focusing on reducing the number of parameters and nu-merical operations. Using a low number of filters, depth-wise separable convolution, and global pooling, this model has only 20,454 parameters and needs 6.9 MFLOP to make an inference for an input of 10 seconds of the ECG leads I and II, sampled at 200 Hz. To test its effectiveness for AF detection we used the PhysioNet/CinC Challenge 2021 public dataset, stratifying the classes into sinus rhythm, AF, and other rhythms. After 10 Monte Carlo cross-validation splits, with 24,260 unbalanced samples for training and 1,536 balanced samples for validation and testing, the observed met-rics (mean±standard deviation) were: Se 94.1±0.1%; Sp 91.9±0.8%; F1-Score 89.50.7±%; and AUC 96.1±0.6%.