Multiscale entropy analysis of single lead ECG and ECG derived respiration for AI based prediction of sleep apnea events

Abstract

Sleep apnea (SA) is a prevalent sleep disorder that affects a significant portion of the adult population. The proposed method involves coarse graining a signal at different scales, using the popular multiscale entropy algorithms to detect apnea and normal events from single lead Electrocardiography (ECG), Instantaneous Heart Rate and ECG derived respiration. The idea of nonlinear dynamical systems analysis for feature extraction along with machine learning approach, the authors present here a moderately accurate sleep apnea detection model with an accuracy ranging from 70% to 100% based on two different probabilistic thresholds of 50 % and 70% with reduction in false positive rate from 28% to 14 % for applications in development of AI based IoT connected smart wearable devices. The two thresholding modes offer a choice to do a trade-off between high training accuracy with high false positive rate and low accuracy with low false positive rate. The performance metrics of each model have been reported and choice is made for best suitable model with prospectives of implementation for diagnostic purposes. The effectiveness of the proposed method in accurate detection of sleep apnea requires further validation of the models with out of distribution dataset.