A Systematic Review on Machine Learning / Deep Learning Model-based Detection of Sleep Apnea Using Bio-Signals

Abstract

Backgrounds: Sleep Apnea (SA) is a sleep-related breathing disorder diagnosed in clinical laboratories. The gold standard is Polysomnography (PSG), a multi-parameter evaluation of a sleep monitoring system that records the biological signals during overnight sleep. Apart from PSG recording, apnea events are recorded by various other bio-signals called Electrocardiogram (ECG), Electroencephalogram (EEG), Oxygen Saturation level (SpO2), etc. Further evaluation of the recorded bio-signals is tedious and time-consuming as experts perform it manually. Aiming to overcome the disadvantage without compromising accuracy, scientists focus on developing robust measurements of SA by using Machine Learning (ML) and Deep Learning (DL) models. Method: This study aimed to analyze the recent research findings in the field of sleep apnea classification and various machine learning and deep learning methods implemented in detecting SA. This study revealed the best-performing technique considering different types of bio-signals used for analysis and the respective ML or DL models used for automatic detection Result: The studies and patents included in this review underwent a precise screening process using PRISMA guidelines. The literature study is comprised of three different analysis tools to showcase the review process and provide evidence for the research findings obtained in the respective publications. The publications considered were limited to the last decade. Conclusion: This review delivers the key finding that ECG signals-based detection of sleep apnea using deep learning model-based deep neural network classifiers will provide more accurate and robust classification, which will pave the way for possible future research directions.