Diagnostic accuracy of machine learning algorithms in electrocardiogram-based sleep apnea detection: A systematic review and meta-analysis

Abstract

Sleep apnea is a prevalent disorder affecting 10 % of middle-aged individuals, yet it remains underdiagnosed due to the limitations of polysomnography (PSG), the current diagnostic gold standard. Single-lead electrocardiography (ECG) has been proposed as a potential alternative diagnostic tool, but interpretation challenges remain. Recent advances in machine learning and deep learning technologies offer promising approaches for enhancing the detection of sleep apnea through automated analysis of ECG signals. This meta-analysis aims to evaluate the diagnostic accuracy of machine learning (ML) and deep learning (DL) algorithms in detecting sleep apnea patterns from single-lead ECG data. A comprehensive literature search across multiple databases was conducted through November 2023, adhering to PRISMA-DTA guidelines. Studies that included sensitivity and specificity data for ECG-based sleep apnea detection using (machine learning/deep learning) ML/DL were selected. The analysis included 84 studies, demonstrating high diagnostic accuracy for ML/DL algorithms, with pooled sensitivity and specificity of over 90 % in per-segment analysis and close to 97 % in per-record analysis. Despite strong diagnostic performance, variations in algorithm effectiveness and methodological biases were noted. This meta-analysis highlights the potential of ML and DL in improving sleep apnea diagnosis and outlines areas for future research to address current limitations.