SmartMatch: A semi-supervised framework for obstructive sleep apnea classification using single-lead electrocardiogram signals with limited annotations

Obstructive Sleep Apnea (OSA) is a prevalent respiratory disorder with significant global health implications, affecting individuals of all ages and demographics. This underlines the demand for reliable diagnostic methods and computational models capable of accurately classifying OSA efficiently using single-lead electrocardiogram (ECG) with Limited Annotations. Recent progress in deep learning (DL) techniques, coupled with highperformance computing, has facilitated automatic classification in medical imaging, offering a viable solution for timely diagnosis. However, Traditional supervised learning (SL) requires large, expert-annotated datasets, which are costly and time-intensive to curate, which is a critical bottleneck in resource-constrained settings. To overcome these challenges, we proposed a semi-supervised learning (SSL) framework, SmartMatch. Our SSL framework minimizes reliance on annotated data by effectively leveraging unlabeled ECG signals, reducing annotation burdens while maintaining diagnostic accuracy. The proposed framework is inspired by hierarchical structures observed in real-world scenarios, where leader-follower dynamics play a crucial role in decision-making. Our approach integrates deep metric learning, employing Adaptive batch hard mining to enhance feature representation, alongside an Adaptive pseudo-labeling strategy to refine label quality, and an Adaptive temporal ensembling to stabilize learning while preserving consistency loss constraints. We conducted experiments on the PhysioNet Apnea-ECG repository (PA-ECG) dataset, which comprises 70 overnight recordings. The proposed SmartMatch achieved remarkable performance, yielding high accuracy, precision, recall, and F1-scores of 91.99% (+/- 0.08), 91.98% (+/- 0.10), 91.99% (+/- 0.11), and 91.97% (+/- 0.10) per-segment, respectively. The results highlight SSL's capability to strengthen DL models for OSA detection, particularly in applications involving home sleep apnea testing and wearable IoT devices.