A dual-branch metric-learning framework for obstructive sleep apnea detection

초록

Obstructive sleep apnea (OSA) screening using wearable-compatible signals remains challenging because of signal noise, temporal complexity, and physiological variation among individuals. We propose a multimodal Siamese metric-learning framework that jointly models electrocardiography (ECG) and oxygen saturation (SpO ) dynamics through a dual-branch encoder and triplet-loss optimization. The architecture integrates a 1D ResNet-18 backbone with bidirectional long short-term memory (BiLSTM)-based temporal fusion to cap- ture complementary physiological patterns. We evaluated the framework using subject-disjoint five-fold cross- validation in a curated cohort from the PSG-Audio dataset. The proposed model achieved an accuracy of , recall of , F1-score of , and AUC of . Patient identities were separated across training, validation, and test partitions, and test data were excluded from triplet construction, model selection, and threshold selection. These results support multimodal metric learning as a competitive within-cohort approach but do not establish generalization to external populations or recording systems.

제목
A dual-branch metric-learning framework for obstructive sleep apnea detection
저자
He, Yinxian ; Kwon, Bokyung Amy ; Kang, Kyungtae
DOI
10.1038/s41598-026-72466-2
발행일
2026-09
유형
정기학술지(Article(Perspective Article포함))
저널명
Scientific Reports
페이지
1 ~ 10