Event-based Detection of Obstructive Sleep Apnea via YOLOv8 Nano and ECG Spectrograms: Integration with Home Sleep Apnea Test and Edge Computing

Obstructive sleep apnea (OSA) remains significantly underdiagnosed due to limitations associated with traditional polysomnography (PSG), including complexity, high cost, and patient inconvenience. To overcome these challenges, this study introduces a novel event-based detection method using the YOLOv8 Nano object detection model applied to electrocardiogram (ECG) spectrograms. ECG features were generated via Continuous Wavelet Transform (CWT) with the Morlet wavelet, enabling precise identification and temporal localization of individual apnea and hypopnea events within the signal. Model performance was rigorously validated using datasets comprising 50 subjects from clinical source: clinical ECG data collected at the National Cheng Kung University Hospital Sleep Center (NCKUHSC). Evaluation involved both Subject-Wise 5-Fold Cross-Validation and Leave-One-Subject-Out (LOSO) cross-validation methods to assess generalization. Experimental results demonstrated that the YOLOv8 Nano model achieved by providing accurate temporal granularity. Additionally, apnea-hypopnea index (AHI) estimation, derived from counting precisely localized events, strongly correlated with clinical ground-truth values (Pearson correlation coefficient R = 0.86, RMSE = 12.16 events/hour for detection on 135-sec ECG spectrogram segments), highlighting clinical accuracy and reliability. The compact model size (~6 MB, 3.2M parameters) facilitates seamless integration with Home Sleep Apnea Tests (HSAT) and edge computing platforms, enabling accessible, cost-effective, and patient-friendly diagnostic solutions. Furthermore, the event-based nature of the results allows for extraction of richer, event-specific clinical parameters beyond AHI. Future research directions include enhancing feature extraction, improving model generalization with larger datasets, exploring these extended clinical parameters, and optimizing embedded computing implementations for real-world clinical use.