SleepPPG-Net2: deep learning generalization for sleep staging from photoplethysmography

Year: 2025

Type: article

Abstract: Objective . sleep staging is essential for diagnosing sleep disorders and managing sleep health. Traditional methods require time-consuming manual scoring. Recent photoplethysmography (PPG)-based deep learning models perform well on local datasets but struggle with external generalization due to data drift. Approach . this study evaluates multi-source domain training for improving out-of-distribution generalization in four-class sleep staging (wake, light, deep, rapid eye movement) from raw PPG time-series. The trained deep learning model is denoted SleepPPG-Net2. Additionally, we examined the impact of demographic factors, ethnicity, and obstructive sleep apnea (OSA) on performance. SleepPPG-Net2 was benchmarked against two state-of-the-art models. Main results . SleepPPG-Net2 outperformed benchmark models, improving generalization performance (Cohen’s kappa) by up to 21%. Performance disparities were observed in relation to age, sex, and OSA severity. Significance . SleepPPG-Net2 enhances PPG-based sleep staging and provides insights into demographic and clinical influences on model performance.

Source: Physiological Measurement

DOI: 10.1088/1361-6579/ae1a34

Authors: Shirel Attia, Revital Shani Hershkovich, Alissa Tabakhov, Angeleene Ang, Arie Oksenberg, Riva Tauman, Joachim A Behar

Institutions: Technion – Israel Institute of Technology, Tel Aviv Sourasky Medical Center

Language: English

Topic: Non-Invasive Vital Sign Monitoring

Subfield: Biomedical Engineering

Field: Engineering

Domain: Physical Sciences

SDG: Good health and well-being

Open Access status: hybrid

Estimated APC paid: $3,325

Funders: National Institutes of Health, National Heart, Lung, and Blood Institute, National Center for Advancing Translational Sciences, Israel Innovation Authority

OpenAlex ID: W4415753745