SleepPPG-Net2: Deep learning generalization for sleep staging from photoplethysmography
This work addresses the need for more generalizable and efficient sleep staging tools to aid in diagnosing sleep disorders, though it appears incremental as it builds on existing deep learning approaches with a multi-source domain training method.
The study tackled the problem of sleep staging from photoplethysmography (PPG) data by developing SleepPPG-Net2, a deep learning model that improved generalization performance by up to 19% in Cohen's kappa compared to state-of-the-art benchmarks, using data from 2,574 patient recordings.
Background: Sleep staging is a fundamental component in the diagnosis of sleep disorders and the management of sleep health. Traditionally, this analysis is conducted in clinical settings and involves a time-consuming scoring procedure. Recent data-driven algorithms for sleep staging, using the photoplethysmogram (PPG) time series, have shown high performance on local test sets but lower performance on external datasets due to data drift. Methods: This study aimed to develop a generalizable deep learning model for the task of four class (wake, light, deep, and rapid eye movement (REM)) sleep staging from raw PPG physiological time-series. Six sleep datasets, totaling 2,574 patients recordings, were used. In order to create a more generalizable representation, we developed and evaluated a deep learning model called SleepPPG-Net2, which employs a multi-source domain training approach.SleepPPG-Net2 was benchmarked against two state-of-the-art models. Results: SleepPPG-Net2 showed consistently higher performance over benchmark approaches, with generalization performance (Cohen's kappa) improving by up to 19%. Performance disparities were observed in relation to age, sex, and sleep apnea severity. Conclusion: SleepPPG-Net2 sets a new standard for staging sleep from raw PPG time-series.