On Improving PPG-Based Sleep Staging: A Pilot Study
This work addresses the problem of improving sleep monitoring accuracy for users of consumer wearables, but it is incremental as it builds on existing methods with hybrid approaches.
The paper tackles the challenge of reliable sleep staging using only PPG signals from wearables by exploring dual-stream cross-attention models that combine PPG with auxiliary data like synthetic ECG, achieving substantial performance gains on the MESA dataset.
Sleep monitoring through accessible wearable technology is crucial to improving well-being in ubiquitous computing. Although photoplethysmography(PPG) sensors are widely adopted in consumer devices, achieving consistently reliable sleep staging using PPG alone remains a non-trivial challenge. In this work, we explore multiple strategies to enhance the performance of PPG-based sleep staging. Specifically, we compare conventional single-stream model with dual-stream cross-attention strategies, based on which complementary information can be learned via PPG and PPG-derived modalities such as augmented PPG or synthetic ECG. To study the effectiveness of the aforementioned approaches in four-stage sleep monitoring task, we conducted experiments on the world's largest sleep staging dataset, i.e., the Multi-Ethnic Study of Atherosclerosis(MESA). We found that substantial performance gain can be achieved by combining PPG and its auxiliary information under the dual-stream cross-attention architecture. Source code of this project can be found at https://github.com/DavyWJW/sleep-staging-models