wav2sleep: A Unified Multi-Modal Approach to Sleep Stage Classification from Physiological Signals
This addresses the need for accurate sleep stage classification from less obtrusive sensors in sleep medicine, though it is incremental as it builds on existing deep learning approaches with a focus on multi-modal flexibility.
The paper tackled the problem of sleep stage classification from variable physiological signals like ECG and PPG, introducing wav2sleep, a unified multi-modal model that outperformed existing models across test-time input combinations after training on over 10,000 recordings from six datasets.
Accurate classification of sleep stages from less obtrusive sensor measurements such as the electrocardiogram (ECG) or photoplethysmogram (PPG) could enable important applications in sleep medicine. Existing approaches to this problem have typically used deep learning models designed and trained to operate on one or more specific input signals. However, the datasets used to develop these models often do not contain the same sets of input signals. Some signals, particularly PPG, are much less prevalent than others, and this has previously been addressed with techniques such as transfer learning. Additionally, only training on one or more fixed modalities precludes cross-modal information transfer from other sources, which has proved valuable in other problem domains. To address this, we introduce wav2sleep, a unified model designed to operate on variable sets of input signals during training and inference. After jointly training on over 10,000 overnight recordings from six publicly available polysomnography datasets, including SHHS and MESA, wav2sleep outperforms existing sleep stage classification models across test-time input combinations including ECG, PPG, and respiratory signals.