University of Arizona
Model weights not public. Contact creators for more information.
Self-supervised deep learning model that extracts cardiovascular-risk-relevant patterns from multimodal polysomnography (PSG) signals -- EEG, ECG, and respiratory signals -- without relying on manual sleep-stage annotations. Trained on 4,398 participants, the model derives 'projection scores' by contrasting embeddings from individuals with and without cardiovascular disease (CVD) outcomes. Externally validated in an independent cohort of 1,093 participants, ECG-derived projection scores were predictive of prevalent and incident cardiac conditions (particularly CVD mortality), and combining projection scores with the Framingham Risk Score consistently improved prediction (AUC 0.607-0.965 internally, 0.710-0.807 externally across most outcomes).
Architecture
Hybrid
Self-supervised backbone combining residual and transformer blocks over multimodal (EEG, ECG, respiratory) polysomnography signals, with disease-related "projection scores" derived by contrasting embeddings of CVD-positive vs. CVD-negative individuals in the learned latent space
Framework
PyTorch
Added to catalog
2026-08-14
Independent Polysomnography External Validation Cohort (sleep-ssl)
Sleep Heart Health Study / Wisconsin Sleep Cohort (sleep-ssl training)
Cardiovascular-disease-related projection scores derived from self-supervised embeddings of multimodal polysomnography (EEG/ECG/respiratory) signals