A multimodal sleep foundation model for disease prediction | Nature Medicine

A deep learning-based model, developed using the rich, multimodal data available from polysomnography-derived sleep recordings, performs well on common sleep analysis tasks and predicts future disease risk across a range of diseases.

Main Sleep is a complex process characterized by intricate interactions across physiological systems, including brain, heart, respiratory and muscle activity1. PSG—the gold standard for sleep evaluation—captures these interactions through recordings of several modalities, including brain activity signals (BAS, including electroencephalogram (EEG) and electrooculogram (EOG)), electrocardiography (ECG), electromyography (EMG) and respiratory signals2. Sleep disorders affect millions of people and are increasingly recognized as indicators of, and contributors to, various health conditions3.…

saved by

• Chris Wong
• Mackay G

related reading

• SensorFM: Towards a general intelligence and interface for wearable health dataresearch.google
• SensorFM: Towards a general intelligence and interface for wearable health dataresearch.google
• Using Interpretability to Identify a Novel Class of Alzheimer's Biomarkersgoodfire.ai
• Prediction of Parkinson’s Disease Using Machine Learning Methodsncbi.nlm.nih.gov
• Prediction of Parkinson’s Disease Using Machine Learning Methodspmc.ncbi.nlm.nih.gov
• Enhancing early Parkinson’s disease detection through multimodal deep learning and explainable AI: insights from the PPMI database | Scientific Reportsnature.com
• Theses on Sleep - Alexey Guzeyguzey.com
• The Medical AI Manifesto - Introducing Sophont – Dr. Tanishq Abrahamtanishq.ai
• Generalist - GEN-0 / Embodied Foundation Models That Scale with Physical Interactiongeneralistai.com
• Do Language Models Need Sleep? Offline Recurrence for Improved Online Inferencearxiv.org
• Prognostic Modeling of Parkinson’s Disease Progression Using Early Longitudinal Patterns of Changepmc.ncbi.nlm.nih.gov
• Towards passive heart health monitoring via smartphone cameraresearch.google