Agentic AI-enabled discovery across large-scale sleep physiology (AI Sleep Co-Scientist)
Rahul Thapa, Umaer Hanif, Robin Guillard, Andreas Brink-Kjaer, Adrien Specht, Matteo Saibene, Magnus Ruud Kjaer, Harrison G. Zhang, Federico Bianchi, Elisabeth Roxane M. Heremans, et al.
arXiv 2607.25175· 2026
PSGEEGECGText
Summary
Expert-guided environment where scientists direct specialist agents for hypothesis development, signal preprocessing and statistics, each result linked to executable code; applied across four cohorts of ~124,000 PSG recordings.
Key facts
- License
- Not stated
Updated: Oct 11, 2026
Related Research
- A Decodability-Grounded Audit of Clinical Prediction Claims in PPG Foundation Models
Audits frozen representations of four encoders on 37,784 MC-MED encounters via concept decodability,
- A meta-learning method with reduced data requirements for training and updating deep learning models on wearable devices
Meta-learning lowers how much data a new wearable must collect up front, and a prototypical updating
- A Physiology-Aware Hierarchical Foundation Model for Long-Context Waveform Representation Learning (Physio-HNet)
Causal hierarchical waveform FM replacing fixed patches with physiology-aware dynamic chunking (land