Emmanuel Mignot

Papers

• Dual foundation models for accelerometry predict future health
  2026 · medRxiv preprint

  This medRxiv study encoded one week of UK Biobank wrist accelerometry from 97,696 people with two frozen self-supervised models and trained one survival model for 390 health outcomes. In 5,253 held-out participants mean concordance was 0.688, and one shared component explained 76% of predicted risk variance. Movement data also flagged early signs of neurodegenerative disease, strongest for Parkinson's (five-year AUROC 0.90).

  • Published: medRxiv preprint, 2026
  • Cohort: 97,696 UK Biobank participants
  • Signals: wrist accelerometry (1 week)
• Learning transferable human physiology from two million hours of sleep with SleepFM-2
  2026 · arXiv preprint, cs.AI

  Rahul Thapa, Christopher Sun, William Theodor Lehn-Schiøler, Sophia Claire Kivelson, Umaer Hanif, Hyatt Moore IV, Harrison G. Zhang, Hafsa Ahmed, Marcus Dige, Niels R. Lorenzen, Elisabeth Roxane M.

  • Venue: arXiv preprint, cs.AI
  • Subjects: 282,511 PSG recordings from 26 cohorts (235,865 used for pretraining); counts reported as recordings, not subjects
  • Signals: EEG, EOG, EMG, ECG, respiration, PPG, ACC
• SleepFM: Multi-modal Representation Learning for Sleep Across Brain Activity, ECG and Respiratory Signals
  2024 · arXiv preprint

  SleepFM is a multimodal sleep foundation model trained on more than 100,000 hours of polysomnography from over 14,000 people, covering brain, heart and breathing signals. A leave-one-out contrastive approach beat standard pairwise contrastive learning. Simple models on its embeddings beat an end-to-end CNN on sleep staging (macro AUROC 0.88 vs 0.72).

  • Published: arXiv preprint, 2024
  • Data: 100,000+ hours PSG from 14,000+ participants
  • Signals: EEG, ECG, respiration

Models

• SleepFM-2
• SleepFM (v1)

Datasets used in this work

• DREAMT: Dataset for Real-time sleep stage EstimAtion using Multisensor wearable Technology

Co-authors