# Learning transferable human physiology from two million hours of sleep with SleepFM-2

arXiv: https://arxiv.org/abs/2609.06849 · HTML: https://mlsanity.com/paper/2609.06849/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 123 references that are in the map.
- First posted on arXiv 6 Sep 2026.

## Builds on (most cited first, 12 of 12)

- [Large-scale Training of Foundation Models for Wearable Biosignals](https://mlsanity.com/paper/2312.05409/) (2023)
- [Scaling Wearable Foundation Models](https://mlsanity.com/paper/2410.13638/) (2024)
- [SensorLM: Learning the Language of Wearable Sensors](https://mlsanity.com/paper/2506.09108/) (2025)
- [SleepLM: Natural-Language Intelligence for Human Sleep](https://mlsanity.com/paper/2602.23605/) (2026)
- [OSF: On Pre-training and Scaling of Sleep Foundation Models](https://mlsanity.com/paper/2603.00190/) (2026)
- [Mechanistic Interpretability of EEG Foundation Models via Sparse Autoencoders](https://mlsanity.com/paper/2605.13930/) (2026)
- [Stanford Sleep Bench: Evaluating Polysomnography Pre-training Methods for Sleep Foundation Models](https://mlsanity.com/paper/2512.09591/) (2025)
- [SleepMaMi: A Universal Sleep Foundation Model for Integrating Macro- and Micro-structures](https://mlsanity.com/paper/2602.07628/) (2026)
- [Pretraining on Sleep Data Improves non-Sleep Biosignal Tasks](https://mlsanity.com/paper/2605.02500/) (2026)
- [Clinical Feasibility of Smartphone-based EEG in Kenya](https://mlsanity.com/paper/2605.08157/) (2026)
- [BiTimeCrossNet: Time-Aware Self-Supervised Learning for Pediatric Sleep](https://mlsanity.com/paper/2602.02769/) (2026)
- [Agentic AI-enabled discovery across large-scale sleep physiology](https://mlsanity.com/paper/2607.25175/) (2026)

## Abstract (arXiv)

Sleep provides a nightly window into health by capturing coordinated activity across the brain, heart, muscles and respiratory system. We introduce SleepFM-2, a sleep foundation model developed and evaluated on 282,511 polysomnography recordings from 26 cohorts, including 235,865 used for pretraining. These data span more than two million hours of multimodal physiology. Compared with SleepFM, SleepFM-2 improves disease prediction and sleep scoring, supports arousal, limb movement and respiratory event detection, and transfers to wearable sensing and subjective sleep phenotypes. A model combining its PSG representation with age, sex and BMI met a prespecified discrimination and significance criterion for 188 subsequently recorded EHR phenotypes in two held-out cohorts, including one health system unseen during pretraining. SleepFM-2 also outperformed a 480-feature baseline derived from the same recordings. Its disease scores revealed a reproducible principal component associated with reduced sigma-band spatial coupling and increased hypnodensity entropy. The frozen encoder performed within the observed range of expert scorers for sleep events and transferred to wakeful EEG, headband and in-ear EEG, wrist PPG and wrist accelerometry. It improved sleep staging across six accelerometry cohorts and achieved disease-prediction performance in UK Biobank similar to models pretrained directly on accelerometry. Finally, SleepFM-2 captured aspects of subjective sleep not recovered by conventional PSG summaries, particularly reports of the recorded night. These results show that multimodal sleep physiology can provide a transferable representation of human health across diseases, clinical tasks, sensors and subjective experience.