arXiv：cs.AI· Rahul Thapa, Christopher Sun, William Theodor Lehn-Schioler, Sophia Claire Kivelson, Umaer Hanif, Hyatt Moore IV, Harrison G. Zhang, Hafsa Ahmed, Marcus Dige, Niels R. Lorenzen, Elisabeth Roxane M. Heremans, Adrien Specht, Ulysse Gimenez, Robin Guillard, Andreas Brink-Kjaer, James Zou, Emmanuel Mignot·· 4 小时前AI 评分59
SleepFM-2：基于超两百万小时睡眠数据的多模态睡眠基础模型
Learning transferable human physiology from two million hours of sleep with SleepFM-2
AI 导读
斯坦福团队在 arXiv 发布 SleepFM-2 睡眠基础模型，基于 26 个队列共 282,511 份多导睡眠图记录预训练，数据超过两百万小时多模态生理信号。
正文
Authors:Rahul Thapa, Christopher Sun, William Theodor Lehn-Schioler, Sophia Claire Kivelson, Umaer Hanif, Hyatt Moore IV, Harrison G. Zhang, Hafsa Ahmed, Marcus Dige, Niels R. Lorenzen, Elisabeth Roxane M. Heremans, Adrien Specht, Ulysse Gimenez, Robin Guillard, Andreas Brink-Kjaer, James Zou, Emmanuel Mignot
Abstract: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.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.06849 [cs.AI] |
| (or arXiv:2609.06849v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2609.06849 arXiv-issued DOI via DataCite |
Submission history
From: Rahul Thapa [view email]
[v1]
Sun, 6 Sep 2026 21:47:56 UTC (4,813 KB)
[v2]
Fri, 2 Oct 2026 05:21:45 UTC (4,814 KB)
来源：arXiv：cs.AI · arxiv.org