Stanford's SleepFM AI predicts future disease and mortality years before diagnosis using sleep data

AI trained on sleep data predicts future disease and mortality years in advance

By Tarun Sai LomteReviewed by Lauren HardakerJan 8 2026 By learning hidden physiological patterns from overnight sleep studies, a new AI foundation model reveals how sleep can serve as an early warning system for disease risk years before clinical diagnosis. Study: A multimodal sleep foundation model for disease prediction. Image credit: AnnaStills/Shutterstock.com In a recent study published in Nature Medicine, researchers developed a multimodal sleep foundation model, SleepFM, for disease prediction. From sleep disorders to systemic disease risk Sleep disorders impact millions of individuals and are increasingly recognized as contributors to and indicators of various conditions. Polysomnography (PSG) is the gold standard for sleep analysis, capturing rich physiological signals. Previous machine learning studies have typically targeted individual diseases or limited sleep metrics, leaving much of the rich complexity captured by PSG underused. SleepFM links overnight physiology to long-term disease risk In the present study, researchers developed SleepFM, a multimodal sleep foundation model, for disease prediction. PSG data were used from four cohorts: BioSerenity, the Outcomes of Sleep Disorders in Older Men (MrOS), the Multi-Ethnic Study of Atherosclerosis (MESA), and Stanford Sleep Clinic (SSC). Together, these cohorts comprised around 65,000 participants and 585,000 hours of sleep recordings. In addition, the Sleep Heart Health Study (SHHS) dataset was used to evaluate external transfer learning and generalization and was excluded from pretraining. The team employed a self-supervised contrastive learning objective for pretraining. After pretraining, the performance of SleepFM's learned representations was assessed by fine-tuning on four benchmark tasks: sex classification, sleep stage classification, age estimation, and sleep apnea classification. SleepFM's ability to predict chronological age was assessed for age estimation. The model achieved a mean absolute error of 7.33 years. Performance varied by age group, with higher accuracy in middle-aged and pediatric groups and greater error in older adults. Sex classification had an area under the receiver operating characteristic curve (AUROC) of 0.86 and an area under the precision, recall curve of 0.9. SleepFM performed well in distinguishing wake, stage 2, and rapid eye movement stages but showed confusion in transitional sleep stages, such as stage 1, in line with known variability in scoring. Notably, the model achieved competitive performance compared to state-of-the-art models, including U-Sleep, Greifswald Sleep Stage Classifier (GSSC), Yet Another Spindle Algorithm (YASA), and STAGES, although specialized models occasionally outperformed SleepFM on certain external datasets. For sleep apnea classification, SleepFM demonstrated competitive performance, with accuracies of 0.87 and 0.69 for presence and severity classification, respectively. Next, the researchers linked SSC data with electronic health records, extracting diagnostic codes and their timestamps for disease prediction. These codes were mapped to a hierarchical system of more than 1,800 disease categories designed for phenome-wide association studies (phecodes). After filtering for prevalence and temporal constraints, 1,041 phecodes were retained for evaluation, with cases defined as diagnoses occurring more than seven days after the sleep study to avoid trivial associations. SleepFM achieved robust results in various areas, including pregnancy-related complications, mental disorders, neoplasms, and circulatory conditions. The model achieved an AUROC of 0.93 for Parkinson's disease and 0.84 for both developmental delays and disorders and mild cognitive impairment, measured over a six-year prediction window. Among circulatory conditions, SleepFM effectively predicted intracranial hemorrhage and hypertensive heart disease with six-year AUROC values of 0.82 and 0.88, respectively. The authors emphasize that these predictions reflect statistical risk stratification rather than causal relationships or imminent disease onset. Among neoplasms, SleepFM demonstrated strong predictive performance for prostate cancer, melanomas of the skin, and breast cancer. The team then examined the model's generalization capabilities across temporal distribution and external site validation. For temporal generalization, the model was tested on a separate cohort of Stanford patients from 2020 onwards; SleepFM maintained strong predictive performance despite the limited follow-up period. To evaluate cross-site generalization, the transfer learning capabilities of SleepFM were assessed on the SHHS dataset. Embeddings from the pretrained model were extracted and fine-tuned on a subset of this dataset. Because outcome definitions differed across sites, evaluation was limited to six overlapping cardiovascular outcomes. SleepFM demonstrated robust transfer learning performance across these key outcomes, achieving significant predictive accuracy for congestive heart failure, stroke, and cardiovascular disease-related mortality. Finally, the researchers compared SleepFM against two supervised baselines, end-to-end PSG and demographics. The demographics baseline was trained on structured clinical features, for example, body mass index, age, sex, and race or ethnicity. The end-to-end PSG model was trained on raw PSG data, including age and sex, but without pre-training. The percentage difference in AUROC between the two baselines and SleepFM ranged from 5 % to17 %. SleepFM consistently outperformed both baselines across most categories of diseases. Moreover, SleepFM was superior in predicting all-cause mortality, achieving an AUROC of 0.85, compared to both baselines that had an AUROC of 0.78. Across disease categories, the model demonstrated strong risk stratification performance, with more than 130 conditions achieving a Harrell's C index of at least 0.75. According to the authors, these results highlight the potential of sleep as a rich, underused source of longitudinal health signals. Sleep-based AI models could reshape early disease detection In summary, the study developed a large-scale sleep foundation model using more than 585,000 hours of PSG data. SleepFM was robust in predicting dementia, heart failure, chronic kidney disease, and death. The model achieved competitive performance on standard tasks, such as apnea detection and sleep staging, comparable to state-of-the-art models. SleepFM also showed strong transfer learning capabilities, maintaining robust predictive power for several cardiovascular outcomes across independent datasets. Furthermore, the model outperformed supervised baselines across diverse disease categories, predicting all-cause mortality more accurately than both baselines. However, the authors note that most data were derived from individuals referred for clinical sleep studies, which may limit generalizability to the broader population. They also acknowledge that, like many foundation models, SleepFM's learned representations are not yet fully interpretable at the level of specific physiological mechanisms. Overall, these findings suggest that SleepFM could complement existing risk assessment tools and help identify early disease signs. Future studies may explore how integrating sleep models with data from health records, imaging, and omics can enhance their utility. Download your PDF copy now! Journal reference: Thapa R, Kjaer MR, He B, et al. (2026). A multimodal sleep foundation model for disease prediction. Nature Medicine. DOI: 10.1038/s41591-025-04133-4. DOI: https://doi.org/10.1038/s41591-025-04133-4. https://www.nature.com/articles/s41591-025-04133-4

Sleep Lab Data Can Predict Illnesses Years Earlier, Study Finds

By Dennis Thompson HealthDay ReporterWEDNESDAY, Jan. 7, 2026 (HealthDay News) -- Your body is talking while you sleep, and what it's saying could help doctors predict your future risk for major diseases, a new study says. An experimental artificial intelligence (AI) called SleepFM can use people's sleep data to predict their risk of developing more than 100 health problems, researchers reported Jan. 6 in the journal Nature Medicine. SleepFM excelled at predicting conditions as varied as cancers, pregnancy complications, heart problems and mental disorders, the study reported. It also could predict a person's overall risk of death, researchers noted. "SleepFM is essentially learning the language of sleep," co-senior researcher James Zou said in a news release. He's an associate professor of biomedical data science at Stanford Medicine. Researchers trained the AI on 585,000 hours of sleep data from 65,000 people who'd had their sleep monitored at a sleep center. These comprehensive sleep assessments record brain activity, heart activity, breathing, leg movements, eye movements and more, researchers said. "We record an amazing number of signals when we study sleep," co-senior researcher Dr. Emmanuel Mignot, a professor of sleep medicine at Stanford, said in a news release. "It's a kind of general physiology that we study for eight hours in a subject who's completely captive. It's very data rich." The team then used long-term data from the Stanford Sleep Medicine Center to tie sleep data to health risks. About 35,000 patients went to the center for sleep assessment and were followed for up to 25 years. SleepFM analyzed more than 1,000 disease categories in the patients' health records, and found 130 that could be predicted with reasonable accuracy by their sleep data, researchers said. They used a statistic called the C-index, or concordance index, to test the AI's ability to predict diseases. A C-index of 0.8 or higher shows it can predict disease accurately. "A C-index of 0.8 means that 80% of the time, the model's prediction is concordant with what actually happened," Zou said. SleepFM's predictions were particularly strong regarding Parkinson's disease (C-index 0.89), dementia (0.85); hypertensive heart disease (0.84); heart attack (0.81); prostate cancer (0.89); breast cancer (0.87); and death (0.84). "We were pleasantly surprised that for a pretty diverse set of conditions, the model is able to make informative predictions," Zou said. The team found that there was some cross-talk when it came to the heart and head while sleeping. Heart signals during sleep factored more prominently in heart disease predictions, while brain signals did so with mental health predictions, researchers said. However, combining all the data coming in produced the most accurate predictions. "The most information we got for predicting disease was by contrasting the different channels," Mignot said. Sleep data that appeared out of sync -- a brain that looks asleep but a heart that looks awake, for example -- seemed to spell trouble for a person's health. The team is now working on ways to further improve SleepFM's predictions, possibly by adding data from other devices such as wearables. Researchers also are trying to better understand what SleepFM is looking at when it makes its predictions. "It doesn't explain that to us in English," Zou said. "But we have developed different interpretation techniques to figure out what the model is looking at when it's making a specific disease prediction." More information The Sleep Foundation has more on sleep lab studies for patients. SOURCE: Stanford Medicine, news release, Jan. 6, 2026