In 2026, Stanford University researchers published in Nature Medicine a study redefining medical screening.
Bedroom of an Engadine chalet just before dawn: cold bluish light from the window, pale linen sheets, a smart ring and watch resting on the nightstand; no faces.
The AI model SleepFM, trained on over 585,000 hours of sleep recordings from \~65,000 participants, predicts the risk of 130 clinical conditions from a single night of monitoring — with accuracy (C-Index) above 0.75.
Macro detail of a wearable ring and a smartwatch recording sleep phases in low light; night-blue tones, soft reflections; no faces.
What the research demonstrated
SleepFM analyses the physiological and temporal structure of sleep — not simply hours slept, but the sequence of phases, their duration and cycle regularity.
Luminous chart of REM and deep-sleep phases projected on the dark wall of a premium clinical room; soft light, order; no faces.
The most accurate predictions concern cancer, pregnancy complications, circulatory pathologies and mental disorders, with C-index above 0.8.
The number that changes everything: 585,000 hours
No physician in history has analysed 585,000 hours of sleep.
Chalet window at dawn framing the snowy Engadine peaks seen from an unmade bed; cold natural light, stillness; no faces.
SleepFM has, uncovering patterns invisible to the human eye. This does not replace the physician: it provides an unprecedented early-warning tool.
How Klinik Sankt Moritz's Digital Twin applies this research
Silent corridor of an Alpine clinic at dawn, warm materials (wood and stone) and soft light; a mood of clinical calm; no faces.
Modern wearables — Oura Ring, Whoop, Fitbit, Apple Watch — already measure sleep phases with good accuracy. The Digital Twin structures this data according to SleepFM criteria, generating a risk profile updated every morning.
Bedroom of an Engadine chalet just before dawn: cold bluish light from the window, pale linen sheets, a smart ring and watch resting on the nightstand; no faces.
It is the first level of an active prevention system certified by Klinik Sankt Moritz physicians.
Why this is revolutionary for medical tourism
Macro detail of a wearable ring and a smartwatch recording sleep phases in low light; night-blue tones, soft reflections; no faces.
A patient arriving at Klinik Dubai carries months of sleep data. The Digital Twin has already built their risk profile. The physician starts from that person's biological truth, collected while they slept in their own bed.
Luminous chart of REM and deep-sleep phases projected on the dark wall of a premium clinical room; soft light, order; no faces.
Mignot et al. — Nature Medicine (2026) — https://www.nature.com/articles/s41591-025-04133-4 · www.nature.com
On the same topic
- 12 Years of Data, One Clear Finding: Your Sleep Profile Today Predicts Your Dementia Tomorrow.12-year follow-up on 2,667 men: fragmented sleep increases dementia risk by 35% and cardiovascular event risk by 32%.
- 15 Years Before the Diagnosis, Your Sleep Already Knew. Now So Does Science.Analysis on over 1 million EHR records: sleep disorder risks emerge up to 15 years before neurodegenerative disease diagnosis.
- 52,952 People, One Clear Result: Your Sleep Predicts Atrial Fibrillation.The world's largest study on wearables and atrial fibrillation: 52,952 patients, objective sleep data as independent predictors. Discover what we measure for you.