Skip to content
Sleep Week

Future capability, systems physiology

Recovery intelligence as a tool for predicting disease.

One night of measured physiology contains more than a sleep score. It is a readout of how the body's major systems are working together. New foundation models read the same recording a sleep lab already collects and forecast risk across more than 100 conditions, years before symptoms.

Concept in development, subject to clinical review and regulatory pathway

The finding

585,000 hours of physiology, 130 predictable conditions.

Stanford Medicine researchers trained SleepFM, the first sleep foundation model, on polysomnography from 65,000 people, then paired it with up to 25 years of health records.

585,000

Hours of polysomnography used for training

65,000 participants

1,000+

Disease categories screened in health records

Stanford Sleep Medicine Center

130

Conditions predictable with reasonable accuracy

Nature Medicine, Jan 2026

25 yrs

Longest outcome follow-up in the cohort

Records from 1999 to 2024

Source: Stanford Medicine, "New AI model predicts disease risk while you sleep," January 6, 2026, reporting on a study published in Nature Medicine. Sleep Week does not operate SleepFM. This page describes a proposed future service layer.

How it reads a night

Six systems, one language.

A training method called leave-one-out contrastive learning hides one channel and forces the model to reconstruct it from the others, so the systems learn to speak to each other, the same relationships Human Recovery Intelligence is built to surface.

Hover or select a channel to read what it contributes.

Fusion

Foundation model output

A ranked risk horizon across 130 conditions, read from system relationships

The strongest signal is not any single channel. It is incoherence between channels, a brain that reads asleep while the heart reads awake.

Predictive strength

Where the signal is strongest.

C-index is the probability the model correctly ranks which of two people experiences an event first. Models near 0.70 are already used clinically.
Filter
Scale

C-index by condition, as reported in the Stanford Medicine study. 0.50 is chance. Bars are scaled from the 0.50 chance baseline, so differences between conditions are visible.

Strongest categories

  • Cancers
  • Circulatory conditions
  • Pregnancy complications
  • Mental health disorders
  • Neurodegenerative disease

Risk horizon

  1. Night 1

    8 hours of physiology recorded

  2. Minutes

    5-second windows tokenized, the language of sleep

  3. Same week

    Clinician-reviewed risk ranking issued

  4. 1 to 25 years

    Outcome window the model was validated against

Why it changes the deliverable

From a sleep score to a coherence-informed risk horizon.

Conventional sleep report

Predictive sleep analysis

Data used

A handful of summary metrics

Every channel, every five seconds, all night

Most of a polysomnogram is discarded today.

Question answered

How did you sleep last night

What is your physiology signalling about the next decade

Time frame

One night, retrospective

Validated against outcomes up to 25 years out

Modality handling

Channels read separately by a scorer

Channels contrasted against each other by the model

Disagreement between brain and heart carried the most information.

Output

Apnea index and stage percentages

Ranked, clinician-reviewed risk across condition families

Proposed Sleep Week pathway

How this would enter the program.

A fourth-night optional add-on to the existing four-day intensive, gated by consent and physician review at every step.
  1. 01

    Consent and eligibility

    Opt-in, separate from the core program, with a written scope of what is and is not being predicted.

  2. 02

    Full polysomnography night

    Lab-grade montage in the Sleep Suite rather than wearables alone.

  3. 03

    Model-assisted analysis

    Multimodal risk ranking produced as decision support, never as a diagnosis.

  4. 04

    Physician review and referral

    A clinician interprets, contextualises and routes anything actionable to real care.

Concept stageNot available for bookingResearch collaboration sought

Guardrails

Prediction is not diagnosis.

A risk ranking is a probability statement about groups of people, not a verdict about one person. Sleep Week would deploy this only with the limits below in force.

No unaccompanied results

Nothing is released without a physician reviewing it with the guest first.

No screening claims

The model is not a cleared screening test for cancer, dementia or cardiac disease.

Interpretability is partial

Researchers can see which channels drive a prediction, not the full reasoning.

Data stays yours

Recordings would not be used for model training without explicit separate consent.

Read the research context

SleepFM was developed by Stanford Medicine researchers with colleagues at the Technical University of Denmark, Copenhagen University Hospital, BioSerenity, University of Copenhagen and Harvard Medical School, with co-senior authors Emmanuel Mignot, M.D., Ph.D., and James Zou, Ph.D. The team is exploring whether wearable data can extend the model beyond the lab. Published in Nature Medicine on January 6, 2026.

Related

Where measurement already happens.

Predictive analysis would sit on top of the instrumentation the program runs today.