A study in JMIR Medical Informatics (2025) analysed data from 272 Fitbit participants over at least 5 working days, deriving 26 biometric indicators.
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.
Explainable AI (XAI) identified HRV and sleep quality as the key biomarkers associated with metabolic syndrome.
What metabolic syndrome is and why it matters
Macro detail of a wearable ring and a smartwatch recording sleep phases in low light; night-blue tones, soft reflections; no faces.
Metabolic syndrome — combining abdominal obesity, insulin resistance, hypertension, hypertriglyceridaemia and low HDL — affects \~25% of the world's adult population and is the main predictor of type 2 diabetes and cardiovascular disease.
Luminous chart of REM and deep-sleep phases projected on the dark wall of a premium clinical room; soft light, order; no faces.
Explainable AI (XAI): not just results, but explanations
Chalet window at dawn framing the snowy Engadine peaks seen from an unmade bed; cold natural light, stillness; no faces.
Unlike black-box AI models, XAI provides the explanation: which variables contributed most, in which direction, with what weight. In medicine, a physician needs to understand why the system says what it says.
The most predictive indicators
Silent corridor of an Alpine clinic at dawn, warm materials (wood and stone) and soft light; a mood of clinical calm; no faces.
Among 26 indicators, the most predictive of metabolic syndrome: HRV, midsleep time (indicator of chronotype and circadian rhythm) and total sleep time. Combined, these three outperform many traditional blood tests in predictive value.
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 Digital Twin as an XAI engine
The Digital Twin does not just tell you 'you are at risk': it explains which biological behaviours contribute most and how to modify them. It is the difference between a test result and a strategy.
Macro detail of a wearable ring and a smartwatch recording sleep phases in low light; night-blue tones, soft reflections; no faces.
Kim et al. — JMIR Medical Informatics (2025) — https://medinform.jmir.org/2025/1/e69328 · medinform.jmir.org
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.