Using wearables to enable cardiovascular-kidney-metabolic (CKM) risk profiling for personalized coaching
Health & Bioscience
First seen by Oriel on .
AI summary
Google Research presents an investigational framework that uses wearable and optional blood data to estimate coachable CKM health age and simulate personalized 12-week habit interventions.
- The coachable health age model uses modifiable signals including resting heart rate, steps, sleep duration, and Active Zone Minutes, with optional VO2max and metabolic markers.
- SensorWM was trained on 2.28 million person-weeks from roughly 100,000 Fitbit users and forecasts 20 physiological markers under alternative 12-week routines.
- Lifestyle coaches preferred counterfactual-grounded plans in 71.4% of evaluations, while physicians found 99.2% within safe exercise limits and 97.6% physiologically accurate.
- A multimodal model evaluated in 819 participants combined wearable data with cholesterol-to-HDL ratio, eGFR, and HOMA-IR to profile cardiovascular, kidney, and metabolic strain.
- Evaluations were retrospective and offline; the models remain investigational research prototypes, not clinical diagnostic tools, and require prospective trials.
#wearables #machine learning #digital health #ckm syndrome
Generated by gpt-5.6-sol. Check the original for details.
Aliases
| Source | External ID | URL |
|---|---|---|
| Google Research Blog | https://research.google/blog/using-wearables-to-enable-cardiovascular-kidney-metabolic-ckm-risk-profiling-for-personalized-coaching/ | https://research.google/blog/using-wearables-to-enable-cardiovascular-kidney-metabolic-ckm-risk-profiling-for-personalized-coaching/ Read discussion |