Driving · 2026-11-09
Personalized health coaching via coachable health age and counterfactual wearable trajectories
Simon A. Lee, Zeinab Esmaeilpour, Menglian Zhou, Marius Guerard, Sohrab Sidhu, Alexandru Solot, Hamid Palangi, Pramod Rudrapatna, Ming-Zher Poh, Max A. Xu, Daniel McDuff, Dimitrios Antos, Yuzhe Yang, Jeffrey N. Chiang, Anthony Z. Faranesh, Lindsey Sunden, Mark Malhotra, Shwetak Patel, A. Ali Heydari, Ahmed A. Metwally
AI-assisted summary based on the paper. Consult the linked source for methods and limitations. Benchmark numbers appear after editor verification.
TL;DR
The authors introduce Coachable Health Age (CHA), an interpretable health-age metric from passively captured, modifiable wearable signals. They also develop Sensor World Model (SensorWM), an action-conditioned wearable world model pretrained on 2.28M person-weeks. CHA and SensorWM are integrated into an agentic counterfactual coaching system that synthesizes personalized 12-week coaching plans preferred by lifestyle coaches and rated safe by clinicians.
Why it matters
The work targets the gap between retrospective wearable summaries and quantitative, actionable behavioral prescriptions by adding (1) a coachable, interpretable health-age target (CHA) and (2) action-conditioned counterfactual physiological forecasting (SensorWM). This is then coupled to an optimization-based coaching agent and evaluated by both lifestyle coaches and board-certified clinicians, including safety criteria for exercise intensity.
Method
- Build Coachable Health Age (CHA) from modifiable wearable domains (resting heart rate proxy, sleep duration, daily steps, and weekly Active Zone Minutes) on an age-equivalent scale tied to cardiometabolic risk constructs.
- Pretrain Sensor World Model (SensorWM), an action-conditioned latent world model on longitudinal wearable data (96,957 participants; 2.28M person-weeks; 2.2M person-weeks stated in abstract), to auto-regressively simulate future physiological trajectories over 12-week horizons conditioned on candidate actions.
- Integrate CHA and SensorWM into an agentic counterfactual coaching system using feasibility-constrained optimization to rank counterfactual pathways and generate personalized 12-week plans for evaluation by coaches and clinicians.
Abstract (from arXiv)
Personalized health coaching requires moving beyond retrospective wearable summaries toward quantitative, actionable behavioral prescriptions. We introduce Coachable Health Age (CHA), an interpretable health-age metric built from modifiable physiological and behavioral signals passively captured by consumer wearables. Across the WEAR-ME (N=2,780), All of Us (N=22,748), and longitudinal Fitbit (N=1,464) cohorts, CHA aligns with established cardiometabolic health constructs and improves prognostic discrimination for incident cardiovascular and metabolic disease beyond age, sex, and body mass index. To enable prospective behavioral optimization, we developed Sensor World Model (SensorWM), an action-conditioned wearable world model pretrained on over 2.2 million person-weeks of longitudinal sensor data from approximately 100,000 participants. SensorWM accurately forecasts multi-week physiological responses to candidate lifestyle changes ($R^2=0.664$), outperforming generic time-series foundation models while preserving downstream clinical signal for diabetes, hypertension, and other health outcomes. Finally, we integrate CHA and SensorWM into an agentic counterfactual coaching system to synthesize personalized 12-week coaching plans. In blinded paired reviews, certified lifestyle coaches preferred counterfactual-grounded plans over plans grounded in wearable history alone for overall quality (71.4%, P < 0.001) and anticipated adherence (71.0%, P < 0.001), and board-certified clinicians judged 99.2% of counterfactual-grounded plans to meet clinical safety criteria (vs. 97.6% of comparison plans). Automated evaluations across the full cohort (N=2,780) also favored counterfactual-grounded plans. By closing the loop between longitudinal tracking, trajectory prediction, and counterfactual coaching, our framework provides a scalable path to systematically improve cardiometabolic health.
Related papers
- From Prediction to Action: Population Health World Model for Digital Medicine
- Repeated-Measure Leakage, Distribution Shift, and Reliability under Partial Observation in Patient World Models
- Forecasting Patient Trajectories from the Electronic Health Records with Action-Conditioned World Models
- PatientWM: Towards Generalizable Clinical World Models via Unified Patient States
- InertiaMPDD: Multimodal Personalized Depression Detection via Emotional Inertia-Inspired Dynamics Modeling
Publication record
Bibliographic evidence describes where and when a record appeared. It does not validate scientific claims.
First public release: Date not supplied · Indexed by Pub-AI: 2026-11-09 UTC
Personalized health coaching via coachable health age and counterfactual wearable trajectories
Source date: Date not supplied · Original record ↗
- arxiv
- 2611.08568
Imported from the existing registry. No new publication milestone asserted.
Abstract · arxiv
Personalized health coaching requires moving beyond retrospective wearable summaries toward quantitative, actionable behavioral prescriptions. We introduce Coachable Health Age (CHA), an interpretable health-age metric built from modifiable physiological and behavioral signals passively captured by consumer wearables. Across the WEAR-ME (N=2,780), All of Us (N=22,748), and longitudinal Fitbit (N=1,464) cohorts, CHA aligns with established cardiometabolic health constructs and improves prognostic discrimination for incident cardiovascular and metabolic disease beyond age, sex, and body mass index. To enable prospective behavioral optimization, we developed Sensor World Model (SensorWM), an action-conditioned wearable world model pretrained on over 2.2 million person-weeks of longitudinal sensor data from approximately 100,000 participants. SensorWM accurately forecasts multi-week physiological responses to candidate lifestyle changes ($R^2=0.664$), outperforming generic time-series foundation models while preserving downstream clinical signal for diabetes, hypertension, and other health outcomes. Finally, we integrate CHA and SensorWM into an agentic counterfactual coaching system to synthesize personalized 12-week coaching plans. In blinded paired reviews, certified lifestyle coaches preferred counterfactual-grounded plans over plans grounded in wearable history alone for overall quality (71.4%, P < 0.001) and anticipated adherence (71.0%, P < 0.001), and board-certified clinicians judged 99.2% of counterfactual-grounded plans to meet clinical safety criteria (vs. 97.6% of comparison plans). Automated evaluations across the full cohort (N=2,780) also favored counterfactual-grounded plans. By closing the loop between longitudinal tracking, trajectory prediction, and counterfactual coaching, our framework provides a scalable path to systematically improve cardiometabolic health.
