Playing out “what-if” futures with a sensor world model
Knowing your health age tells you where you stand today. Turning that number into a personalized plan requires answering a “what-if” (or counterfactual) question: What will happen to my body over the next 12 weeks if I change specific habits, and which plan can I realistically stick with?
Simply plugging new step or sleep targets into a static calculator misses how the body adapts as a connected system. When you consistently move more and sleep better over several weeks, your resting heart rate and heart rate variability gradually improve too, creating extra health benefits downstream.
To capture these dynamics, we developed Sensor World Model (SensorWM), an action-conditioned world model pre-trained on 2.28 million person-weeks of de-identified data from roughly 100,000 consenting Fitbit users. Given two weeks of baseline wearable data, SensorWM forecasts how 20 physiological markers will evolve over the next 12 weeks under different daily steps, sleep, and cardio routines, outperforming general-purpose time-series foundation models like TimesFM while preserving the clinical patterns associated with diabetes, hypertension, and insulin resistance.
We paired SensorWM with a feasibility-constrained optimizer and a language model coaching agent to do three things:
- Simulate: SensorWM rolls out 125 candidate 12-week habit combinations for each person, comparing them against a “status-quo” projection if habits stay the same.
- Filter for realism and safety: The most aggressive workout plan doesn’t help if it causes burnout in week two. Our optimizer weighs projected health-age reductions against each person’s historical habit flexibility and clinical safety bounds, picking a more ambitious target (−2.3 years) for someone with high baseline flexibility, and a gentler ramp (−1.3 years) for someone whose routine is more constrained.
- Coach: The language model translates the top-ranked pathways into a supportive, progressive 12-week coaching plan.
