Demo
A check-engine light
for burnout.
Run at 100% for long enough and something breaks. AlloStatus tracks a daily resilience buffer from your wearables and lifestyle, and lights up early — when the trend starts sliding — so you can ease off before you hit a wall, not after.
Nothing pulled up yet. Generate a sample to explore the dashboard with synthetic data, or sign in to connect your own wearables.
How it works
From raw signals to one honest number.
Read your signals
Wearables feed HRV, sleep timing and resting heart rate; you log diet, social connection and exercise — six factors in all.
Compare to your own normal
Each factor is scored against your rolling 30-day baseline, so “good” means good for you — not a population average.
One resilience buffer
The six combine into a single 0–100 score, with the factors draining it most ranked so you know exactly where to act.
Caught early
The check-engine light watches the trend, not just today, and lights up while a slide is still easy to reverse.
The weights, in full
Each factor is compared against your own rolling 30-day baseline, capped so one bad reading can't dominate, then combined with these literature-anchored weights into a 0–100 buffer. The weights are the whole model — no black box.
- Heart-rate variability22%
McEwen, 2007 — autonomic dysregulation is among the strongest single predictors of allostatic load.
- Sleep consistency20%
Seeman et al., 2001 — HPA-axis and metabolic risk cluster with irregular sleep timing.
- Resting heart rate18%
Seeman, 1997 — resting cardiovascular tone in the allostatic-load index.
- Exercise15%
McEwen & Stellar, 1993 — regular activity buffers cortisol and inflammatory load.
- Diet quality15%
Allostatic-load metabolic cluster — glucose, lipids, adiposity.
- Social support10%
Seeman, 1996 — social integration as an HPA-axis buffer.