Rare Disease Trajectory Simulator

Five synthetic patients, five rare diseases, one shared probabilistic architecture. The demonstrator shows how observed physiology updates a posterior estimate of current latent disease state, which is then propagated into a posterior predictive trajectory and clinically defined event risk.

Research demonstrator: all patients, parameters, thresholds and observations are synthetic and illustrative. Nothing shown is clinically validated or intended for patient care.
Disease knowledge
Natural history + priors
Observed physiology
Wearable + clinical data
Posterior current state
Latent state + uncertainty
Predictive trajectory
24–72 h distribution
Event probability
Disease-specific endpoint

Posterior predictive disease trajectory

Observed latent-state estimate to the vertical divider; posterior predictive median and 50%, 80% and 95% credible intervals to the right. Higher state values represent greater disease burden for this demonstrator.

Observed physiological signals

Event-risk forecast

Posterior state & N-of-1 learning

The posterior narrows as patient-specific observations accumulate. In an implementation, the full joint posterior over latent state, patient-specific parameters and disease parameters would be propagated forward rather than reduced to these display summaries.

Why this patient is informative

Recent synthetic observations

Simulation logic is deliberately transparent rather than clinically calibrated: a disease-specific latent burden trajectory generates synthetic physiology; observations update a posterior state estimate; Monte-Carlo-style deterministic quantile approximations create the forecast envelope; forecast state, slope and selected physiological features determine synthetic event risk. The purpose is to test the architecture and interaction design before disease-specific statistical fitting.