Bayesian Cardiovascular Digital Twin

5-state Kalman filter/smoother with UKF nonlinear dynamics
Generated 2026-03-24 00:24 · Post-HSCT Patient
Days Modeled
79
2026-01-04 to 2026-03-23
Latent States
5
KF + UKF estimation
Alert Events
22
1 in last 7 days
Post-Drug Days
8
Since 2026-03-16
Log-Likelihood
-313.43
EM-learned parameters

Latent State Trajectories

The Kalman smoother estimates 5 latent physiological states from noisy, intermittent sensor data. Solid lines show the smoothed posterior mean; shaded bands show 95% credible intervals. Dotted lines overlay the UKF estimates for comparison.

Observations vs Model Estimates

Raw sensor observations (dots) overlaid with the model's filtered estimates (lines). Good model fit is indicated by the line tracking the dots closely.

Prediction Performance

One-Step-Ahead Prediction Quality

Innovation Alerts (22 total, 1 in last 7 days)

2026-03-23: HRV (RMSSD) deviation = 3.3 sigma

Ruxolitinib Drug Response (started 2026-03-16)

StatePre-drug MeanPost-drug MeanShift (SD)Directionp-valueTime Constant
Autonomic Tone-0.0830.2678+0.474improved0.24383.17 days
Cardiac Reserve-0.43540.5381+1.071improved0.03985.37 days
Circadian Phase0.95910.0688-1.659stable0.04.77 days
Inflammation Level-0.56170.0919+0.673worsened0.00774.89 days
Sleep Quality-0.1350.3732+0.725improved0.00.28 days

KF vs UKF Comparison

The Unscented Kalman Filter uses nonlinear circadian dynamics and exponential autonomic decay with sigma-point propagation (no Jacobian needed). Large differences from the linear KF suggest significant nonlinear dynamics.

Multi-Modal Sensor Fusion Quality

Sensor Contribution to State Estimation

Residual Diagnostics

White noise residuals (Ljung-Box p > 0.05) indicate the model captures temporal structure well. Significant autocorrelation suggests model misspecification for that sensor.

Disclaimer: This is a computational model for research and self-monitoring purposes only. It is NOT a medical device and should NOT be used for clinical decision-making. The Oura Ring is a consumer wearable; its measurements have known limitations in accuracy. All state estimates are model-dependent and should be interpreted with appropriate uncertainty. Consult qualified healthcare professionals for medical decisions.