Oura Digital Twin Dashboard
Oura Gen 4: 2026-01-08 to 2026-10-06 (272 unique days, 327 sleep periods) · 10/10 analysis modules loaded · Ruxolitinib 10 mg BID from 2026-03-16
POST-HSCT BIOMETRIC MONITORING
Consumer wearable suggests a physiological shift after JAK inhibitor start
exploratory N=1 monitoring in a confounded window
p=0.126
Lowest raw
p-value
p-value
0.126
FDR-adjusted
q-value
q-value
10/11
Streams surviving
FDR correction
FDR correction
205,038
Biometric readings
analyzed
analyzed
Pre-Ruxolitinib to Post-Ruxolitinib
67 days (73 sleep periods) vs
205 days (254 sleep periods)
Key Finding
Temperature deviation shows the lowest raw p-value observed (p=0.126, q=0.126, 87% posterior probability) in a confounded 205-day post-intervention window. 10/11 CausalImpact streams reach raw p<0.05; 10/11 survive FDR correction. Separate UKF comparisons: Cardiac Reserve shift p<0.001, Sleep Quality shift p<0.001, Lowest HR p<0.001.
Temperature deviation shows the lowest raw p-value observed (p=0.126, q=0.126, 87% posterior probability) in a confounded 205-day post-intervention window. 10/11 CausalImpact streams reach raw p<0.05; 10/11 survive FDR correction. Separate UKF comparisons: Cardiac Reserve shift p<0.001, Sleep Quality shift p<0.001, Lowest HR p<0.001.
Temperature
p=0.126
Effect: -0.05°C
HRV (RMSSD)
21.3ms
vs healthy 42-49 ms | Kleiger 1987 / Bigger 1992
Resting HR
73bpm
Lowest HR p<0.001
SpO2
95.6%
BOS risk: MODERATE (39/100)
Sleep Efficiency
74%
Below 85% threshold
Autonomic Tone
0.21SD
UKF state | improved | p<0.001
GVHD Score
19/100
7d avg: 18
Anomaly Days
28/327
Feb 9 detected (28 anomaly days, N=1)
Interrupted Time Series: Temperature Response
CausalImpact BSTSTreatment Effect Sizes
CausalImpact + UKFDisease State Trajectory
rSLDS 4-State ModelAnomaly Detection
5-Algorithm EnsembleComposite Biomarker Trends
6 BiomarkersSpO2 & BOS Risk
Pulmonary ScreeningCombined Biosignal Timeline
5-Channel ViewHeart Rate Terrain Map
3D SurfacePhase Space Reconstruction
Nonlinear DynamicsSleep Architecture Heatmap
Epoch-LevelCircadian Rhythm Analysis
Cosinor ModelMethodology & Data Provenance
Data Source
Oura Ring Gen 4 (continuous PPG, accelerometry, thermometry)
Volume
182,298 HR readings · 22,740 HRV samples · 26,183 sleep epochs
Analysis Pipeline
CausalImpact (BSTS) · Unscented Kalman Filter (5 latent states) · rSLDS (4 disease states) · 5-algorithm anomaly ensemble · 6 composite biomarkers · Chronos-2 / ARIMA forecasting
Sleep Architecture
Deep: 15.5% Light: 51.3% REM: 13.6% Awake: 19.6%
For research and clinical discussion only. Not a diagnostic tool. All p-values are exploratory.