Oura Ring Gen 4 sensor data, not clinical measurementsN=1 case study, not validated for clinical decisionsHEV diagnosed Mar 18; Day 109 post-ruxolitinibMore
Consumer wearable data can support exploratory review only. The HEV diagnosis, temporally confounded with treatment start, remains a material confounder.

Ruxolitinib Forecast

HRV (7-DAY)
Low
25.9ms
Target: 15 ms ESC threshold
Average RMSSD over past 7 nights
LOWEST HR (7-DAY)
Normal
57.9bpm
Target: <70 bpm
Mean lowest heart rate over past 7 nights
DAYS ON RUX
Info
108days
Since 2026-03-16
Days since ruxolitinib initiation
FIRST TARGET ETA
Already met
HRV reaching ESC 15 ms threshold
Expected date based on current trajectory
FORECAST SUMMARY

Forecast Summary

Treatment duration: 108 days on ruxolitinib

HRV (RMSSD) Forecast:
• Current 7-day mean: 25.9 ms (slope: +0.91 ms/week, R²=0.129)
• Best model: exponential
• ESC Threshold (15 ms): Already met
• HSCT Range Low (25 ms): Already met
• Population 25th pct (36 ms): 2026-08-03 (50-95% CI: 2026-08-04 to 2026-11-06)

Heart Rate Forecast:
• Current 7-day mean lowest HR: 57.9 bpm (slope: -1.07 bpm/week)
• Normal (<70 bpm): Already met
• Good (<65 bpm): Already met
• Excellent (<60 bpm): Already met
TRAJECTORIES

HRV & HR Trajectories with Forecast

MILESTONES

Milestone Timeline

MODEL COMPARISON

Model Comparison: Linear vs Exponential (HRV)

PHASE CONTEXT

Three-Phase Recovery Context

METHODOLOGY

Methodology & Caveats

Data: 103 post-ruxolitinib HRV observations, 103 post-ruxolitinib HR observations from Oura Ring Gen 4 (consumer wearable, not clinical-grade).

Linear model: OLS regression on day number since treatment start (2026-03-16). Bootstrap: 1000 resamples for confidence intervals.

Exponential model: y = a · (1 - e-t/τ) + baseline, fit via scipy.optimize.curve_fit with bounded parameters. Model selection by AIC (lower = better).

Three scenarios: Optimistic (75th pct slope), Expected (50th pct), Conservative (25th pct).

Limitations (small N): With only ~103 data points, forecasts carry wide confidence intervals and may shift substantially as more data accumulates. Physiological recovery is non-linear and depends on factors not captured in wearable data (infection status, medication changes, immune reconstitution). These projections are exploratory, not clinical recommendations.