Algorithm Design
Core Formula
Physiological Stress = (wHRV × RHRV) + (wHR × RHR) + (wACT × RACT)
50%
HRV Weight
30%
Heart Rate Weight
20%
Activity Weight
Component 1: HRV Risk Assessment
Heart Rate Variability (HRV) measures beat-to-beat variation in cardiac rhythm, reflecting parasympathetic vagal tone. RMSSD is used as the primary metric.
| Ratio to Baseline | Classification | Risk Adjustment |
|---|---|---|
| ≥ 100% | Excellent recovery | -5% (bonus) |
| 80-100% | Good recovery | 0% (neutral) |
| 60-80% | Moderate stress | +8% |
| < 60% | High stress | +15% |
Component 2: Heart Rate Risk Assessment
Resting heart rate elevation above personal baseline indicates sustained sympathetic activation.
| Deviation (bpm) | Classification | Risk Adjustment |
|---|---|---|
| Below baseline | Recovery indicator | -3% (bonus) |
| ±5 bpm | Normal variation | 0% |
| +6 to +10 bpm | Elevated | +4% |
| +11 to +15 bpm | High elevation | +8% |
| > +15 bpm | Critical | +12% |
Component 3: Activity Risk Assessment
Activity levels compared to personal baseline, with additional volatility penalty for boom-bust patterns.
| Activity Level | Classification | Risk Adjustment |
|---|---|---|
| > 80% of baseline | Normal | 0% |
| 50-80% | Reduced | +4% |
| 30-50% | Low | +8% |
| < 30% | Very low | +12% |
Validation and Accuracy
Correlation with Published Research
HRV-Fatigue correlation
Rao et al., 2020
Combined model performance
Frontiers Digital Health, 2025
Predictive window
Multiple studies
Limitations
Important Considerations
Individual variability
Mitigation: Baseline-relative calibration
Wearable accuracy
Mitigation: Quality scoring, multiple metrics
Confounding factors
Mitigation: User education, contextual notes
Cold start problem
Mitigation: Conservative absolute thresholds
Clinical Considerations
Intended Use
- Self-management with objective health data
- Pattern recognition for triggers
- Clinical support for discussions
NOT Intended For
- Medical diagnosis
- Replacement of clinical judgment
- Emergency health situations
References
Davenport TE, Stevens SR, VanNess JM, Stevens J, Snell CR. (2019)
"Conceptual model for post-exertional malaise in myalgic encephalomyelitis/chronic fatigue syndrome"
Work, 62(3): 505-513
Davis HE, McCorkell L, Vogel JM, Topol EJ. (2023)
"Long COVID: major findings, mechanisms and recommendations"
Nat Rev Microbiol, 21(3): 133-146
Rao N, et al. (2020)
"Heart rate variability as a biomarker for fatigue in chronic fatigue syndrome: A pilot study"
Journal of Translational Medicine, 18: 412
Komaroff AL, Lipkin WI. (2021)
"Insights from myalgic encephalomyelitis/chronic fatigue syndrome may help unravel the pathogenesis of postacute COVID-19 syndrome"
Trends Mol Med, 27(9): 895-906
Wirth K, Scheibenbogen C. (2021)
"A unifying hypothesis of the pathophysiology of myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS)"
Autoimmun Rev, 20(1): 102527
Full reference list with 10 citations available in the complete whitepaper document.