White Paper

Evidence-Led Burnout Risk Monitoring

Contents

  1. Executive Summary
  2. The Problem: Why "Feeling" Alone Is Not Enough
  3. Scientific Foundation: Three Physiological Pillars
    1. HRV (Autonomic Balance)
    2. Sleep Quality & Recovery
    3. Resting Heart Rate & Allostatic Load Proxy
  4. Algorithm Methodology
    1. From Raw Data to Personal Baseline
    2. Cold Start Calibration
    3. Multi-Metric Integration
  5. Use Cases
  6. Future Path: Broader Mental Health Monitoring
  7. Compliance & Safety
  8. References

1. Executive Summary

Burnout is recognized by the World Health Organization as an occupational phenomenon in ICD-11, reflecting its relevance to the workplace rather than a standalone medical diagnosis.

Most organizations still rely on self-report questionnaires (e.g., Maslach Burnout Inventory) to understand burnout risk. These tools are useful, but they are inherently episodic and subjective — they capture how a person reports feeling at a point in time, not how the body is adapting day-to-day.

Wane is a preventive monitoring product. It uses physiological signals from consumer wearables (e.g., Apple Watch, Oura, Garmin, WHOOP — depending on integrations) to build a personal baseline and surface meaningful deviations associated with chronic stress and reduced recovery capacity. Wane then converts these signals into a daily Wane Score and trend insights, designed to support earlier self-awareness and proactive behavior.

This product direction is aligned with emerging research showing that combining wearable-derived physiology with psychosocial/occupational context can improve classification of burnout risk compared with questionnaires alone (e.g., an HRV-augmented model reported AUC-ROC ~0.83 in a small healthcare sample).

Important: Wane is not a medical device, does not diagnose or treat burnout, depression, or any health condition, and should be used as a wellness and performance tool that complements — not replaces — clinical care and organizational policy.

2. The Problem: Why "Feeling" Alone Is Not Enough

Burnout is typically gradual. By the time someone clearly identifies chronic exhaustion or reduced efficacy, the underlying physiological load and recovery disruption may have been present for some time.

Self-report tools also face structural limitations:

Wane addresses a different layer: the physiological pattern of stress and recovery — measured passively and observed over time.

3. Scientific Foundation: Three Physiological Pillars

Wane's scoring logic is anchored in three signal families that are repeatedly discussed across stress, recovery, and burnout-adjacent research. Wane uses them as risk markers, not diagnostic criteria.

3.1 — HRV (Autonomic Balance) Primary metric: RMSSD

Heart Rate Variability (HRV) reflects short-term fluctuations between heartbeats and is commonly used as an indicator related to autonomic nervous system regulation. International standards describe HRV measurement and interpretation considerations.

Why RMSSD

RMSSD is widely used in wearable and research contexts as a time-domain HRV metric linked to parasympathetic activity and short-term variability. Reviews discussing HRV in stress contexts frequently highlight RMSSD's practical robustness, while also noting methodological variability across studies.

Evidence Direction

A recent predictive model in healthcare workers reported improved burnout classification when HRV features were added to psychosocial/occupational factors (AUC-ROC ~0.83 in that dataset). This supports the product hypothesis that physiology can contribute incremental signal beyond questionnaires.

3.2 — Sleep Quality & Recovery Architecture, Continuity, Fragmentation

Sleep is not only duration. Wearables can capture proxies for sleep continuity and stage distribution that are useful for tracking recovery trends.

Large observational work in healthcare workers has shown a strong association between poor sleep quality and all burnout dimensions.

Wearable-based studies using longitudinal modeling also support a bidirectional pattern where daytime stress and strain relate to disrupted nocturnal recovery indicators, reinforcing the value of tracking sleep as a recovery pillar.

Wane therefore weights sleep via:

  • Continuity/fragmentation proxies (e.g., WASO),
  • Restorative components (deep/REM where available),
  • Efficiency and consistency.

3.3 — Resting Heart Rate & Allostatic Load Proxy

Resting heart rate is broadly available across devices and can reflect sustained arousal and reduced recovery when deviating from a person's normal range.

Classic work comparing burnout patients to healthy controls reported differences including elevated heart rate and altered stress biology patterns, supporting the concept that burnout-adjacent states can have measurable physiological correlates.

Separate wearable-focused work in working populations suggests that chronic stress — especially when combined with depressive symptoms — can be associated with detectable heart rate pattern changes (e.g., circadian flattening).

Wane uses RHR as a trend-based indicator relative to personal baseline — not as a universal threshold.

4. Algorithm Methodology

4.1 — From Raw Data to Personal Baseline (n=1)

Physiology varies widely between individuals. Fixed "one-size thresholds" produce false alarms for some users and miss meaningful deterioration for others.

Wane prioritizes within-person change:

  • Short-term vs. long-term averages (trend detection),
  • Volatility and persistence of deviations,
  • Cross-pillar confirmation (HRV + sleep + RHR).

4.2 — Cold Start Calibration (Responsible Use of Norms)

When a new user has limited history, Wane can use population reference ranges only for orientation, not for judgment.

For example, the Lifelines cohort provides HRV reference values stratified by age and sex, which is useful as a starting reference until personal baselines stabilize.

Wane transitions to fully personalized baselines as sufficient individual data accumulates.

Note: Industry datasets and blogs can be used internally for sanity checks, but Wane's external scientific claims rely primarily on peer-reviewed or clearly identified preprint sources.

4.3 — Multi-Metric Integration (Why a "Pillars" Architecture)

Literature reviews on wearables for burnout and well-being highlight that no single physiological marker is sufficient across individuals and contexts; combining signals is a more defensible approach.

Accordingly, Wane produces:

  • A daily Wane Score (0–100),
  • Pillar subscores (HRV / sleep / RHR),
  • Trend alerts when multi-pillar deviation persists.

5. Use Cases

Consumer: "High-Functioning Strain"

A user's performance appears stable, but their recovery indicators trend down: HRV decreases vs. baseline, sleep continuity worsens, and resting HR drifts upward. Wane flags elevated risk and suggests evidence-based recovery behaviors (sleep consistency, reduced late alcohol, pacing training load, stress hygiene). Wane does not claim the user "has burnout" — it flags a risk trend.

B2B HR / Employer Wellness: "Team-Level Prevention"

For organizations, Wane can provide aggregated, privacy-preserving insights (e.g., department-level recovery trend indices, adoption, and risk distribution). No employer view includes medical data interpretation or individual diagnosis, and users retain control of personal data visibility.

6. Future Path: Broader Mental Health Monitoring

Burnout risk overlaps with broader stress and mood-related patterns. Sleep architecture metrics — such as REM latency — have been studied in relation to depression scores, suggesting that sleep signals may carry broader mental-health-adjacent information.

Wane's roadmap can expand from burnout risk monitoring toward a broader recovery and mental well-being platform — while maintaining strict boundaries: screening and trend awareness, not diagnosis or treatment.

7. Compliance & Safety

Wane is a wellness product intended for informational purposes only. It:

8. References

  1. WHO — Burn-out as an occupational phenomenon (ICD-11).
  2. Rubio-López et al. (preprint) — HRV + psychosocial factors, AUC-ROC ~0.83 in healthcare sample.
  3. HRV Standards (ESC/NASPE Task Force, 1996).
  4. HRV & stress review context (RMSSD commonly used; methodological limits noted).
  5. Chen et al. (2023) — Sleep quality & burnout in healthcare workers. Sleep Medicine, 102, 205–212.
  6. Frontiers in Digital Health — Wearable longitudinal modeling (stress ↔ sleep recovery indicators).
  7. De Vente et al. (2003) — Physiological differences in burnout vs controls (HR/cortisol patterns). Occupational and Environmental Medicine, 60(Suppl 1), i54–i61.
  8. Lutin et al. (2022) — Chronic stress + depressive symptoms & HR pattern changes. Frontiers in Psychiatry, 13, 1022298.
  9. Lifelines cohort — HRV reference values (age/sex stratified).
  10. JMIR — Wearable technologies for burnout/well-being (scoping review).
  11. REM sleep latency & depression score association (pilot).