Supplements

Sleep physiology features from digital trackers predict next-day physical fatigue in healthy adults with moderate accuracy

This exploratory study found that sleep tracker-derived features, particularly respiratory rate and REM sleep duration, could predict next-day physical fatigue in healthy adults with an AUC of 0.75. Predictive performance was lower in neurodegenerative disease (AUC=0.62) and immune-mediated inflammatory disease cohorts, indicating limited generalizability to chronic disease populations.

Last updated: Jul 7, 2026•0 RCTs•📖 Read as article →

Evidence Score

Evidence Score34/100
Human RCT☆☆☆☆☆
Meta-analysis☆☆☆☆☆
Mechanism★★★★★
Safety★★★★☆
Confidencelow

Study Evidence

Study 1. Exploring the feasibility of modeling next-day fatigue and sleepiness using digital sleep tracker data in neurodegenerative and immune-mediated inflammatory diseases.

observational

Zhai B, Chen L, Ma X, Pinaud C, Chatterjee M, Kortelainen JM, Rehman RZU, Ahmaniemi T, Avey S, Guan Y, Macrae V, Hinchliffe C, Del Din S, Manyakov NV, Göder R, Romijnders R, Maetzler W, Reilmann R, Aufenberg S, Schubert R, van der Woude CJ, Zhang D, Ng WF · Frontiers in digital health (2026)

Participants: N/A
Duration: 3,062 nights (average ~23 nights per participant)
Intervention: Use of consumer- and research-grade sleep trackers (BedSensor, ZKONE, DREEM 2) for overnight sleep monitoring
Outcome: Next-day physical fatigue, mental fatigue, and daytime sleepiness measured via patient-reported outcomes
Effect Size: AUC=0.75 for physical fatigue in healthy adults; AUC=0.62 in NDD; AUC=0.66 for mental fatigue in healthy adults; AUC=0.66 for daytime sleepiness in NDD
Population: 134 participants (42 healthy adults, 39 with neurodegenerative diseases, 53 with immune-mediated inflammatory diseases) across four European centres

Result:

PubMed: 42388291DOI: 10.3389/fdgth.2026.1752629

Mechanism Graph

Sleep trackers measure physiological and sleep-architecture features (e.g., respiratory rate, REM duration, REM latency, deep sleep)
↓
Machine learning models use these features to classify next-day fatigue and sleepiness levels
↓
Respiratory rate and REM sleep duration are key predictors in healthy adults
↓
Result: Models show preliminary discriminative capacity for next-day physical fatigue in healthy adults

Limitations

  • ⚠Outcome binarisation using a global threshold may conflate between-person disease-group differences with within-person symptom variation
  • ⚠Predictive performance in chronic disease cohorts remains limited, underscoring need for larger, multimodal studies
  • ⚠Exploratory analysis with small sample sizes per subgroup

Frequently Asked Questions

What sleep features were most predictive of next-day fatigue?▼

Respiratory rate and REM sleep duration were the main drivers for predicting physical fatigue in healthy adults, while REM latency and deep sleep were key features in the neurodegenerative disease group.

How accurate were the sleep trackers in predicting fatigue?▼

The best model achieved an AUC of 0.75 for next-day physical fatigue in healthy adults, indicating moderate discriminative capacity. Performance was lower in disease groups, with AUCs around 0.62-0.66.

Can these findings be applied to people with chronic diseases?▼

Not directly. The predictive performance was limited in neurodegenerative and immune-mediated inflammatory disease cohorts, suggesting that disease-specific models and larger studies are needed.

What type of sleep trackers were used in this study?▼

Three devices were used: BedSensor (a bed-mounted sensor), ZKONE (a wearable), and DREEM 2 (a headband), covering both consumer- and research-grade trackers.

Products

Affiliate links coming soon. We only recommend products that match the doses and forms used in the cited research.

References

  1. 1.Zhai B, Chen L, Ma X, Pinaud C, Chatterjee M, Kortelainen JM, Rehman RZU, Ahmaniemi T, Avey S, Guan Y, Macrae V, Hinchliffe C, Del Din S, Manyakov NV, Göder R, Romijnders R, Maetzler W, Reilmann R, Aufenberg S, Schubert R, van der Woude CJ, Zhang D, Ng WF. "Exploring the feasibility of modeling next-day fatigue and sleepiness using digital sleep tracker data in neurodegenerative and immune-mediated inflammatory diseases.." Frontiers in digital health, 2026. PMID: 42388291 DOI: 10.3389/fdgth.2026.1752629
Disclaimer: This content is for educational purposes only and is not medical advice. Evidence scores reflect the quality and quantity of available research, not clinical recommendations. Always consult a healthcare professional before starting any supplement or intervention.