Supplements

Wearable sleep trackers show feasibility for predicting next-day physical fatigue in healthy adults using sleep physiology features.

This exploratory study found that machine learning models using sleep tracker data achieved an AUC of 0.75 for predicting next-day physical fatigue in healthy adults, with respiratory rate and REM sleep duration as key features. Predictive performance was lower in neurodegenerative disease (AUC=0.62) and immune-mediated inflammatory disease cohorts. The findings are preliminary and limited by outcome binarisation and small sample sizes.

Last updated: Jul 13, 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 collect physiological and sleep-architecture features (e.g., respiratory rate, REM duration, REM latency, deep sleep)
↓
Machine learning models are trained on these features to predict next-day fatigue and sleepiness
↓
Models are evaluated using leave-one-subject-out cross-validation
↓
Result: Preliminary discriminative capacity for next-day physical fatigue, especially in healthy adults

Limitations

  • ⚠Outcome binarisation using a global threshold may conflate between-person disease-group differences with within-person symptom variation
  • ⚠Small sample sizes for chronic disease subgroups limit generalisability
  • ⚠Predictive performance in chronic disease cohorts remains limited

Frequently Asked Questions

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

Respiratory rate and REM sleep duration were key predictors for physical fatigue in healthy adults; REM latency and deep sleep were important in neurodegenerative disease.

How was the study's predictive performance measured?▼

Performance was measured using area under the receiver operating characteristic curve (AUC) from machine learning models with leave-one-subject-out cross-validation.

Did the sleep trackers accurately measure sleep compared to polysomnography?▼

A sub-study with 28 participants showed that the sleep trackers had moderate agreement with polysomnography (PSG), the gold standard for sleep measurement.

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

Predictive performance was limited in neurodegenerative and immune-mediated inflammatory disease cohorts, so further research with larger, multimodal studies is needed before clinical application.

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.