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.
This article is automatically generated from the structured evidence profile behind the claim above. Scores reflect the quality and quantity of available research, not clinical advice.
Wearable sleep trackers show feasibility for predicting next-day physical fatigue in healthy adults using sleep physiology features. The current body of evidence comprises 1 study. EvidenceHub rates the overall confidence at 34/100 (low).
The Claim
Wearable sleep trackers show feasibility for predicting next-day physical fatigue in healthy adults using sleep physiology features.
This conclusion is most relevant to: 134 participants (42 healthy adults, 39 with neurodegenerative diseases, 53 with immune-mediated inflammatory diseases) across four European centres.
What the Research Shows
The conclusion draws on 1 linked study. Highlights from the cited literature:
- ▸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) —
How It Works
The proposed biological pathway:
- ▸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
Who Might Benefit
Evidence fit by population:
- ▸134 participants (42 healthy adults, 39 with neurodegenerative diseases, 53 with immune-mediated inflammatory diseases) across four European centres
Recommended Dose
N/A
Limitations & Caveats
Important context when interpreting this evidence:
- ▸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.
References
- 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