Feasibility of predicting next-day fatigue levels using heart rate variability and activity-sleep metrics in people with post-COVID fatigue, 2025, Abo

[forestglip]

Feasibility of predicting next-day fatigue levels using heart rate variability and activity-sleep metrics in people with post-COVID fatigue

Spoiler: Authors

Aboagye, Nana Yaw; Germann, Maria; Baker, Kenneth F.; Baker, Mark R.; Del Din, Silvia

[Line breaks added]

Background
Post-COVID fatigue (pCF) represents a significant burden for many individuals following SARS-CoV-2 infection. The unpredictable nature of fatigue fluctuations impairs daily functioning and quality of life, creating challenges for effective symptom management.

Objective
This study investigated the feasibility of developing predictive models to forecast next-day fatigue levels in individuals with pCF, utilizing objective physiological and behavioral features derived from wearable device data.

Methods
We analyzed data from 68 participants with pCF who wore an Axivity AX6 device on their non-dominant wrist and a VitalPatch electrocardiogram (ECG) sensor on their chest for up to 21 days while completing fatigue questionnaires every other day.

HRV features were extracted from the VitalPatch single-lead ECG signal using the NeuroKit Python package, while activity and sleep features were derived from the Axivity wrist-worn device using the GGIR package.

Using a 5-fold cross-validation approach, we trained and evaluated the performances of two machine learning models to predict next-day fatigue levels using Visual Analogue Scale (VAS) fatigue scores: Random Forest and XGBoost.

Results
Using five-fold cross-validation, XGBoost outperformed Random Forest in predicting next-day fatigue levels (mean R² = 0.79 ± 0.04 vs. 0.69 ± 0.02; MAE = 3.18 ± 0.63 vs. 6.14 ± 0.96).

Predicted and observed fatigue scores were strongly correlated for both models (XGBoost: r = 0.89 ± 0.02; Random Forest: r = 0.86 ± 0.01). Key predictors included heart rate variability features-sample entropy, low-frequency power, and approximate entropy-along with demographic (age, sex) and activity-related (moderate and vigorous duration) factors.

These findings underscore the importance of integrating physiological, demographic, and activity data for accurate fatigue prediction.

Conclusions
This study demonstrates the feasibility of combining heart rate variability with activity and sleep features to predict next-day fatigue levels in individuals with pCF. Integrating physiological and behavioral data show promising predictive accuracy and provides insights that could inform future personalized fatigue management strategies.

Web | DOI | PMC | PDF | Frontiers in Digital Health | Open Access

 

[Utsikt]

Overall, a comprehensive set of daily features was derived from the recordings and grouped into four primary domains:

1. Activity features (e.g., mean acceleration, intensity-specific time, activity bouts, and fragmentation indices),

2. Sleep features (e.g., total sleep duration, sleep efficiency, timing, and movement-based parameters),

3. Circadian rhythm features (e.g., M5, L5, and relative amplitude),

4. HRV features, reflecting autonomic nervous system function based on ECG-derived RR intervals.

In total, 279 daily features were extracted per participant per day: 192 from HRV and 82 from activity, sleep, and circadian rhythm domains, plus 5 demographic and treatment condition variables, age, sex, and intervention condition dummy variables).

That’s a lot of data:

Predicted and observed fatigue scores were strongly correlated for both models (XGBoost: r = 0.89 ± 0.02; Random Forest: r = 0.86 ± 0.01). Key predictors included heart rate variability features-sample entropy, low-frequency power, and approximate entropy-along with demographic (age, sex) and activity-related (moderate and vigorous duration) factors.

It does not sound feasible to get the HRV data from normal monitors, so it might be difficult to implement it in real life.

Conclusions
This study demonstrates the feasibility of combining heart rate variability with activity and sleep features to predict next-day fatigue levels in individuals with pCF. Integrating physiological and behavioral data show promising predictive accuracy and provides insights that could inform future personalized fatigue management strategies.

How?