Key result
A feature selection machine learning model incorporating age, cortisol, and very low frequency heart rate variability achieved an AUC of 0.760 for predicting fatigue severity, maintaining predictive power with a reduced number of variables.
Why the study?
Although non-invasive wearable cortisol measurement has advanced, it remains unclear how effectively cortisol combined with other physiological biomarkers predicts fatigue.
Does a machine learning model integrating cortisol and HRV improve fatigue prediction compared to HRV alone in patients undergoing routine health examinations?
Cohort (n=336)
No
Does a machine learning model integrating cortisol and HRV improve fatigue prediction compared to HRV alone in patients undergoing routine health examinations?
A machine learning model integrating age, cortisol, and very low frequency heart rate variability can accurately predict fatigue severity, demonstrating potential for lightweight implementation in wearable health monitoring devices.
Answers are grounded in this paper and cite their sources.
May aid wearable-based fatigue prediction; leaves open prospective validation before clinical adoption.
Objective: Fatigue is a critical indicator in modern health management, and efficient, accurate methods for predicting fatigue levels using wearable devices have garnered increasing attention. Although recent advancements have enabled non-invasive cortisol measurement via wearable sensors, it remains unclear how effectively cortisol, in combination with other physiological biomarkers, predicts fatigue. Therefore, this study aimed to evaluate the effectiveness of a multimodal machine learning model that integrates cortisol levels and heart rate variability (HRV) for fatigue prediction. Methods: Data from 336 participants who completed the Fatigue Severity Scale (FSS) were analyzed. Missing data mechanisms for cortisol were examined, and multivariate imputation by chained equations (MICEs) were applied. A TabNet deep-learning model was used to predict low and high fatigue levels based on HRV and cortisol data. Results: The model using only HRV variables achieved a test AUC of 0.774, whereas the model incorporating both HRV and cortisol levels achieved 0.741, indicating a minimal overall performance difference. Feature importance analysis revealed that, in the cortisol-included model, predictions relied on a limited set of features. When feature selection was applied to this model, a reduced set of variables-age, cortisol, and logarithmic very low frequency-achieved comparable predictive performance (AUC = 0.759) without performance degradation. Conclusion: This study demonstrated that a fatigue prediction model based on cortisol and HRV can maintain significant predictive power with a reduced number of variables. These findings suggest the potential for practical implementation in wearable devices, enabling accurate fatigue monitoring while minimizing sensor count and computational burden.
No takes yet. Share an insight, caveat, or question.
Kim et al. (2025) conducted a cohort in Fatigue (n=336). Multimodal machine learning model integrating cortisol and HRV vs. Machine learning model using only HRV variables was evaluated on Test Area Under the Curve (AUC) for predicting high fatigue (FSS ≥ 4.0). A feature selection machine learning model incorporating age, cortisol, and very low frequency heart rate variability achieved an AUC of 0.760 for predicting fatigue severity, maintaining predictive power with a reduced number of variables.
Synapse has enriched 10 related papers. Consider them for comparative context: