Key result
ECG-based GRU model detects elderly fatigue with ~98% accuracy, outperforming standard machine learning baselines.
Why the study?
Fatigue detection in elderly individuals is essential for preventing health complications, but existing ECG-based solutions lack lightweight, interpretable, and deployable designs for real-world elderly care.
Does a portable ECG-based system using a GRU machine learning model accurately detect fatigue in elderly individuals?
Does a portable ECG-based system using a GRU machine learning model accurately detect fatigue in elderly individuals?
Effect estimate: AUC 0.98
A portable, low-cost ECG-based system utilizing a GRU machine learning model can accurately detect fatigue in elderly individuals, offering a potential tool for fall-risk prevention.
Fatigue detection in elderly individuals is essential for preventing health complications, particularly fall-related incidents, in residential and home care settings. Electrocardiogram (ECG) signals offer a non-invasive means of capturing fatigue-related physiological changes, yet existing solutions often lack the lightweight, interpretable, and deployable design required for real-world elderly care. This study proposes a portable, low-cost ECG-based system for real-time fatigue detection, using an enhanced AD8232 module integrated with an ESP32 microcontroller, with the aim of supporting fall-risk prevention. A dataset of 6,304 ECG segments was collected from 100 elderly participants. SMOTE and Gaussian noise injection were applied to address class imbalance and improve robustness. GRU, LSTM, and RNN models were trained and validated using subject-wise splitting. The GRU model achieved the best performance, with 97.96% accuracy, an AUC of 0.98, and an F1-score of 0.98, outperforming LSTM, RNN, and classical baselines. These results demonstrate the feasibility of a low-cost, embedded ECG-based system for fatigue detection, offering interpretable and generalizable outcomes suitable for elderly care and fall-risk prevention applications. Further clinical validation is planned to confirm its real-world effectiveness.
No takes yet. Share an insight, caveat, or question.
Baccouch et al. (2026) studied Fatigue (n=100). GRU model-based portable ECG system vs. LSTM, RNN, and classical baselines was evaluated on Fatigue detection accuracy (AUC 0.98). An ECG-based GRU machine learning model detected fatigue in elderly individuals with 97.96% accuracy and an AUC of 0.98, outperforming LSTM, RNN, and classical baseline models.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: