Key result
ECG-derived HRV with Random Forest under leave-one-subject-out validation achieved 86.7% accuracy and an ROC AUC of 0.946 (95% CI 0.871-0.998) for binary stress classification.
Why the study?
ECG is the gold standard for assessing HRV in alcohol use disorder, but its scalability in outpatient rehabilitation is limited. Consumer-grade PPG wearables offer a practical alternative, yet systematic calibration of PPG-derived HRV against ECG standards has been lacking.
Does ECG-derived heart rate variability evaluated with leave-one-subject-out cross-validation accurately classify binary stress states in subjects undergoing controlled stress induction, and how well do consumer-grade wearables agree with research-grade devices in ambulatory heart rate monitoring?
Observational (n=15)
No
Does ECG-derived heart rate variability evaluated with leave-one-subject-out cross-validation accurately classify binary stress states in subjects undergoing controlled stress induction, and how well do consumer-grade wearables agree with research-grade devices in ambulatory heart rate monitoring?
ECG-derived HRV features analyzed with leave-one-subject-out cross-validation achieve robust subject-independent stress-state classification (ROC AUC 0.946), providing a proof-of-concept foundation for autonomic relapse monitoring in alcohol use disorder, though consumer-grade wrist wearables showed wide heart rate limits of agreement (-43 to +49 bpm) during ambulatory use.
Answers are grounded in this paper and cite their sources.
ECG HRV ML models show promise for stress classification; leaves open whether calibrated PPG wearables can match performance in AUD monitoring.
Heart rate variability (HRV) is a validated non-invasive marker of autonomic dysregulation associated with stress reactivity and relapse risk in alcohol use disorder (AUD). While electrocardiography (ECG) remains the gold standard for HRV assessment, its scalability in outpatient rehabilitation is limited. Consumer-grade wearables using photoplethysmography (PPG) offer a practical alternative, but systematic calibration of PPG-derived HRV against ECG standards has been lacking. We evaluated the feasibility of using calibrated PPG-derived HRV for stress-state classification as a proxy for relapse-relevant autonomic signatures. Using the WESAD public dataset (15 subjects, ECG + PPG), we extracted time-domain (RMSSD, SDNN, pNN50), frequency-domain (LF, HF, LF/HF), and nonlinear (sample entropy, DFA) HRV features. Classical machine learning models achieved 80% accuracy with ROC AUC of 0.85 for binary stress classification using ECG-derived features. Linear calibration mapping PPG features to ECG space improved PPG-based ROC AUC from 0.79 to 0.85, matching ECG performance. Deep sequence models (LSTM, CNN) did not improve over feature-based approaches in this dataset, likely due to limited sample size. We additionally collected seven-day concurrent PPG recordings from Empatica EmbracePlus (FDA-cleared) and Fitbit (consumer-grade) wearables worn by a study participant to characterize cross-device agreement in ambulatory settings. These results establish that calibrated PPG-derived HRV from consumer wearables can approximate ECG-level discriminative performance for stress-state classification, supporting the feasibility of scalable HRV-based relapse monitoring in AUD rehabilitation.
No takes yet. Share an insight, caveat, or question.
Chhaya et al. (2026) conducted an observational in Stress reactivity / Alcohol Use Disorder relapse monitoring (proxy) (n=15). ECG-derived heart rate variability (HRV) Random Forest classifier with leave-one-subject-out (LOSO) cross-validation vs. Conventional 70/30 stratified train-test split with subject leakage was evaluated on Binary stress-state classification accuracy and ROC AUC (AUC 0.946, 95% CI 0.871-0.998). ECG-derived HRV with Random Forest under leave-one-subject-out validation achieved 86.7% accuracy and an ROC AUC of 0.946 (95% CI 0.871-0.998) for binary stress classification.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: