Key result
Wearable-derived heart rate variability achieved an ROC AUC of 0.56 (p=0.003) for classifying moderate depressive symptoms, indicating limited predictive performance in naturalistic settings.
Why the study?
Heart rate variability is a putative biological mechanism and marker of depression that can be measured in naturalistic settings, making machine learning on HRV data a promising approach to predict and monitor depressive symptoms.
Does machine learning applied to wearable-derived HRV data accurately predict moderate depressive symptoms in patients with anxiety and depression?
Cross-Sectional (n=2,629)
Does machine learning applied to wearable-derived HRV data accurately predict moderate depressive symptoms in patients with anxiety and depression?
Effect estimate: ROC AUC 0.56
p-value: p=0.003
Using wearable-derived HRV and machine learning to predict depressive symptoms in real-world settings yields poor predictive accuracy (ROC AUC 0.56).
Limited real-world performance cautions against clinical use for depression screening; leaves open whether refined metrics or longitudinal designs add value.
Heart Rate Variability (HRV) is a putative biological mechanism and marker of depression, which can be measured with low costs and in naturalistic settings. Therefore, applying machine learning (ML) on HRV data, could be a promising path to predict and monitor depressive symptoms in patient populations. A sample of 2629 participants completed self-administered HRV resting state recordings with a wearable device as part of a therapist-supported digital mental health intervention for anxiety and depression. Findings revealed that higher baseline Patient Health Questionaire-9 (PHQ-9) scores were associated with significantly higher heart rate (r = 0.14, p <0.001) and lower root mean error of successive differences (r = -0.09, p <0.001). We contrasted multiple machine learning algorithms with repeated 5-fold cross validation on a separate training set of 1830 to classify participants as having moderate depressive symptoms, indexed as a PHQ-9 score of 10 or greater. The best performing algorithm reached an area under the receiver operating characteristic score (ROC AUC) of 0.56 (p = 0.003) on the previously unseen test set, which was less than expected. Sensitivity analyses showed that model performance was not substantially impacted by variations in PHQ cut-offs or data quality. In conclusion, using wearable-derived HRV for cross-sectional prediction of depressive symptoms is challenging in settings with myriad real-world, day-to-day sources of variation.
No takes yet. Share an insight, caveat, or question.
Hornstein et al. (2022) conducted a cross-sectional in Anxiety and depression (n=2,629). Wearable-derived Heart Rate Variability (HRV) was evaluated on Classification of moderate depressive symptoms (PHQ-9 score ≥ 10) (ROC AUC 0.56, p=0.003). Wearable-derived heart rate variability achieved an ROC AUC of 0.56 (p=0.003) for classifying moderate depressive symptoms, indicating limited predictive performance in naturalistic settings.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: