Entropy-Dominated Temporal Vocal Dynamics as Digital Biomarkers for Depression Detection
For automated depression detection, this work demonstrates that temporal dynamics, specifically entropy, capture clinically meaningful information beyond static features, offering a novel digital phenotype.
The study investigated whether entropy-driven temporal vocal biomarkers improve depression detection over static pooled features, achieving a best AUC of 0.646 with entropy biomarkers, significantly outperforming the static baseline of 0.593.
Automated depression detection often relies on static aggregation of conversational signals, potentially obscuring clinically meaningful behavioral dynamics. We investigated whether entropy-driven temporal biomarkers improve depression detection beyond standard pooled features using the DAIC-WOZ corpus. Using 142 labeled participants, we reconstructed utterance-level acoustic trajectories and compared pooled temporal baselines, trajectory dynamics, Shannon entropy biomarkers, recurrence quantification, sample entropy, fractal complexity, and coupling biomarkers under leakage-aware validation. Static pooling achieved an AUC of 0.593, trajectory dynamics improved performance to 0.637, and entropy biomarkers produced the strongest statistically significant improvement over pooled baselines (AUC 0.646; nested cross-validated AUC 0.615; permutation p = 0.017). Entropy biomarkers outperformed recurrence, coupling, sample entropy, and fractalbased features, with several biomarkers stable across folds. These findings suggest depression-related signal may lie less in average acoustic levels than in entropy of conversational dynamics, supporting temporally informed digital phenotypes for mental-health assessment.