Entropy-Dominated Temporal Vocal Dynamics as Digital Biomarkers for Depression Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Samanta, Himadri S
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915967983943680
author Samanta, Himadri S
author_facet Samanta, Himadri S
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_26998
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Entropy-Dominated Temporal Vocal Dynamics as Digital Biomarkers for Depression Detection
Samanta, Himadri S
Other Quantitative Biology
Artificial Intelligence
Machine Learning
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.
title Entropy-Dominated Temporal Vocal Dynamics as Digital Biomarkers for Depression Detection
topic Other Quantitative Biology
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2604.26998