Automatic quantification of hand gestures in current and remitted Major Depressive Disorder during oral expression
- PMID: 40513704
- PMCID: PMC12291071
- DOI: 10.1016/j.jad.2025.119684
Automatic quantification of hand gestures in current and remitted Major Depressive Disorder during oral expression
Abstract
Nonverbal behavior plays a crucial role in social interactions and may provide insights into Major Depressive Disorder (MDD). While previous research suggests that hand gesture deficits are linked to depression, it remains unclear whether these deficits are state-dependent or persist beyond active illness. This study utilized an automated, video-based tool to quantify spontaneous hand gestures in individuals with current (cMDD) and remitted (rMDD) MDD during oral expression. A total of 145 participants (97 rMDD and 49 cMDD) completed a recorded gesture-elicitation task, and hand movement trajectories were extracted using video-based body tracking. Results revealed that individuals with current MDD exhibited significantly fewer gestures per minute compared to remitted individuals (p = .016, d = 0.38). Furthermore, gesture frequency negatively correlated with depressive symptom severity (r = -0.17, p = .046) and observational measures of psychomotor retardation (r = -0.23, p = .012). These findings suggest that gesture deficits are more strongly tied to the active state of depression rather than serving as a marker of vulnerability or a scar from previous depressive episodes. Automated gesture analysis provides an objective and scalable method for assessing nonverbal behavior in MDD. Future research should explore its clinical utility as a biomarker for symptom severity and treatment response.
Keywords: Automatic detection; Hand gesture; MDD; Nonverbal behavior; Psychomotor retardation.
Copyright © 2025 Elsevier B.V. All rights reserved.
Conflict of interest statement
Declaration of competing interest The authors declare no competing interests.
References
-
- Alghowinem S, Goecke R, Wagner M, Parkerx G, & Breakspear M (2013). Head Pose and Movement Analysis as an Indicator of Depression. 2013 Humaine Association Conference on Affective Computing and Intelligent Interaction, 283–288. 10.1109/ACII.2013.53 - DOI
-
- Bazarevsky V, Grishchenko I, Raveendran K, Zhu T, Zhang F, & Grundmann M (2020). BlazePose: On-device Real-time Body Pose tracking (No. arXiv:2006.10204). arXiv. 10.48550/arXiv.2006.10204 - DOI
MeSH terms
Grants and funding
LinkOut - more resources
Full Text Sources
