EUVIMEDOtkrijte EUVIMED
VergleichsstudieOpen access

Comparative Efficacy of MultiModal AI Methods in Screening for Major Depressive Disorder: Machine Learning Model Development Predictive Pilot Study

Donghao Chen iD, Pengfei Wang iD, Xiaolong Zhang iD, Runqi Qiao iD, Nanxi Li iD, Xiaodong Zhang iD, Honggang Zhang iD, Gang Wang iD

JMIR Formative Research · 2025-05-30 · 9 · e56057-e56057

DOI: 10.2196/56057 ↗

At a glance

Vergleichsstudie in JMIR Formative Research, published online on 2025-05-30. Written by Donghao Chen and 7 co-authors. Institution: School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China. Major MEDLINE topics: Major Depressive Disorder, Machine Learning, Mass Screening, Artificial Intelligence. Cited 11 times so far (Crossref); 49 references. The full text is freely available in PubMed Central.

SažetakSubjectsBibliografski podaciCiteRelated studies

Abstract (original language)

Background

Conventional approaches for major depressive disorder (MDD) screening rely on two effective but subjective paradigms: self-rated scales and clinical interviews. Artificial intelligence (AI) can potentially contribute to psychiatry, especially through the use of objective data such as objective audiovisual signals.

Objective

This study aimed to evaluate the efficacy of different paradigms using AI analysis on audiovisual signals.

Methods

We recruited 89 participants (mean age, 37.1 years; male: 30/89, 33.7%; female: 59/89, 66.3%), including 41 patients with MDD and 48 asymptomatic participants. We developed AI models using facial movement, acoustic, and text features extracted from videos obtained via a tool, incorporating four paradigms: conventional scale (CS), question and answering (Q&A), mental imagery description (MID), and video watching (VW). Ablation experiments and 5-fold cross-validation were performed using two AI methods to ascertain the efficacy of paradigm combinations. Attention scores from the deep learning model were calculated and compared with correlation results to assess comprehensibility.

Results

In video clip-based analyses, Q&A outperformed MID with a mean binary sensitivity of 79.06% (95%CI 77.06%‐83.35%; P =.03) and an effect size of 1.0. Among individuals, the combination of Q&A and MID outperformed MID alone with a mean extent accuracy of 80.00% (95%CI 65.88%‐88.24%; P = .01), with an effect size 0.61. The mean binary accuracy exceeded 76.25% for video clip predictions and 74.12% for individual-level predictions across the two AI methods, with top individual binary accuracy of 94.12%. The features exhibiting high attention scores demonstrated a significant overlap with those that were statistically correlated, including 18 features (all Ps

Subjects

MeSH terms (MEDLINE)

Major Depressive DisorderMachine LearningMass ScreeningArtificial IntelligenceHumansFemaleMaleAdultPilot ProjectsMiddle Aged

Author keywords

MDDartificial intelligencecomputational psychiatryfacial action unitmajor depressive disordermultimodal analysismultiparadigm analysis

Authors and institutions

  • School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China.
  • Beijing Key Laboratory of Mental Disorders, National Clinical Research Center for Mental Disorders & National Center for Mental Disorders, Beijing Anding Hospital, Capital Medical University, Beijing, China.
  • Advanced Innovation Center for Human Brain Protection, Capital Medical University, Beijing, China.

ORCID profiles: Donghao Chen, Pengfei Wang, Xiaolong Zhang, Runqi Qiao, Nanxi Li, Xiaodong Zhang, Honggang Zhang, Gang Wang

Cite

APA

Chen, D., Wang, P., Zhang, X., Qiao, R., Li, N., Zhang, X., Zhang, H., & Wang, G. (2025). Comparative Efficacy of MultiModal AI Methods in Screening for Major Depressive Disorder: Machine Learning Model Development Predictive Pilot Study. JMIR Formative Research, 9, e56057-e56057. https://doi.org/10.2196/56057

Vancouver

Chen D, Wang P, Zhang X, Qiao R, Li N, Zhang X, et al. Comparative Efficacy of MultiModal AI Methods in Screening for Major Depressive Disorder: Machine Learning Model Development Predictive Pilot Study. JMIR Formative Research. 2025;9:e56057-e56057. doi:10.2196/56057

BibTeX
@article{Chen2025,
  author = {Chen, Donghao and Wang, Pengfei and Zhang, Xiaolong and Qiao, Runqi and Li, Nanxi and Zhang, Xiaodong and Zhang, Honggang and Wang, Gang},
  title = {Comparative Efficacy of MultiModal AI Methods in Screening for Major Depressive Disorder: Machine Learning Model Development Predictive Pilot Study},
  journal = {JMIR Formative Research},
  year = {2025},
  volume = {9},
  pages = {e56057--e56057},
  doi = {10.2196/56057}
}
Start for free →