EUVIMEDEUVIMED entdecken
Open Access

Evaluating the Efficacy of AI-Based Interactive Assessments Using Large Language Models for Depression Screening: Development and Usability Study

Zheng Jin iD, Jiaxing Hu iD, Dandan Bi iD, Kaibin Zhao iD, Huan Yu iD

JMIR Formative Research · 13.01.2026 · 10 · e78401

DOI: 10.2196/78401 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JMIR Formative Research, online erschienen am 13.01.2026. Verfasst von Zheng Jin und 4 weiteren Autor:innen. Beteiligte Einrichtung: International Joint Laboratory of Behavior and Cognitive Science, Zhengzhou Normal University, Zhengzhou, Henan, China. Hauptthemen laut MEDLINE: Depression, Mass Screening, Psychometrics, Artificial Intelligence. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

The evolution of language models, particularly large language models, has introduced transformative potential for psychological assessment, challenging traditional rating scale methods that have dominated clinical practice for over a century.

Objective

This study aimed to develop and validate an automated assessment paradigm that integrates natural language processing with conventional measurement tools to assess depressive symptoms, exploring its feasibility as a novel approach in psychological evaluation.

Methods

A cohort of 115 participants, including 28 (24.3%) individuals diagnosed with depression, completed the Beck Depression Inventory Fast Screen via a custom ChatGPT interface (BDI-FS-GPT) and the Chinese version of the Patient Health Questionnaire–9 (PHQ-9). Statistical analyses included the Spearman correlation (PHQ-9 vs BDI-FS-GPT scores), Cohen κ (diagnostic agreement), and area under the curve (AUC) evaluation.

Results

Spearman analysis revealed a moderate correlation between PHQ-9 and BDI-FS-GPT scores. The Cohen κ indicated moderate diagnostic agreement between the PHQ-9 and the BDI-FS-GPT (κ=0.43; 76.5% agreement), substantial agreement between the BDI-FS-GPT and the clinical diagnosis (κ=0.72; 88.7% agreement), and moderate agreement between the PHQ-9 and the clinical diagnosis (κ=0.55; 71.4% agreement). The BDI-FS-GPT demonstrated excellent diagnostic accuracy (AUC=0.953) at a cutoff of 3, detecting 89.3% of participants with depression with an 11.5% false-positive rate compared to the PHQ-9 (AUC=0.859) at a cutoff of 5 (sensitivity=71.4%; false-positive rate=13.8%). Participants also reported significantly higher satisfaction with the automated assessment compared to the traditional scale (P=.02).

Conclusions

The automated assessment paradigm framework combines the interactivity and personalization of natural language processing–powered tools with the psychometric rigor of traditional scales, suggesting a preliminary feasibility paradigm for future psychological assessment. Its ability to enhance engagement while maintaining reliability and validity provides encouraging evidence, warranting validation in larger and more diverse studies as large language model technology advances. International Registered Report Identifier (IRRID) RR2-10.1101/2024.07.19.24310543

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

DepressionMass ScreeningPsychometricsArtificial IntelligenceHumansLarge Language ModelsFemaleAdultMaleMiddle AgedReproducibility of ResultsNatural Language ProcessingSurveys and QuestionnairesCohort StudiesIntelligent Systems

Stichwörter der Autor:innen

AAPAIBDI-FSBeck Depression Inventory Fast ScreenChatGPTNLPartificial intelligenceautomated assessment paradigmlarge language modelsmental health assessmentnatural language processingpsychology

Autor:innen und Institutionen

  • International Joint Laboratory of Behavior and Cognitive Science, Zhengzhou Normal University, Zhengzhou, Henan, China.
  • School of Electrical, Computer and Telecommunications Engineering, University of Wollongong, Wollongong, Australia.
  • Department of Psychology, Zhejiang Normal University, Jinhua, Zhejiang, China.

ORCID-Profile: Zheng Jin, Jiaxing Hu, Dandan Bi, Kaibin Zhao, Huan Yu

Zitieren

APA

Jin, Z., Hu, J., Bi, D., Zhao, K., & Yu, H. (2026). Evaluating the Efficacy of AI-Based Interactive Assessments Using Large Language Models for Depression Screening: Development and Usability Study. JMIR Formative Research, 10, e78401. https://doi.org/10.2196/78401

Vancouver

Jin Z, Hu J, Bi D, Zhao K, Yu H. Evaluating the Efficacy of AI-Based Interactive Assessments Using Large Language Models for Depression Screening: Development and Usability Study. JMIR Formative Research. 2026;10:e78401. doi:10.2196/78401

BibTeX
@article{Jin2026,
  author = {Jin, Zheng and Hu, Jiaxing and Bi, Dandan and Zhao, Kaibin and Yu, Huan},
  title = {Evaluating the Efficacy of AI-Based Interactive Assessments Using Large Language Models for Depression Screening: Development and Usability Study},
  journal = {JMIR Formative Research},
  year = {2026},
  volume = {10},
  pages = {e78401},
  doi = {10.2196/78401}
}
Kostenlos starten →