Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Previously submitted to: JMIR AI (no longer under consideration since Apr 03, 2025)

Date Submitted: Feb 6, 2025

Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.

The effectiveness of CBT-based AI-driven conversational agents for mental health intervention: A systematic review and meta-analysis

  • Yaming Hang; 
  • Wenzhi Wu; 
  • Yi Feng; 
  • Kai Yan; 
  • Yinuo Liu; 
  • Xiyao Xiao; 
  • Zhihong Qiao

ABSTRACT

Background:

As an innovative and transformative intelligent intervention tool, Artificial Intelligence (AI) is swiftly gaining prominence in mental health interventions. Concurrently, Cognitive Behavioral Therapy (CBT), widely recognized for its structured and empirically-supported methodology, is increasingly being integrated as a foundational concept into AI-driven intervention frameworks. However, the specific efficacy of this integration still awaits in-depth verification.

Objective:

This study aims to examine the intervention effectiveness of CBT-based AI-driven Conversational Agents (CAs) in various mental health problems, and identify potential moderators for effectiveness.

Methods:

Studies were identified through a systematic search in five main databases: PubMed, Cochrane Library, Web of Science, PsycINFO, and Embase. The quality of these studies, possible publication bias and moderators were then examined. A total of 15 randomized controlled trials with 1,737 participants were included in the analysis.

Results:

The results indicated that AI-driven, CBT-based CAs showed a small to moderate effect on depressive symptoms (g = 0.36, 95% CI 0.20-0.51) and a small effect on negative affect (g = 0.21, 95% CI 0.02-0.39); while the effects on generalized anxiety, stress, and positive affect were not significant after adjusting for publication bias (g = -0.04 to g = 0.18). In addition, multi-modal CAs were more effective than single-modality CAs in reducing depressive symptoms (g = 0.82, 95% CI 0.54-1.09). Younger age was associated with a greater reduction in depressive symptoms (β = -0.02, P < 0.05).

Conclusions:

These findings underscored the potential of CBT-based AI-driven CAs in addressing certain mental health issues and in certain populations.


 Citation

Please cite as:

Hang Y, Wu W, Feng Y, Yan K, Liu Y, Xiao X, Qiao Z

The effectiveness of CBT-based AI-driven conversational agents for mental health intervention: A systematic review and meta-analysis

JMIR Preprints. 06/02/2025:72249

DOI: 10.2196/preprints.72249

URL: https://preprints.jmir.org/preprint/72249

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.