Effectiveness of Conversational Agents for Depression and Anxiety: Systematic Review and Network Dose-Response Meta-Analysis of Agent Types, Dose, and Human Support
Journal of Medical Internet Research · 2026-11-13 · 28 · e104186
DOI: 10.2196/104186 ↗At a glance
Netzwerk-Metaanalyse in Journal of Medical Internet Research, published online on 2026-11-13. Written by Pengyu Yang and 8 co-authors. Institution: Faculty of Nursing, Universiti Malaya, Kuala Lumpur, Wilayah Persekutuan Kuala Lumpur, Malaysia. Major MEDLINE topics: Anxiety, Communication, Depression. 78 references.
Topics: Depression
Abstract (original language)
Background
Conversational agents (CAs) are increasingly used to deliver scalable interventions for depression and anxiety, but existing evidence has often treated these tools as a single category. The comparative effectiveness of different agent types, intervention doses, and levels of human support remains unclear.
Objective
This review systematically evaluated the comparative effectiveness of various CA modalities and levels of human support, as well as potential dose-response relationships across different CA types.
Methods
A comprehensive search of PubMed, Embase, Web of Science, Scopus, Ovid, CINAHL, and Psychology and Behavioral Sciences Collection (PBSC) databases was conducted from inception to December 2025. Eligible studies were randomized controlled trials (RCTs) evaluating CA-based interventions. We conducted a random-effects network meta-analysis (NMA) using postintervention outcomes and assessed inconsistency and risk of bias (RoB). Evidence certainty was assessed using the CINeMA (confidence in network meta-analysis) framework. Where data permitted, model-based network dose-response meta-analysis (MBNMA) was performed to examine dose-response associations.
Results
A total of 41 studies (n=7577) were included. NMA showed that AI-enhanced intensive human support (AEIHS) appeared to produce greater symptom improvement for depression and anxiety compared with pure human digital guidance (PHDG; Hedges g=–4.28, 95% CI –5.56 to –2.99) and open-ended multimodal-enhanced chatbot (OEMM; Hedges g=–4.49, 95% CI –6.31 to –2.66), whereas most other comparisons were not statistically significant. MBNMA indicated that goal-oriented conversational agent (GOCA) and highly structured modular chatbot (HSMC) appeared to exhibit nonlinear effects, with preliminary evidence suggesting potentially enhanced response at low-to-moderate doses, though these findings require further investigation. However, publication bias was detected for depression (Egger P=.02), and the overall certainty of evidence was very low, primarily due to RoB, indirectness, and imprecision.
Conclusions
While hybrid CA models with enhanced human involvement appeared to show potential advantages over fully automated systems, the evidence base remains limited. The very low certainty of evidence constrains confidence in comparative rankings and dose recommendations. Future high-quality trials are needed to establish optimal CA architectures and intervention doses for scalable mental health care. Trial Registration PROSPERO CRD420251145207; https://www.crd.york.ac.uk/PROSPERO/view/CRD420251145207
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Faculty of Nursing, Universiti Malaya, Kuala Lumpur, Wilayah Persekutuan Kuala Lumpur, Malaysia.
- Department of Intensive Care Unit, Peking University Shenzhen Hospital, Shenzhen, Guangdong, China.
- Department of Nursing, Leshan Vocational and Technieal College, Leshan, Sichuan, China.
- Faculty of Medicine, Macau University of Science and Technology, Macau, Macau, China.
- Department of Nursing, The Second Affiliated Hospital of Hainan Medical University, Haikou, Hainan, China.
- School of Nursing, Hainan Medical University, Haikou, Hainan, China.
ORCID profiles: Pengyu Yang, Ping Lei Chui, Mingxin He, Yao Wu, Pengfei Cheng, Minxiang Li, Haojie Sun, Lurong Cai, Hua Zhang
Cite
APA
Yang, P., Chui, P. L., He, M., Wu, Y., Cheng, P., Li, M., Sun, H., Cai, L., & Zhang, H. (2026). Effectiveness of Conversational Agents for Depression and Anxiety: Systematic Review and Network Dose-Response Meta-Analysis of Agent Types, Dose, and Human Support. Journal of Medical Internet Research, 28, e104186. https://doi.org/10.2196/104186
Vancouver
Yang P, Chui PL, He M, Wu Y, Cheng P, Li M, et al. Effectiveness of Conversational Agents for Depression and Anxiety: Systematic Review and Network Dose-Response Meta-Analysis of Agent Types, Dose, and Human Support. Journal of Medical Internet Research. 2026;28:e104186. doi:10.2196/104186
BibTeX
@article{Yang2026,
author = {Yang, Pengyu and Chui, Ping Lei and He, Mingxin and Wu, Yao and Cheng, Pengfei and Li, Minxiang and Sun, Haojie and Cai, Lurong and Zhang, Hua},
title = {Effectiveness of Conversational Agents for Depression and Anxiety: Systematic Review and Network Dose-Response Meta-Analysis of Agent Types, Dose, and Human Support},
journal = {Journal of Medical Internet Research},
year = {2026},
volume = {28},
pages = {e104186},
doi = {10.2196/104186}
}
EUVIMED