EUVIMEDOpdag EUVIMED
Systematische ÜbersichtOpen access

Evaluating Generative AI in Mental Health: Systematic Review of Capabilities and Limitations

Liying Wang iD, Tanmay Bhanushali iD, Zhuoran Huang iD, Jingyi Yang iD, Sukriti Badami iD, Lisa Hightow-Weidman iD

JMIR Mental Health · 2025-05-15 · 12 · e70014-e70014

DOI: 10.2196/70014 ↗

At a glance

Systematische Übersicht in JMIR Mental Health, published online on 2025-05-15. Written by Liying Wang and 5 co-authors. Institution: Institute on Digital Health and Innovation, College of Nursing, Florida State University, 222 S Copeland St, Tallahassee, FL, 32306, United States, 1…. Major MEDLINE topics: Artificial Intelligence, COVID-19, Mental Disorders, Mental Health. Cited 93 times so far (Crossref); 44 references. The full text is freely available in PubMed Central.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Background

The global shortage of mental health professionals, exacerbated by increasing mental health needs post COVID-19, has stimulated growing interest in leveraging large language models to address these challenges.

Objectives

This systematic review aims to evaluate the current capabilities of generative artificial intelligence (GenAI) models in the context of mental health applications.

Methods

A comprehensive search across 5 databases yielded 1046 references, of which 8 studies met the inclusion criteria. The included studies were original research with experimental designs (eg, Turing tests, sociocognitive tasks, trials, or qualitative methods); a focus on GenAI models; and explicit measurement of sociocognitive abilities (eg, empathy and emotional awareness), mental health outcomes, and user experience (eg, perceived trust and empathy).

Results

The studies, published between 2023 and 2024, primarily evaluated models such as ChatGPT-3.5 and 4.0, Bard, and Claude in tasks such as psychoeducation, diagnosis, emotional awareness, and clinical interventions. Most studies used zero-shot prompting and human evaluators to assess the AI responses, using standardized rating scales or qualitative analysis. However, these methods were often insufficient to fully capture the complexity of GenAI capabilities. The reliance on single-shot prompting techniques, limited comparisons, and task-based assessments isolated from a context may oversimplify GenAI’s abilities and overlook the nuances of human–artificial intelligence interaction, especially in clinical applications that require contextual reasoning and cultural sensitivity. The findings suggest that while GenAI models demonstrate strengths in psychoeducation and emotional awareness, their diagnostic accuracy, cultural competence, and ability to engage users emotionally remain limited. Users frequently reported concerns about trustworthiness, accuracy, and the lack of emotional engagement.

Conclusions

Future research could use more sophisticated evaluation methods, such as few-shot and chain-of-thought prompting to fully uncover GenAI’s potential. Longitudinal studies and broader comparisons with human benchmarks are needed to explore the effects of GenAI-integrated mental health care.

Subjects

MeSH terms (MEDLINE)

Artificial IntelligenceCOVID-19Mental DisordersMental HealthHumans

Author keywords

LLMclinical skillsdigital mental health interventionevaluationgenerative artificial intelligencelarge language modelmental health

Authors and institutions

  • Institute on Digital Health and Innovation, College of Nursing, Florida State University, 222 S Copeland St, Tallahassee, FL, 32306, United States, 1 (850) 644-3296.
  • Center of Population Sciences for Health Equity, College of Nursing, Florida State University, Tallahassee, FL, United States.
  • College of Arts and Sciences, University of Washington, Seattle, WA, United States.
  • Khoury College of Computer Sciences, Northeastern University, Boston, MA, United States.
  • Teachers College, Columbia University, New York, NY, United States.

ORCID profiles: Liying Wang, Tanmay Bhanushali, Zhuoran Huang, Jingyi Yang, Sukriti Badami, Lisa Hightow-Weidman

Cite

APA

Wang, L., Bhanushali, T., Huang, Z., Yang, J., Badami, S., & Hightow-Weidman, L. (2025). Evaluating Generative AI in Mental Health: Systematic Review of Capabilities and Limitations. JMIR Mental Health, 12, e70014-e70014. https://doi.org/10.2196/70014

Vancouver

Wang L, Bhanushali T, Huang Z, Yang J, Badami S, Hightow-Weidman L. Evaluating Generative AI in Mental Health: Systematic Review of Capabilities and Limitations. JMIR Mental Health. 2025;12:e70014-e70014. doi:10.2196/70014

BibTeX
@article{Wang2025,
  author = {Wang, Liying and Bhanushali, Tanmay and Huang, Zhuoran and Yang, Jingyi and Badami, Sukriti and Hightow-Weidman, Lisa},
  title = {Evaluating Generative AI in Mental Health: Systematic Review of Capabilities and Limitations},
  journal = {JMIR Mental Health},
  year = {2025},
  volume = {12},
  pages = {e70014--e70014},
  doi = {10.2196/70014}
}
Start for free →