No retraction, correction or concern found when last checked on Oct 24, 2026.

Large Language Models for Mental Health Applications: Systematic Review

Zhijun Guo, Alvina Lai, Johan H Thygesen and 3 more

JMIR Mental Health · 2024 · Systematic review

Abstract

Background. Large language models (LLMs) are advanced artificial neural networks trained on extensive datasets to accurately understand and generate natural language. While they have received much attention and demonstrated potential in digital health, their application in mental health, particularly in clinical settings, has generated considerable debate.

Objective. This systematic review aims to critically assess the use of LLMs in mental health, specifically focusing on their applicability and efficacy in early screening, digital interventions, and clinical settings. By systematically collating and assessing the evidence from current studies, our work analyzes models, methodologies, data sources, and outcomes, thereby highlighting the potential of LLMs in mental health, the challenges they present, and the prospects for their clinical use.

Methods. Adhering to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, this review searched 5 open-access databases: MEDLINE (accessed by PubMed), IEEE Xplore, Scopus, JMIR, and ACM Digital Library. Keywords used were (mental health OR mental illness OR mental disorder OR psychiatry) AND (large language models). This study included articles published between January 1, 2017, and April 30, 2024, and excluded articles published in languages other than English.

Results. In total, 40 articles were evaluated, including 15 (38%) articles on mental health conditions and suicidal ideation detection through text analysis, 7 (18%) on the use of LLMs as mental health conversational agents, and 18 (45%) on other applications and evaluations of LLMs in mental health. LLMs show good effectiveness in detecting mental health issues and providing accessible, destigmatized eHealth services. However, assessments also indicate that the current risks associated with clinical use might surpass their benefits. These risks include inconsistencies in generated text; the production of hallucinations; and the absence of a comprehensive, benchmarked ethical framework.

Conclusions. This systematic review examines the clinical applications of LLMs in mental health, highlighting their potential and inherent risks. The study identifies several issues: the lack of multilingual datasets annotated by experts, concerns regarding the accuracy and reliability of generated content, challenges in interpretability due to the “black box” nature of LLMs, and ongoing ethical dilemmas. These ethical concerns include the absence of a clear, benchmarked ethical framework; data privacy issues; and the potential for overreliance on LLMs by both physicians and patients, which could compromise traditional medical practices. As a result, LLMs should not be considered substitutes for professional mental health services. However, the rapid development of LLMs underscores their potential as valuable clinical aids, emphasizing the need for continued research and development in this area.

Trial Registration. PROSPERO CRD42024508617; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=508617

Full text

Its licence does not allow us to show the full text. Read it at PubMed Central:

References 149

1.
Mental health. World Health Organization. 2022.
Not in our library
2.
Mental disorders. World Health Organization. 2022.
Not in our library
3.
MHPSS worldwide: facts and figures. Government of the Netherlands.
Not in our library
4.
Quantifying the global burden of mental disorders and their economic value · 2022
No notice
5.
Zhang W, Yang C, Cao Z, Li Z, Zhuo L, Tan Y, He Y, Yao L, Zhou Q, Gong Q, Sweeney JA, Shi F, Lui S. Detecting individuals with severe mental illness using artificial intelligence applied to magnetic resonance imaging. EBioMedicine. 2023;90:104541.
Not in our library10.1016/j.ebiom.2023.104541
6.
Mental health and COVID-19: early evidence of the pandemic’s impact: scientific brief, 2 March 2022. World Health Organization. 2022.
Not in our library
7.
Duden GS, Gersdorf S, Stengler K. Global impact of the COVID-19 pandemic on mental health services: a systematic review. J Psychiatr Res. 2022;154:354-77.
Not in our library10.1016/j.jpsychires.2022.08.013
8.
Mental health treatments. Mental Health America.
Not in our library
9.
Stigma, prejudice and discrimination against people with mental illness. American Psychiatric Association.
Not in our library
10.
Nietzel MT. Almost half of Americans don’t seek professional help for mental disorders. Forbes. 2021.
Not in our library
11.
Why do people avoid mental health treatment? Thriveworks. 2022.
Not in our library
12.
Digital Mental Health and COVID-19: Using Technology Today to Accelerate the Curve on Access and Quality Tomorrow · 2020
No notice
13.
Kumar V, Srivastava P, Dwivedi A, Budhiraja I, Ghosh D, Goyal V, Arora R, Santosh KC, Makkar A, Conway M, Singh AK, Vacavant A, Abou el Kalam A, Bouguelia MR, Hegadi R. Large-language-models (LLM)-based AI chatbots: architecture, in-depth analysis and their performance evaluation. Recent Trends in Image Processing and Pattern Recognition. 2024.
Not in our library
14.
Ma Z, Mei Y, Su Z. Understanding the benefits and challenges of using large language model-based conversational agents for mental well-being support. AMIA Annu Symp Proc. 2023;2023:1105-14.
Not in our library
15.
Yang K, Ji S, Zhang T, Xie Q, Kuang Z, Ananiadou S. Towards interpretable mental health analysis with large language models. arXiv. Preprint posted online on April 6, 2023.
Not in our library10.18653/v1/2023.emnlp-main.370
16.
Patients turning to A and E as wait times for NHS mental health treatment spiral. The Guardian. 2022.
Not in our library
17.
Elyoseph Z, Gur T, Haber Y, Simon T, Angert T, Navon Y, Tal A, Asman O. An ethical perspective on the democratization of mental health with generative artificial intelligence. JMIR Preprints. Preprint posted online on March 2, 2024.
Not in our library10.2196/preprints.58011
18.
Delivering Cognitive Behavior Therapy to Young Adults With Symptoms of Depression and Anxiety Using a Fully Automated Conversational Agent (Woebot): A Randomized Controlled Trial · 2017
No notice
19.
Wysa - everyday mental health. Wysa.
Not in our library
20.
An Overview of Chatbot-Based Mobile Mental Health Apps: Insights From App Description and User Reviews · 2023
No notice
21.
Large language models could change the future of behavioral healthcare: a proposal for responsible development and evaluation · 2024
No notice
22.
Harrer S. Attention is not all you need: the complicated case of ethically using large language models in healthcare and medicine. EBioMedicine. 2023;90:104512.
Not in our library10.1016/j.ebiom.2023.104512
23.
Ethics and governance of artificial intelligence for health: guidance on large multi-modal models. World Health Organization. 2024.
Not in our library
24.
What are large language models (LLMs)? IBM.
Not in our library
25.
LLM evaluation: key metrics and best practices. AISERA.
Not in our library
26.
Better language models and their implications. OpenAI. 2019.
Not in our library
27.
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I. Attention is all you need. arXiv. Preprint posted online on June 12, 2017.
Not in our library
28.
Kerner SM. What are large language models (LLMs)? TechTarget.
Not in our library
29.
Devlin J, Chang MW, Lee K, Toutanova K. BERT: pre-training of deep bidirectional transformers for language understanding. arXiv. Preprint posted online on October 11, 2018.
Not in our library10.5260/chara.21.2.8
30.
Rogers A, Kovaleva O, Rumshisky A. A primer in BERTology: what we know about how BERT works. arXiv. Preprint posted online on February 27, 2020.
Not in our library10.1162/tacl_a_00349
31.
ChatGPT a year on: 3 ways the AI chatbot has completely changed the world in 12 months. Euronews. 2023.
Not in our library
32.
Thirunavukarasu AJ, Ting DS, Elangovan K, Gutierrez L, Tan TF, Ting DS. Large language models in medicine. Nat Med. 2023;29(8):1930-40.
Not in our library10.1038/s41591-023-02448-8
33.
Hickey G. The best Large Language Models (LLMs) of 2024. TechRadar. 2024.
Not in our library
34.
Dilmegani C. 10+ large language model examples – benchmark and use cases in '24. AIMultiple.
Not in our library
35.
Timeline of AI and language models. Life Architect.
Not in our library
36.
Priest M. Large language models explained. boost.ai. 2024.
Not in our library
37.
Vucetic D, Tayaranian M, Ziaeefard M, Clark JJ, Meyer BH, Gross WJ. Efficient fine-tuning of BERT models on the edge. Proceedings of the IEEE International Symposium on Circuits and Systems. 2022.
Not in our library10.1109/iscas48785.2022.9937567
38.
Kumar M. Understanding large language models and fine-tuning for business scenarios: a simple guide. Medium. 2023.
Not in our library
39.
Mishra S, Khashabi D, Baral C, Hajishirzi H. Cross-task generalization via natural language crowdsourcing instructions. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics. 2022.
Not in our library10.18653/v1/2022.acl-long.244
40.
Zhang S, Dong L, Li X, Zhang S, Sun X, Wang S, Li J, Hu R, Zhang T, Wu F, Wang G. Instruction tuning for large language models: a survey. arXiv. Preprint posted online on August 21, 2023.
Not in our library10.48550/arxiv.2308.10792

All 149 references

Reads

Read by people on this page

None yet.

Checked or read by AI through naulon

None yet.

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.

Are you an author?

Is this your paper?

Claim it to add your note and be paid when agents cite it. Free.