CoChat
Sign Up
Cited by 78Artificial Intelligence in Healthcare and EducationArtificial Intelligence in EducationEthics and Social Impacts of AI

Can we use ChatGPT for Mental Health and Substance Use Education? Examining Its Quality and Potential Harms

Open access
Spallek, Sophia, Birrell, Louise, Kershaw, Stephanie, Devine, Emma Krogh, Thornton, Louise·2023·JMIR Medical Education
DOI 10.2196/51243PMC PMC10722374

Published version of a preprint

Open this paper in CoChat — free accountOpen PDF

Abstract

Background: The use of generative artificial intelligence, more specifically large language models (LLMs), is proliferating, and as such, it is vital to consider both the value and potential harms of its use in medical education. Their efficiency in a variety of writing styles makes LLMs, such as ChatGPT, attractive for tailoring educational materials. However, this technology can feature biases and misinformation, which can be particularly harmful in medical education settings, such as mental health and substance use education. This viewpoint investigates if ChatGPT is sufficient for 2 common health education functions in the field of mental health and substance use: (1) answering users’ direct queries and (2) aiding in the development of quality consumer educational health materials. Objective: This viewpoint includes a case study to provide insight into the accessibility, biases, and quality of ChatGPT’s query responses and educational health materials. We aim to provide guidance for the general public and health educators wishing to utilize LLMs. Methods: We collected real world queries from 2 large-scale mental health and substance use portals and engineered a variety of prompts to use on GPT-4 Pro with the Bing BETA internet browsing plug-in. The outputs were evaluated with tools from the Sydney Health Literacy Lab to determine the accessibility, the adherence to Mindframe communication guidelines to identify biases, and author assessments on quality, including tailoring to audiences, duty of care disclaimers, and evidence-based internet references. Results: GPT-4’s outputs had good face validity, but upon detailed analysis were substandard in comparison to expert-developed materials. Without engineered prompting, the reading level, adherence to communication guidelines, and use of evidence-based websites were poor. Therefore, all outputs still required cautious human editing and oversight. Conclusions: GPT-4 is currently not reliable enough for direct-consumer queries, but educators and researchers can use it for creating educational materials with caution. Materials created with LLMs should disclose the use of generative artificial intelligence and be evaluated on their efficacy with the target audience.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.2196/51243

Cites

14 of 15 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • LLM-CBs generally do not sufficiently adhere to professional guidelines or standards.

    “LLM-CBs generally do not sufficiently adhere to professional guidelines or standards65,71–73 and, according to health professionals’ analyses on chatbot responses, show special harmful potential in the context of crisis situations71.”

    From A scoping review on the mental health harms of LLM-based chatbots (2026) · cites this paper as [73]

    The Results (Evaluation Metrics; page not provided) report that GPT-4 responses to direct queries and simple prompts adhered less well to communication guidelines, and that 23% of assessed outputs contained stigmatizing language. The Discussion (Future Opportunities; page not provided) says initial outputs will not adhere to all guidelines. These findings support a concern about GPT-4 in mental health and substance use education, but not the broader claim that LLM-based chatbots generally fail to meet professional standards. (LLM, conf=0.87)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 2

  1. [1]Nori H King N McKinney S Carignan D Horvitz E Capabilities of GPT-4 on medical challenge problems arXiv Preprint posted online on April 12, 2023.
  2. [6]Bubeck S Chandrasekaran V Eldan R Gehrke J Horvitz E Kamar E Lee P Lee YT Li Y Lundberg S Nori H Palangi H Ribeiro MT Zhang Y Sparks of artificial general intelligence: early experiments with GPT-4 arXiv Preprint posted online on March 22, 2023.

Cited by

Sorted by citations

Related

Authors
Spallek, S., Birrell, L., Kershaw, S., Devine, E. K., & Thornton, L.
Affiliations
The University of Sydney (AU)
Corresponding author
Spallek, Sophia
ORCID
Venue
JMIR Medical Education
Publisher
JMIR Publications Inc.
Published
2023-11-30
Volume
9
Pages
e51243
ISSN
2369-3762 (ISSN-L)
DOI
10.2196/51243
PMC
PMC10722374
OpenAlex
W4388502894
Cited by
77
References
14
Citations by year
2026: 22 · 2025: 33 · 2024: 21 · 2023: 1
FWCI
3.08
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
  • JMIR Medical Education (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • PubMed Central (publishedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Physical Sciences › Computer Science › Information Systems › Artificial Intelligence in Education
  • Social Sciences › Safety Research › Ethics and Social Impacts of AI
Keywords
ChatGPT, large language models, mental health education, drug education, health education materials, GPT-4, health literacy, communication bias, misinformation, prompt engineering, AI-generated content quality, AI harms

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review