Can we use ChatGPT for Mental Health and Substance Use Education? Examining Its Quality and Potential Harms (Preprint)
Preprint
- 26 July 2023
- preprint
- Published by JMIR Publications Inc. in JMIR Preprints
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.Keywords
All Related Versions
- Published version: JMIR Medical Education, 9, e51243.
This publication has 8 references indexed in Scilit:
- The ChatGPT (Generative Artificial Intelligence) Revolution Has Made Artificial Intelligence Approachable for Medical ProfessionalsJournal of Medical Internet Research, 2023
- The Advent of Generative Language Models in Medical EducationJMIR Medical Education, 2023
- Multiple Automated Health Literacy Assessments of Written Health Information: Development of the SHeLL (Sydney Health Literacy Lab) Health Literacy Editor v1JMIR Formative Research, 2023
- Classification of Trademark Distinctiveness using OpenAI GPT 3.5 modelSSRN Electronic Journal, 2023
- Evaluation of Positive Choices, a National Initiative to Disseminate Evidence-Based Alcohol and Other Drug Prevention Strategies: Web-Based Survey StudyJMIR Pediatrics and Parenting, 2022
- Evaluation of a Digital Health Initiative in Illicit Substance Use: Cross-sectional Survey StudyJournal of Medical Internet Research, 2021
- Health Literacy and Shared Decision-making: Exploring the Relationship to Enable Meaningful Patient Engagement in HealthcareJournal of General Internal Medicine, 2020
- Worldwide inequality in access to full text scientific articles: the example of ophthalmologyPeerJ, 2019