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

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.

Updated systematic review of Australian school-based prevention programmes for alcohol and other drugs: a review protocol.

INTRODUCTION: Adolescent onset substance use is associated with neurodevelopmental, social and psychological harms. Thus, alcohol and other drug prevention programmes are essential to promote health and well-being during this period. Schools are uniquely positioned to deliver such prevention programmes. The last decade has seen a large expansion of school-based alcohol and drug prevention programmes in Australia, warranting an update of the comprehensive review conducted by Teesson et al in 2012. This proposed review aims to (1) identify school-based substance use prevention programmes that have been trialled in Australia since 2011, (2) evaluate their efficacy and (3) identify intervention components associated with effectiveness. This will assist schools in identifying and adopting effective evidence-based programmes and inform future programme development, evaluation and policy. METHODS AND ANALYSIS: Studies published from 2011 will be identified by searching the electronic databases PubMed, PsycINFO, Medline, Embase, ProQuest and Cochrane Library in addition to grey literature searches. Eligible studies will be controlled trials (including randomised controlled trials, cluster randomised controlled trials and quasi-experimental trials) of programmes measuring drug and alcohol related outcomes that are conducted in a school setting and have been trialled within Australia. Records will be independently screened for eligibility by two review authors, with disagreements being resolved by consensus or a third review author where necessary. Data extraction, risk of bias and study quality will also be completed independently by two review authors. A qualitative synthesis of all eligible studies will be presented. In addition, if there are sufficient data to combine studies, a random-effects meta-analysis will be conducted. ETHICS AND DISSEMINATION: This research is exempt from ethics approval as no primary data are collected, with work instead being carried out on published documents. The findings of this proposed review will be disseminated in a peer-reviewed journal and at conferences. PROSPERO REGISTRATION NUMBER: CRD42021272959.

School-based preventive interventions targeting e-cigarette use among adolescents: a systematic review protocol.

INTRODUCTION: Electronic cigarette (e-cigarette) use has drastically increased in recent years, particularly among adolescents. This poses several acute and chronic harms to young people, including poisonings, burns, serious lung injury and-where nicotine e-liquid is used-the potential to impact healthy brain development and precipitate future nicotine addiction. School-based prevention programmes have the potential to address this growing public health concern by reaching large numbers of young people during a critical period for intervention; however, the efficacy of such interventions has not been systematically explored. This systematic review aims to determine the existence and efficacy of school-based preventive interventions targeting e-cigarette use. METHODS AND ANALYSIS: A systematic search of MEDLINE, Embase, PsycINFO, Scopus, CINAHL, Cochrane Database of Systematic Reviews and international clinical trials registries will be conducted from 2000 to April 2022 to identify eligible studies (randomised controlled trials, cluster randomised controlled trials and quasiexperimental studies) evaluating school-based interventions to prevent e-cigarette use among adolescents. Two reviewers will independently screen title, abstract and full text of all studies for eligibility. Both reviewers will independently extract the data and assess the risk of bias. Any discrepancies will be resolved by a third reviewer. Results will be summarised in a narrative synthesis and data will be meta-analysed if appropriate. Heterogeneity in findings will be assessed narratively, and using the I2 statistic (where meta-analysis is feasible), meta-regression will be used to explore potential factors associated with programme efficacy, where data permit. ETHICS AND DISSEMINATION: This research is conducted on published work and does not require ethics approval. The findings will be published in a peer-reviewed journal and used to guide the development of new school-based e-cigarette preventive interventions. TRIAL REGISTRATION NUMBER: CRD42022323352.