ChatGPT sits the DFPH exam: large language model performance and potential to support public health learning.

BACKGROUND: Artificial intelligence-based large language models, like ChatGPT, have been rapidly assessed for both risks and potential in health-related assessment and learning. However, their applications in public health professional exams have not yet been studied. We evaluated the performance of ChatGPT in part of the Faculty of Public Health's Diplomat exam (DFPH). METHODS: ChatGPT was provided with a bank of 119 publicly available DFPH question parts from past papers. Its performance was assessed by two active DFPH examiners. The degree of insight and level of understanding apparently displayed by ChatGPT was also assessed. RESULTS: ChatGPT passed 3 of 4 papers, surpassing the current pass rate. It performed best on questions relating to research methods. Its answers had a high floor. Examiners identified ChatGPT answers with 73.6% accuracy and human answers with 28.6% accuracy. ChatGPT provided a mean of 3.6 unique insights per question and appeared to demonstrate a required level of learning on 71.4% of occasions. CONCLUSIONS: Large language models have rapidly increasing potential as a learning tool in public health education. However, their factual fallibility and the difficulty of distinguishing their responses from that of humans pose potential threats to teaching and learning.

Opportunistic Non-Governmental Organisation Delivery of a Virtual Stop Smoking Service in England during the COVID-19 Lockdown.

Smoking cessation services have rapidly transformed during the COVID-19 pandemic. Changes include pivoting from face-to-face to telephone and video call support, remote provision of stop smoking aids and more flexible appointments. This study reports an evaluation of a charity-led smoking cessation service rapidly conceived and launched in this context. The pilot service accepted self-referrals in Yorkshire, England from 20 May 2020 to 5 June 2020. A dedicated smoking cessation practitioner provided 12 weeks of weekly behavioural support over telephone or video call. NRT and/or medication and/or e-cigarettes were posted to the participant bi-weekly for up to 12 weeks. Written and telephone evaluation questionnaires were administered post-programme. Of 79 participants, 57 (72.2%) self-reported a 4-week quit and 51 (64.6%) self-reported a 12-week quit. Those concurrently using e-cigarettes and NRT had an 84.1% 12-week quit rate. The majority of participants chose to use e-cigarettes and NRT in combination (55.7%). 39 participants completed an evaluation form, with at least 90% recording they were "very satisfied" with each service component. 27 participants completed a telephone interview, reporting a relationship with practitioners, as well as convenience, and organisational reputation as service strengths. Virtual services can be set up quickly and effectively in response to demand. Quit rates were highest for those concurrently using e-cigarettes and NRT. Service users value flexibility and convenience of remote support and posting of quit aids.