Real-time evaluation of a multi-agency TB-screening event for persons experiencing homelessness in a town with a low incidence of TB in England.

Real-time evaluation (RTE) supports populations (e.g., persons experiencing homelessness (PEH) to engage in evaluation of health interventions who may otherwise be overlooked. The aim of this RTE was to explore the understanding of TB amongst PEH, identify barriers/facilitators to attending screening for PEH alongside suggestions for improving TB-screening events targeting PEH, who have high and complex health needs. This RTE composed of free-text structured one-to-one interviews performed immediately after screening at a single tuberculosis (TB) screening event. Handwritten forms were transcribed for thematic analysis, with codes ascribed to answers that were developed into core themes. All RTE participants (n=15) learned about the screening event on the day it was held. Key concerns amongst screening attendees included: stigma around drug use, not understanding the purpose of TB screening, lack of trusted individuals/services present, too many partner organizations involved, and language barriers. Facilitators to screening included a positive welcome to the event, a satisfactory explanation of screening tests, and sharing of results. A need for improved event promotion alongside communication of the purpose of TB screening amongst PEH was also identified. A lack of trust identified by some participants suggests the range of services present should be reconsidered for future screening events.

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.