RESUMO
The objective of this study is to evaluate ChatGPT's accuracy and reliability in answering complex medical questions related to occupational health and explore the implications and limitations of AI in occupational health medicine. The study also provides recommendations for future research in this area and informs decision-makers about AI's impact on healthcare. A group of physicians was enlisted to create a dataset of questions and answers on Italian occupational medicine legislation. The physicians were divided into two teams, and each team member was assigned a different subject area. ChatGPT was used to generate answers for each question, with/without legislative context. The two teams then evaluated human and AI-generated answers blind, with each group reviewing the other group's work. Occupational physicians outperformed ChatGPT in generating accurate questions on a 5-point Likert score, while the answers provided by ChatGPT with access to legislative texts were comparable to those of professional doctors. Still, we found that users tend to prefer answers generated by humans, indicating that while ChatGPT is useful, users still value the opinions of occupational medicine professionals.
RESUMO
With the development of SARS-CoV-2 vaccines, many authors started evaluating the immunization efficacy of the available vaccines mainly through sero-positivity tests or by a quantitative assessment of the IgG against the spike protein of SARS-CoV-2 virus in vaccinated subjects. In this work, we compared the titers resulting from vaccination and tried to understand the potential factors affecting the immune response to the available SARS-CoV-2 vaccines. This study was conducted on 670 volunteers employed at the University of Pisa and undergoing a health surveillance program at the University Hospital of Pisa. For each participant, 10 mL of blood, information about contacts with confirmed cases of COVID-19, age, sex, SARS-CoV-2 vaccination status, previous SARS-CoV-2 infection and symptoms, type of vaccine and the date of administration were collected. In the multivariate analysis, the type of vaccine, the presence of symptoms in SARS-CoV-2 positive individuals, and the distance from the second dose significantly affected the antibody titer; the combined vaccination resulted in a faster decay over time compared with the other types of vaccination. No significant differences were observed between Spikevax and Comirnaty (p > 0.05), while the antibody levels remain more stable in subjects undergoing Vaxzevria vaccination (p < 0.01) compared with mRNA-based ones.