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.

Malignant pleural mesothelioma (MPM) is a cancer mainly caused by asbestos fiber inhalation, characterized by an extremely long latency and poor prognosis. Recently, researchers have focused on testing the diagnostic ability of several biomarkers. Gamma-Glutamyltransferase (GGT) has been demonstrated to be the sum of several GGT sub-fractions activity, classified based on their molecular weight in big-GGT, medium-GGT, small-GGT, and free-GGT. This work aims to evaluate whether specific GGT fractional enzymatic activity patterns could be helpful in MPM diagnosis. We analyzed blood samples from 175 workers previously exposed to asbestos, 157 non-exposed healthy subjects, and 37 MPM patients through a molecular exclusion chromatographic method. We found a specific profile of GGT fractions activity, significantly associated with MPM, resulting in an increase in b-, m- activity, along with an evident, yet not significant, decrease in f-activity. Receiver-operating characteristic (ROC) analysis showed that the best Area Under Curve (AUC) value resulted from the combined index b/f (0.679, 95% CI: 0.582–0.777). Combining the b-/f-GGT activity with the levels of serum mesothelin-related protein (SMRP; another promising MPM biomarker) improved the diagnostic accuracy, increasing the AUC value to 0.875 (95% CI: 0.807–0.943, p = <0.0001). Since MPM has a specific pattern of GGT enzymatic activity, we could hypothesize that GGT fractions play different specific biochemical roles. The improvement in the diagnostic power given by the combination of these two biomarkers confirms that the strategy of biomarkers combination might be a better approach for MPM diagnosis.

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.

Malignant pleural mesothelioma is an aggressive malignancy with poor prognosis. Unilateral pleural effusion is frequently the initial clinical sign requiring therapeutic thoracentesis, which also offers a diagnostic opportunity. Detection of soluble biomarkers can support diagnosis, but few show good diagnostic accuracy. Here, we studied the expression levels and discriminative power of two putative biomarkers, prosaposin and extracellular sulfatase SULF-1, identified by proteomic and transcriptomic analysis, respectively. Pleural effusions from a total of 44 patients (23 with mesothelioma, 8 with lung cancer, and 13 with non-malignant disease) were analyzed for prosaposin and SULF-1 by enzyme-linked immunosorbent assay. Pleural effusions from mesothelioma patients had significantly higher levels of prosaposin and SULF-1 than those from non-malignant disease patients. Receiver-operating characteristic (ROC) analysis showed that both biomarkers have good discriminating power as pointed out by an AUC value of 0.853 (p = 0.0005) and 0.898 (p < 0.0001) for prosaposin and SULF-1, respectively. Combining data ensued a model predicting improvement of the diagnostic performance (AUC = 0.916, p < 0.0001). In contrast, prosaposin couldn’t discriminate mesothelioma patients from lung cancer patients while ROC analysis of SULF-1 data produced an AUC value of 0.821 (p = 0.0077) but with low sensitivity. In conclusion, prosaposin and SULF-1 levels determined in pleural effusion may be promising biomarkers for differential diagnosis between mesothelioma and non-malignant pleural disease. Instead, more patients need to be enrolled before granting the possible usefulness of these soluble proteins in differentiating mesothelioma pleural effusions from those linked to lung cancer.