Background: There are evident sex differences in the incidence of and mortality rates for several tumors. Soft tissue sarcomas (STSs) account for no more than 1% of all malignancies in adults. This study aimed to provide a comprehensive overview of the sex differences in the epidemiology of STSs and the related costs. Methods: This retrospective population-based study draws on epidemiological data regarding cases of STS collected by the cancer registry of the Italian Veneto region for the years 1990–2018. A joinpoint regression analysis was performed to identify significant changes in the trends of the standardized incidence rates in males and females. Bivariate and survival analyses were conducted to assess differences in clinicopathological characteristics and short-term mortality by sex. Direct health care costs incurred over 2 years after a diagnosis of STS were calculated, stratified by sex. Results: The incidence rates of STS at any age were higher for males; only among males the incidence rates showed a tendency to slightly increase. No significant sex differences came to light in short-term mortality or clinicopathological profile, except for the cancer site. Health care costs in the 2 years after a diagnosis of STS were not sex related. Conclusion: The STS incidence was found to be higher for males and showed a rising trend over the last three decades only for males. These findings could result from the occupational exposure to environmental mutagens mainly involving men. Sex did not affect the survival or the clinicopathological STS profile.

Background: The introduction and evolution of antiretrovirals has changed the panorama of comorbidities in people living with HIV (PLWH) by reducing the risk of AIDS-defining cancers (ADC). By contrast, due to ageing and persistent inflammation, the prevalence and incidence of non-AIDS-defining cancers have significantly increased. Therefore, we aimed at describing cancer epidemiology in our cohort over 28 years. Methods: We retrospectively included all PLWH in our clinic who ever developed cancers, considering features of ADC and NADC, from January 1996 to March 2023. Demographic, clinical characteristics, and survival were analyzed, comparing three observation periods (1996–2003, 2004–2013, and 2014–2023). Results: A total of 289 PLWH developed 308 cancers over the study period; 77.9% were male, the mean age was 49.6 years (SD 12.2), and 57.4% PLWH developed NADC and 41.5% ADC. Kaposi (21.8%) and non-Hodgkin lymphoma (20.1%) were the most frequent cancers. Age at the time of cancer diagnosis significantly increased over time (41.6 years in the first period vs. 54.4 years in the third period, p < 0.001). In the first period compared with the last, a simultaneous diagnosis of HIV infection and cancer occurred in a higher proportion of persons (42.7 vs. 15.3, p < 0.001). While viro-immunological control at cancer diagnosis significantly improved over time, the proportions of cancer progression/remission remained stable. Overall survival significantly increased, but this trend was not confirmed for ADC. Conclusions: The probability of survival for ADC did not decrease as significantly as the number of ADC diagnoses over time. By contrast, NADC dramatically increased, in line with epidemiological studies and other literature data. The changing patterns of malignancies from ADC to NADC underline the need for public health interventions and the fostering of screening programs aimed at the prevention and early detection of NADC in PLWH.

Background: Cutaneous malignant melanoma (CMM) ranks among the ten most frequent malignancies, clinicopathological staging being of key importance to predict prognosis. Artificial intelligence (AI) has been recently applied to develop prognostically reliable staging systems for CMM. This study aims to provide a useful machine learning based tool to predict the overall CMM short-term survival.Methods: CMM records as collected at the Veneto Cancer Registry (RTV) and at the Veneto regional health service were considered. A univariate Cox regression validated the strength and direction of each independent variable with overall mortality. A range of machine learning models (Logistic Regression classifier, Support-Vector Machine, Random Forest, Gradient Boosting, and k-Nearest Neighbors) and a Deep Neural Network were then trained to predict the 3-years mortality probability. Five-fold cross-validation and Grid Search were performed to test the best data preprocessing procedures, features selection, and to optimize models hyperparameters. A final evaluation was carried out on a separate test set in terms of balanced accuracy, precision, recall and F1 score. The best model was deployed as online tool.Results: The univariate analysis confirmed the significant prognostic value of TNM staging. Adjunctive clinicopathological variables not included in the AJCC 8th melanoma staging system, i.e., sex, tumor site, histotype, growth phase, and age, were significantly linked to overall survival. Among the models, the Neural Network and the Random Forest models featured the best prognostic performance, achieving a balanced accuracy of 91% and 88%, respectively. According to the Gini importance score, age, T and M stages, mitotic count, and ulceration appeared to be the variables with the greatest impact on survival prediction.Conclusions: Using data from patients with CMM, we developed an AI algorithm with high staging reliability, on top of which a web tool was implemented (unipd.link/melanomaprediction). Being essentially based on routinely recorded clinicopathological variables, it can already be implemented with minimal effort and further tested in the current clinical practice, an essential phase for validating the model’s accuracy beyond the original research context.

Kaposi’s sarcoma (KS) is a rare angioproliferative tumor classified in four different clinical–epidemiological forms. The diagnosis is based on histopathological and immunohistochemical analyses. The treatment is heterogeneous and includes several local and systemic therapeutic strategies. Methods: This is a retrospective cohort study including 86 KS patients treated between 1993 and 2022 at the University Hospital of Padua (AOPD) and at the Veneto Institute of Oncology (IOV). The data were extracted from an electronic database. Survival curves were generated using the Kaplan–Meier method, and Cox regression models were employed to explore associations with overall and disease-free survival. The male sex (89.53%), classical variant (43.02%), and cutaneous involvement (77.9%) were predominant. More than 61.6% of patients received a single treatment. Surgery, antiretroviral therapy, and chemotherapy were the mostly adopted approaches. A persistent response was observed in approximately 65% of patients, with a 22% relapse rate (at least 2 years). The overall survival ranges from 90 to 70% at 2 to 10 years after the diagnosis. Iatrogenic KS demonstrated a higher mortality (52.9%). This study reflects our experience in the management of KS. Comorbidities are very frequent, and treatments are heterogeneous. A multidisciplinary approach involving multiple referral specialists is essential for the appropriate management of this disease during diagnosis, treatment, and follow-up.

Healthcare-associated infections (HAIs) are a global public health concern, imposing significant clinical and financial burdens. Despite advancements, surveillance methods remain largely manual and resource-intensive, often leading to underreporting. In this context, automation, particularly through Artificial Intelligence (AI), shows promise in optimizing clinical workflows. However, adoption challenges persist. This study aims to evaluate the current performance and impact of AI in HAI surveillance, considering technical, clinical, and implementation aspects. We conducted a systematic review of Scopus and Embase databases following PRISMA guidelines. AI-based models' performances, accuracy, AUC, sensitivity, and specificity, were pooled using a random-effect model, stratifying by detected HAI type. Our study protocol was registered in PROSPERO (CRD42024524497). Of 2834 identified citations, 249 studies were reviewed. The performances of AI models were generally high but with significant heterogeneity between HAI types. Overall pooled sensitivity, specificity, AUC, and accuracy were respectively 0.835, 0.899, 0.864, and 0.880. About 35.7 % of studies compared AI system performance with alternative automated or standard-of-care surveillance methods, with most achieving better or comparable results to clinical scores or manual surveillance. <7.6 % explicitly measured AI impact in terms of improved patient outcomes, workload reduction, and cost savings, with the majority finding benefits. Only 30 studies deployed the model in a user-friendly tool, and 9 tested it in real clinical practice. In this systematic review, AI shows promising performance in HAI surveillance, although its routine application in clinical practice remains uncommon. Despite over a decade, retrieved studies offer scant evidence on reducing burden, costs, and resource use. This prevents their potential superiority over traditional or simpler automated surveillance systems from being fully evaluated. Further research is necessary to assess impact, enhance interpretability, and ensure reproducibility.