Artificial Intelligence (AI) is rapidly transforming medical education by enabling adaptive tutoring, interactive simulation, diagnostic enhancement, and competency-based assessment. This narrative review explores how AI has influenced learning processes in undergraduate and postgraduate medical training, focusing on methodological rigor, educational impact, and implementation challenges. The literature reveals promising results: large language models can generate didactic content and foster academic writing; AI-driven simulations enhance decision-making, procedural skills, and interprofessional communication; and deep learning systems improve diagnostic accuracy in visually intensive tasks such as radiology and histology. Despite promising findings, the existing literature is methodologically heterogeneous. A minority of studies use controlled designs, while the majority focus on short-term effects or are confined to small, simulated cohorts. Critical limitations include algorithmic opacity, generalizability concerns, ethical risks (e.g., GDPR compliance, data bias), and infrastructural barriers, especially in low-resource contexts. Additionally, the unregulated use of AI may undermine critical thinking, foster cognitive outsourcing, and compromise pedagogical depth if not properly supervised. In conclusion, AI holds substantial potential to enhance medical education, but its integration requires methodological robustness, human oversight, and ethical safeguards. Future research should prioritize multicenter validation, longitudinal evaluation, and AI literacy for learners and educators to ensure responsible and sustainable adoption.

Given the ongoing COVID-19 pandemic, there is a need to identify SARS-CoV-2 and to differentiate it from other respiratory viral infections, especially influenza A and B, in various critical settings. Since their introduction, the use of rapid antigen tests has spread worldwide, but there is variability in their diagnostic accuracy. In the present study, we evaluated the clinical performance of the ID NOW™ COVID-19 2.0, a molecular point-of-care test (POCT) based on enzymatic isothermal amplification for the differential diagnosis of SARS-CoV-2 and influenza A/B in a pediatric emergency setting. A cohort of pediatric patients admitted between December 2022 and February 2023 were simultaneously tested with the POCT and standard laboratory molecular assay. Our findings showed high negative agreement of the POCT assay across the different age groups for SARS-CoV-2, influenza A, and influenza B (more than 98.0%), while its positive agreement varied significantly for the abovementioned viral species from 50.0% to 100%. These results highlight the potential of the ID NOW™ COVID-19 2.0 POCT assay as a reliable and rapid tool for excluding SARS-CoV-2 and influenza A/B infections in symptomatic pediatric patients, although its variable positive agreement suggests a need for confirmatory RT-qPCR testing in certain clinical and epidemiological settings in order to ensure accurate diagnosis and appropriate patient management.

In this retrospective study, we analyzed the possible predictive changes in lymphocyte subsets of Coronavirus Disease 19 (COVID-19) hospitalized patients. We enrolled 107 COVID-19 patients older than 18 years of age, admitted to Alessandria Hospital with a confirmed diagnosis of SARS-CoV-2 infection by Reverse Transcriptase-Polymerase Chain Reaction (RT-PCR), who performed the analysis of lymphocyte subsets, between 2020 March 01 and 2021 May 31. Patients have been split up into two groups, based on clinical manifestations: group 1 non-severe disease (n=44) and group 2 severe disease (n=63), according to the World Health Organization (WHO) interim guidance. For the comparison between the two groups of patients, statistical significance was tested with the Mann-Whitney and the Chi-Square test. In the group of patients with severe disease, the blood cell analysis showed a significant reduction in the counts of total lymphocytes, absolute CD3 lymphocytes, and CD8 lymphocytes, as well as a significant reduction in monocyte percent and a very significant increase in neutrophil counts. From the results obtained, it can be stated that lymphocytopenia is associated with the progression of the disease and increased mortality.

Background and Aims: Osteonecrosis of the Jaw (ONJ), recently renamed Medication-Related Osteonecrosis of the Jaw (MRONJ), is a recently recognized disease (2003), characterized by alterations including clinical signs and symptoms (not limited to bone exposure) together with jawbone radiological destruction, better assessed by Computed Tomography (CT) scan. We designed an observational (retrospective and prospective) study to systematically investigate the rate of occurrence of the various radiological signs of CT semeiotics, predefined in an appropriate table (i.e., focal and diffuse osteosclerosis, sequestrum, cortical disruption, periosteal reaction, osteolysis, etc.) in patients with MRONJ, diagnosed according to the criteria of the Italian SICMF-SIPMO recommendations (2020). Results: since March 2022, 120 patients with MRONJ were examined; 5 were considered not eligible due to lack of adequate CT images. Clinical data and radiological features of 115 patients were recorded and are under examination. Conclusions: the sample was higher than expected, and it appears sufficient to proceed to the evaluation of radiological features and draw conclusions about the investigated issue.

Background and Objectives: Pediatric cardiovascular risk factors tend to track into adulthood, accelerating the atherosclerotic process. This study aimed to assess the prevalence of cardiometabolic risk factors, integrating anthropometric parameters, central adiposity indices, early growth trajectories, family history, and household lifestyle, in a primary-care pediatric cohort (the RISCAPED study). Materials and Methods: A cross-sectional multicenter study was conducted across primary care pediatric practices in the province of Alessandria, Northwest Italy, enrolling children aged 6 to 12 years. Weight status was classified according to World Health Organization 2007 criteria, abdominal adiposity by Waist-to-Height Ratio (WHtR > 0.5), and high blood pressure according to American Academy of Pediatrics percentiles (≥95th percentile). Family lifestyle habits were evaluated via the Family Nutrition and Physical Activity (FNPA) screening tool. Factors independently associated with high blood pressure and excess weight were identified using multivariable logistic regression models. Results: Among 479 children with complete anthropometric data (median age: 9.0 years), 42.3% presented with excess weight (21.9% overweight, 20.4% obesity). WHtR increased significantly across weight groups (median 0.44, 0.46 and 0.50, respectively; p < 0.001). Previously undiagnosed high blood pressurewas identified in 7.1% of the cohort, with a significant systolic blood pressure gradient (p < 0.001). Rapid weight gain during early infancy was significantly more frequent in children with obesity (10.6% vs. <5.3%, p = 0.025). In multivariable models, a family history of thrombophilic disorders (OR 3.16, 95% CI 1.27–7.41) and a less favourable FNPA score (OR 0.94 per point, 0.89–0.99) were independently associated with high blood pressure; a family history of hyperglycemia was associated overweight/obesity (OR 1.71, 1.06–2.78), and a family history of obesity wa associated with childhood obesity (OR 1.71, 1.02–2.88). Conclusions: Cardiovascular risk factors emerge early during primary school age, with central adiposity and silent high blood pressure manifesting prior to clinical disease. Multi-generational family history emerged as a consistent marker of risk, supporting routine multi-domain cardiovascular screening in primary pediatric healthcare.

We present a modular human-in-the-loop pipeline that converts unstructured discharge letters into process-mining–ready event traces. The pipeline uses task-specific Large Language Model prompting to extract temporally ordered clinical events, followed by expert validation and iterative refinement. Validated traces are stored for PM analyses. The approach is currently evaluated on 466 Stroke Unit discharge letters from Alessandria Hospital.