Background and Objectives: Telemedicine has become an essential component of chronic Inflammatory Bowel Disease (IBD) care, yet the factors that shape patient satisfaction with remote consultations remain only partially understood. This study aimed to assess satisfaction with institutional telemedicine services among Italian patients with ulcerative colitis (UC) and Crohn’s disease (CD), and to identify sociodemographic, clinical and organisational predictors to inform more person-centred telehealth models. Materials and Methods: We conducted a prospective, multi-centre, cross-sectional study in three IBD units in northern, central and southern Italy between June and October 2024. Consecutive adult patients who had completed a scheduled, non-emergency telemedicine visit were invited within 24–48 h to complete an online questionnaire including the Italian Telemedicine Satisfaction Questionnaire (I-TSQ), sociodemographic items, IBD-related variables, and telemedicine process indicators (accessibility, technology usability, technical support, time saved). Data were analysed descriptively and with multivariable linear regression to determine independent predictors of satisfaction, adjusting for recruiting centre. Results: A total of 705 patients participated (54.9% UC; 55.3% disease duration > 10 years). Overall, telemedicine satisfaction was high (mean I-TSQ total 57.5 ± 4.9; range 35–70), and all respondents reported reduced indirect costs compared with in-person visits. Greater ease of technology use, more frequent contact with the care team, male sex, older age, and employment were independently associated with higher satisfaction scores. Conversely, first-ever teleconsultations, CD, subcutaneous therapies, more difficult platform access, and the need for technical support were linked to lower satisfaction. Model fit was modest (R² up to 0.20), suggesting the presence of additional unmeasured relational and contextual factors. Conclusions: Telemedicine for IBD is widely accepted in Italy, but satisfaction is strongly conditioned by digital usability, previous experience, and clinical complexity. Tailored telehealth pathways that incorporate user-friendly platforms, proactive technical support, and attention to vulnerable subgroups are needed to translate high satisfaction into sustained, equitable remote care.

Artificial intelligence, particularly Large Language Models (LLM) such as ChatGPT, is emerging as a potentially transformative support for traditionally complex and time-consuming Systematic Literature Reviews (SLRs). In this study, we compared the traditional SLR process executed accordingly with Cochrane guidelines, with an AI-assisted approach using ChatGPT across various stages, from research question formulation to report writing. Effectiveness was assessed through quantitative measurements of time savings at each phase. Results showed substantial time reductions in several operational tasks, including Gantt chart, generating search terms and suggesting selection criteria. However, critical issues arose in stages requiring interpretative judgement, such as analyzing results, assessing risk of bias and final drafting. While AI cannot replace the role of the researcher, it is a valuable tool to optimize SLR workflow. The combination of human expertise and LLM capabilities presents a promising solution, provided it is accompanied by continuous development of AI systems to improve their reliability, transparency and interoperability.

The growing capabilities of Large Language Models (LLMs) in understanding and generating clinical text are transforming the processing of unstructured medical data. This study presents a prompt-based framework for extracting structured information from Multidisciplinary Tumor Board (MTB) reports on ovarian cancer, written in Italian. Focusing on the anamnestic section, the main features (about Demographic, Scores, Comorbidities, Treatments and Gynecological History) are extracted through in-context learning prompts, and evaluated with the LLM-as-a-judge majority-voting scheme. Results show high accuracy across macroareas and strong agreement among judge models, confirming the robustness of the approach. The occurrence-based analysis further highlights how variable frequency influences extraction reliability, ensuring a more balanced interpretation of model performance. Overall, the framework enables reliable LLM-based information extraction and supports the creation of structured clinical knowledge for oncology applications.