Recenti progressi in medicina最新文献

{"title":"Pipeline multimodale integrata per l’analisi longitudinale delle neurodegenerazioni: integrazione di test cognitivi e neuroimaging con machine learning per una indagine sui meccanismi comuni di Alzheimer e Parkinson.","authors":"Simone Torsello, Samuele Carli, Alice Cuzzucoli, Daniele Caligiore","doi":"10.1701/4573.45798","DOIUrl":"https://doi.org/10.1701/4573.45798","url":null,"abstract":"<p><p>This study introduces a multimodal pipeline that combines cognitive tests and MRI data from ADNI and PPMI to examine Parkinson's and Alzheimer's diseases. Using FastSurfer for quick brain volume analysis, it uncovers common neurobiological mechanisms and patterns of cognitive decline. Early findings support longitudinal multimodal evaluation, advancing precision medicine and personalized clinical decision-making in neurodegenerative disorders.</p>","PeriodicalId":20887,"journal":{"name":"Recenti progressi in medicina","volume":"116 10","pages":"607-608"},"PeriodicalIF":0.0,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145213524","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Valutazione del ragionamento clinico dei reasoning large language models su casi clinici complessi.","authors":"Vittorio De Vita, Bianca Destro Castaniti, Mariapia Vassalli, Lorenzo De Mori, Doriana Lacalaprice, Emanuele Arcà, Antonio Cristiano, Chiara Battipaglia, Pietro Eric Risuleo, Tommaso Dionisi, Francesco Andrea Causio","doi":"10.1701/4573.45794","DOIUrl":"https://doi.org/10.1701/4573.45794","url":null,"abstract":"<p><p>Large language models (LLMs) show promise in explicit reasoning for complex medical fields like psychiatry. This study assessed the clinical validity of Gemini's chain-of-thought (CoT) reasoning in 10 complex psychiatric cases, evaluated by specialists using six metrics. Results indicate high performance (average score ≥4.26/5), especially in step sufficiency and factual accuracy, suggesting that CoT reasoning by LLMs can support transparent and detailed clinical decision-making.</p>","PeriodicalId":20887,"journal":{"name":"Recenti progressi in medicina","volume":"116 10","pages":"599-600"},"PeriodicalIF":0.0,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145213527","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ricerca di strategie ottimali di prompting di un LLM per fornire un supporto efficace al dialogo medico-paziente.","authors":"Francesco Giuliani, Onofrio Cappucci, Clara De Gennaro, Francesco Ricciardi, Sergio Russo, Massimiliano Copetti, Paola Crociani, Maura Pugliatti, Maurizio Leone","doi":"10.1701/4573.45779","DOIUrl":"https://doi.org/10.1701/4573.45779","url":null,"abstract":"<p><p>The study evaluated the use of a popular large language model (LLM) to support neurologists in communicating with patients with Multiple Sclerosis. We describe the development of a tailored COSTAR prompt and the process that led to its refinement. A cohort of neurologists assessed the prompt's effectiveness using the QAMAI tool. The results highlight both strengths and the issues that must be addressed for the effective clinical use of LLMs in this context.</p>","PeriodicalId":20887,"journal":{"name":"Recenti progressi in medicina","volume":"116 10","pages":"569-570"},"PeriodicalIF":0.0,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145213538","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Why tomorrow's public health needs to be digital: artificial intelligence and automation for a sustainable Italian National Health Service.","authors":"Francesco Baglivo, Giacomo Diedenhofen, Luigi De Angelis, Alessio Pivetta, Francesco Andrea Causio, Angelo D'Ambrosio, Francesca Aurora Sacchi, Marcello Di Pumpo, Alessandro Belpiede, Gianpaolo Ghisalberti, Diana Ferro, Caterina Rizzo","doi":"10.1701/4573.45775","DOIUrl":"https://doi.org/10.1701/4573.45775","url":null,"abstract":"<p><p>Italy's National Health Service (SSN) serves one of Europe's oldest populations under fiscal constraint and a fragmented data infrastructure. Rather than a standalone fix, artificial intelligence should be treated as a catalyst for a human-centred digital transformation that improves access, quality, and sustainability. Building on the Italian Society for Artificial Intelligence in Medicine (SIIAM) vision, we outline a pragmatic agenda. First, reduce elective-care backlogs by automating confirmations, reminders, cancellations, and rescheduling; deploy multilingual conversational agents to collect structured pre-visit histories and deliver summaries, while natural-language processing flags overdue follow-ups. Second, advance equity by offering inclusive digital front doors and tele-triage that prioritise patients facing language, literacy, socioeconomic, or geographic barriers. Third, curb waste through clinical-decision support and workflow automation that standardise evidence-based practice and relieve documentation burden. Fourth, modernise surveillance by pairing large language model powered voice agents for behaviour and symptom monitoring with participatory systems and AI epidemic intelligence. Fifth, link data and people through multidisciplinary teams and a human-in-the-loop approach that embeds transparency, bias mitigation, privacy, and safety. Implementation should start where impact is fastest: risk-stratified booking, proactive reminders, and shared dashboards with comparable indicators. To sustain gains, ring-fence resources for regional multidisciplinary units, enforce interoperability and reference datasets, and align procurement with European requirements for auditability and post-deployment monitoring. AI can help reshape Italian healthcare, but success ultimately depends on integrated data, trained teams, and robust governance.</p>","PeriodicalId":20887,"journal":{"name":"Recenti progressi in medicina","volume":"116 10","pages":"551-555"},"PeriodicalIF":0.0,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145213541","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intelligenza artificiale generativa in medicina del lavoro: quindici large language models a confronto su quesiti a scelta multipla in lingua italiana.","authors":"Martina Padovan, Alessandro Palla","doi":"10.1701/4573.45789","DOIUrl":"https://doi.org/10.1701/4573.45789","url":null,"abstract":"<p><p>This study offers a comparative evaluation of fifteen generative artificial intelligence models using 397 Italian multiple-choice questions on occupational medicine. Model accuracy ranged from 75.06% to 95.72%. The results highlight the need to assess large language models in specialized fields to support their safe and effective integration into medical education and occupational medicine practice.</p>","PeriodicalId":20887,"journal":{"name":"Recenti progressi in medicina","volume":"116 10","pages":"589-590"},"PeriodicalIF":0.0,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145213439","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Validazione clinica di un sistema Model Context Protocol per il supporto decisionale pediatrico: studio su casi benchmark.","authors":"Gianluca Mondillo, Alessandra Perrotta, Vittoria Frattolillo, Mariapia Masino, Simone Colosimo, Fabio Giovanni Abbate, Pierluigi Marzuillo","doi":"10.1701/4573.45787","DOIUrl":"https://doi.org/10.1701/4573.45787","url":null,"abstract":"<p><p>Model Context Protocol (MCP) is an open standard for connecting AI applications to external tools. While not designed for healthcare, it offers advantages for clinical decision support through natural language queries. We developed a pediatric MCP server with 46 clinical tools and tested it using 32 cases. Results: correctly processed 31/32 cases. This is the first clinical validation of MCP technology, demonstrating high reliability for clinical application.</p>","PeriodicalId":20887,"journal":{"name":"Recenti progressi in medicina","volume":"116 10","pages":"585-586"},"PeriodicalIF":0.0,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145213550","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"La piattaforma S-RACE: una soluzione cloud per dati sanitari real-world, che guida la traslazione clinica e la governance responsabile della intelligenza artificiale.","authors":"Alberto Traverso, Simone Barbieri, Marco Denti, Antonio Esposito, Carlo Tacchetti","doi":"10.1701/4573.45788","DOIUrl":"https://doi.org/10.1701/4573.45788","url":null,"abstract":"<p><p>The S-RACE platform is a cloud-based AI solution for using real-world health data. It addresses data quality and governance challenges with an end-to-end pipeline, including on-premise anonymisation and tools for clinicians and data scientists. Aligned with responsible AI principles, it aims to accelerate the translation of AI research into clinical practice, improving patient care.</p>","PeriodicalId":20887,"journal":{"name":"Recenti progressi in medicina","volume":"116 10","pages":"587-588"},"PeriodicalIF":0.0,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145213380","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Il metaverso in anestesia: il progetto “Insieme” per l’empowerment del paziente e l’educazione continua in medicina.","authors":"Matteo Panizzi, Valentina Bellini, Tania Domenichetti, Luigino Darhour, Luca Sancricca, Elena Bignami","doi":"10.1701/4573.45783","DOIUrl":"https://doi.org/10.1701/4573.45783","url":null,"abstract":"<p><p>The \"Insieme\" project applies the metaverse to anesthesia by creating a digital twin of the Operating Suite to improve the doctor-patient relationship, reduce preoperative anxiety, and support continuous education. Patients undergo an immersive virtual journey, interacting with nurse and doctor avatars, simulating the surgical experience and postoperative awakening.</p>","PeriodicalId":20887,"journal":{"name":"Recenti progressi in medicina","volume":"116 10","pages":"577-578"},"PeriodicalIF":0.0,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145213385","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cancer Virtual Lab: una piattaforma sicura e interoperabile basata su knowledge graph e large language model per la ricerca oncologica.","authors":"Paolo De Angelis, Alice Andalò, Nicola Gentili, Luca Giorgetti, Lorenzo Ridolfi, Roberto Pasolini, Andrea Pagliarani, Martina Cavallucci, Roberto Vespignani, Antonella Carbonaro","doi":"10.1701/4573.45795","DOIUrl":"https://doi.org/10.1701/4573.45795","url":null,"abstract":"<p><p>Cancer Virtual Lab is a secure and interoperable platform for oncology research. It integrates HL7 FHIR and ontology-based knowledge graphs to structure clinical data, enabling advanced semantic reasoning. Generative AI supports researchers by guiding data exploration and interpretation, accelerating insights and enhancing precision oncology in a privacy-preserving, scalable environment.</p>","PeriodicalId":20887,"journal":{"name":"Recenti progressi in medicina","volume":"116 10","pages":"601-602"},"PeriodicalIF":0.0,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145213387","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Valutazione one-shot di Mistral7B sul nuovo benchmark EuropeMedQA.","authors":"Olivia Riccomi, Francesco Andrea Causio, Vittorio De Vita, Antonio Cristiano, Manuel Del Medico, Lorenzo De Mori, Chiara Battipaglia, Melissa Sawaya, Luigi De Angelis, Marcello Di Pumpo, Alessandra Piscitelli, Pietro Eric Risuleo, Giulia Vojvodic, Bianca Destro Castaniti, Nicolò Scarsi","doi":"10.1701/4573.45804","DOIUrl":"https://doi.org/10.1701/4573.45804","url":null,"abstract":"<p><p>Artificial intelligence (AI) adoption in healthcare is rising. Unbiased evaluation requires uncontaminated benchmarks. We evaluated Mistral-7B-Instruct-v0.1 on 1120 human-validated Italian medical multiple-choice questions (SSM). Mistral achieved 40,2% accuracy and 38.8% F1 score on the dataset. Likely causes include English-centric instruction tuning, lack of medical domain knowledge, and prompt misalignment with the task format. These findings suggest that LLMs need further improvements before deployment.</p>","PeriodicalId":20887,"journal":{"name":"Recenti progressi in medicina","volume":"116 10","pages":"619-620"},"PeriodicalIF":0.0,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145213507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}