Recenti progressi in medicina最新文献

Breakthrough digital phenotyping approach reveals three distinct behavioral patterns from smartphone data that could revolutionize personalized mental health care. Using AI clustering on 77 users, we discovered "Night Owls", "Routine-Oriented", and "Always-Connected" behavioral types with 90%+ accuracy. Our explainable ML pipeline identifies key digital biomarkers for targeted interventions, offering clinicians data-driven insights for precision psychiatry.

This study shows that machine learning can accurately distinguish between mitochondrial and nuclear DNA mutations in primary mitochondrial diseases using only non-genetic and non-histological clinical data. While language models underperform in comparison, they show potential as complementary diagnostic tools.

Clinical research is increasingly regulated. Despite growing artificial intelligence (AI) use in healthcare, there is a lack of adequate tools to support researchers in non profit (AI or not) studies. To assist with the classification of clinical software, ClinEthix, a prototype conversational tool, has been developed to help researchers with regulatory qualification. A survey of 20 researchers found it highly useful, clear and user-friendly. Future developments will integrate LLMs and human feedback to improve accuracy.

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.

In Italy, the growing enthusiasm for artificial intelligence (AI) in healthcare contrasts with significant infrastructural, cultural, and trust-related barriers hindering its real-world adoption. Moving beyond the hype requires a systems thinking approach, proposing the learning health system (LHS) framework as a structured path for integration. We highlight the complementary roles of AI models: traditional machine learning (ML) is proven for diagnostics and prognostics, while large language models (LLMs) excel at administrative tasks and can structure unstructured data to train robust ML tools. The LHS cycle reveals key challenges for Italy: moving from Practice-to-Data requires overcoming data fragmentation; from Data-to-Knowledge involves transforming data into insights while mitigating bias; and from Knowledge-to-Practice necessitates bridging the gap between evidence and clinical workflow by building trust and AI literacy. Ultimately, successful and equitable AI implementation depends on a holistic strategy combining infrastructure development, multidisciplinary collaboration, and robust governance to enhance the quality and sustainability of the national healthcare system.

The combined use of IoT and AI enables automatic and precise collection of operative times through BLE bracelets, improving efficiency compared to manual recording. Surgery-specific models, trained on real data, better predict procedure duration, optimizing management and resources in the operating room.

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.

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.

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.

GLARE-Edu is an AI-powered, adaptive platform supporting healthcare professionals and students in learning clinical guidelines and improving decision-making through personalized training and realistic case simulations. Two case studies demonstrated significant improvements in guideline application and user satisfaction.