Aims: To evaluate the effectiveness and reliability of large language models (LLMs) in retrieving and synthesizing biomedical information to support off‐label drug prescribing in paediatric rare diseases, and to compare their performance with human‐authored references in terms of scientific rationale, adverse events and drug interactions. Methods: The study reviewed 20 cases of off‐label prescriptions in rare paediatric diseases using 4 LLMs (i.e., GPT‐4o, Sophos‐2, Claude‐3, Scopus AI). The queries addressed focused on scientific rationale, adverse events and drug interactions. The performance measures encompassed sensitivity, precision, accuracy, F1‐score, response quality and reference quality. A Global Performance Score integrated all measures. Results: After evaluating 2758 references and 480 responses, a significant discrepancy was found among 4 LLMs concerning Global Performance Score ( P = .001). Posthoc analysis showed that Scopus AI vs . GPT‐4o comparison was significant, with GPT‐4o showing higher values. Median LLM reference quality often surpassed human performance, yet variability limits conclusions regarding superiority. Conclusions: LLMs are capable of retrieving and synthesizing biomedical information, but performance varies depending on query type and search mode. These tools speed up retrieving relevant information to assess off‐label prescribing appropriateness. Despite the promise of artificial intelligence, human oversight remains critical to ensure data accuracy and reliability.
Driven by technological advances and regulatory developments, the clinical trials industry is undergoing a period of transformation. Decentralized clinical trials (DCTs) promise to streamline processes, increase participant engagement and improve data quality. The pediatric clinical trial landscape is challenging, as participation in a clinical trial affects the whole family. DCTs allow for increased patient engagement, thereby improving trial quality and consequently drug safety. The Italian Medicines Agency (AIFA), in its quest for regulatory simplification and alignment with the European framework, has established comprehensive guidelines to facilitate these decentralized trials. The present work aims to delve into the regulations to understand the feasibility of conducting decentralized pediatric trials in Italy.
Background/Objectives: Pediatric allogeneic hematopoietic stem cell transplantation (allo-HSCT) is complicated by iron overload and hypomagnesemia, both contributing to immune dysfunction and post-transplant morbidity. The combined impact of these metabolic disturbances on pediatric allo-HSCT outcomes remains unexplored. This study aims to determine whether hypomagnesemia can serve as a prognostic biomarker for delayed immune reconstitution and explores its interplay with iron overload in predicting post-transplant complications and survival outcomes. Methods: A retrospective analysis was conducted on 163 pediatric allo-HSCT recipients. Serum magnesium levels were measured at defined intervals post-transplant, and outcomes were correlated with CD4+ T cell recovery, time to engraftment, incidence of graft-versus-host disease (GVHD), and survival within 12 months. Iron status, including siderosis severity, was evaluated using imaging and laboratory parameters obtained from clinical records. Results: Patients who died within 12 months post-transplant exhibited significantly lower magnesium levels. Hypomagnesemia was associated with delayed CD4+ T cell recovery, prolonged engraftment, and an increased risk of acute GVHD. A strong inverse correlation was observed between magnesium levels and the severity of siderosis. Iron overload appeared to exacerbate magnesium deficiency. Additionally, the coexistence of hypomagnesemia and siderosis significantly increased the risk of immune dysfunction and early mortality. No significant association was found with chronic GVHD. Conclusions: Hypomagnesemia is a significant, early predictor of poor outcomes in pediatric allo-HSCT, particularly in the context of iron overload, underscoring the need for early intervention, including iron chelation and MRI, to improve outcomes.