Citations

■

Abstract Response Assessment in Pediatric Neuro-Oncology (RAPNO) is an international working group dedicated to developing standardized recommendations for response assessment in children with central nervous system tumors enrolled on clinical trials. This standardization facilitates easier and more reliable comparison of responses across trials. Since the first RAPNO publication in 2013, response guidelines have been issued for medulloblastoma (MB), low-grade glioma (LGG), high-grade glioma (HGG), diffuse intrinsic pontine glioma, ependymoma, and craniopharyngioma. Many of these guidelines have already been incorporated into clinical trials to evaluate their effectiveness and accuracy. RAPNO has always been predicated on the idea that these consensus recommendations will require updates over time as they are applied in practice given technological advancements, evolving treatment approaches, and growing knowledge of disease pathology. A half-day RAPNO symposium sponsored by the Society of Neuro-Oncology was held in San Diego, California, United States, on May 15, 2025. This event coincided with the 8th Biennial Pediatric Society of Neuro-Oncology meeting. The main objectives were to identify ongoing RAPNO challenges, discuss potential updates, and plan future initiatives across 3 specific groups: (1) LGG/Craniopharyngioma, (2) HGG/diffuse midline glioma (DMG)/Ependymoma, and (3) MB and other seeding tumors. This manuscript reviews the symposium proceedings and highlights key topics and challenges discussed, as well as outlining future RAPNO initiatives.

Abstract Artificial intelligence (AI) and machine learning (ML) are beginning to enhance key workflows across blood banking (BB) and transfusion medicine (TM), including donor engagement, inventory forecasting, immunohaematology interpretation, haemovigilance and clinical decision support. These tools can extract signals from large, diverse datasets to improve efficiency, consistency and timeliness of care while enabling more proactive patient blood management. At the same time, TM is uniquely sensitive to safety and trust, so the field must pair innovation with disciplined validation and governance. This review surveys emerging applications and distils a balanced ethics and oversight framework tailored to TM and BB practice. Core elements include outcome‐focused validation and continuous monitoring; targeted fairness testing where biological or scientific plausibility suggests subgroup differences; layered transparency that distinguishes transparency, interpretability and explainability; and privacy by design with proportionate consent. We emphasize human oversight at every step: clinicians and laboratorians evaluate, monitor and troubleshoot models, perform tasks AI cannot, integrate multiple inputs to make decisions and interact with AI through guardrails such as intended‐use statements, confidence thresholds and clear override pathways. Accountability is shared across users, service directors, institutions and regulators. When implemented with these safeguards, AI can reduce preventable errors, improve resource allocation and support more equitable access to safe transfusion. The goal is principled pragmatism that protects patients and donors while enabling timely adoption of well‐validated tools.

Abstract Background The ability of large language models (LLMs) to work collaboratively and screen studies in a systematic review (SR) is under-explored. Hence, we aimed to evaluate the effectiveness of LLMs in automating the process of screening in systematic reviews. Methods This is an observational study which included labeled data (title and abstracts) for five SRs. Originally, two reviewers screened the citations independently for eligibility. A third reviewer cross-checked each citation for quality assurance. GPT-4, Claude-3-Sonnet, and Gemini-Pro-1.0 were used using zero-shot chain-of-thought prompting. Collaborative approaches included (i): conflict resolution using benefit of the doubt, (ii) majority voting using an independent third LLM and (iii) conflict resolution using an informed third LLM. Performance was assessed using accuracy, precision for exclusion, and recall for inclusion. Work saved over samples (WSS) was computed to estimate the reduction in manual human effort. Results A total of 11300 articles were included in this study. The individual models, GPT-4, Claude-3-Sonnet, and Gemini-Pro-1.0 exhibited a high precision for exclusion, achieving 99.7%, 99.7%, and 99.2% and high recall for inclusion achieving 95.5%, 96.6% and 85.7%, respectively. However, the collaborative approach utilizing the two best-performing models (GPT-4 and Claude-3S) achieved an average precision of 99.9% and a recall of 98.5% (across all collaborative approaches). Furthermore, the proposed collaborative approach resulted in an average WSS of 63.5%, compared to the average WSS of 45.2% for individual models. Conversational LLM interactions showed a consistent pattern of results. Limitations This study was limited due to reliance on proprietary models, and evaluation on oncology datasets. Conclusion Evidence shows that collaborative LLMs enable efficient, high-performing screening in systematic reviews, supporting continuous evidence updates. Primary funding source NIH (U24CA265879-01-1) and Carolyn-Ann-Kennedy-Bacon Fund.

Introduction People most likely to be affected by Alzheimer’s disease and related dementias (ADRD) are underrepresented in clinical research. Identifying and addressing factors which may influence their research participation is important to advance science and promote diversity. We examined the influence of social determinants of health (SDOH) on research participation among people living with ADRD. Methods We included those age 55 years and older living with ADRD, followed in our community practice in Rochester, Minnesota, who completed a questionnaire assessing SDOH and had at least one clinic visit between June 1, 2019 and June 1, 2020. Demographic and SDOH factors were examined by research participation. Results Among 3273 people included, research participation was low overall (265/3273; 8.1%). People participating in research were more likely to be socially integrated and of higher educational attainment (p < 0.05). Conclusion Promoting social interaction is a potential area for focus to increase research participation in at risk populations.

BACKGROUND: The implementation of data science concepts, skills, and tools in critical care research and practice faces multiple, complex barriers. METHODS: We developed an implementation science-based framework and method for measuring the adoption, implementation, and sustainment of data science concepts, skills, and tools in critical care—the Society of Critical Care Medicine (SCCM) Discovery Data Science Campaign (DSC) Implementation Research Logic Model (IRLM). Our IRLM specifies constructs for: 1) key determinants (i.e., barriers and facilitators) influencing the implementation of data science concepts, skills, and tools in critical care; 2) implementation strategies deployed by the SCCM Discovery DSC to address these determinants; 3) theorized mechanisms of action by which these strategies affect outcomes; and 4) upstream and downstream implementation outcomes influenced by implementation strategies. RESULTS AND CONCLUSIONS: We believe that our model can facilitate more rigorous measurement of theoretically grounded, empirically assessable factors driving implementation of data science concepts, skills, and tools in critical care.

Abstract The adoption of electronic health records (EHRs) has transformed health care, improving efficiency and chart accessibility. However, the widespread reliance on unstructured data entry and the lack of standardized documentation frameworks have resulted in significant data fragmentation across health care systems. The prevalence of unstructured data in EHRs limits their potential for clinical decision support, trial matching, real‐world evidence (RWE) generation, and quality measurement. Data fragmentation in health care triggers a cascade of challenges that ultimately compromise patient care. Clinicians face an excessive documentation burden and struggle to locate critical information buried in unstructured notes. Researchers encounter difficulties in extracting reliable clinical data. EHR vendors grapple with standardizing unstructured information for interoperability, and payers are unable to process unstructured clinical data efficiently to support value‐based care models. These challenges are particularly acute in oncology, where complex clinical elements like cancer staging, disease status, and treatment changes require precise, structured documentation. Emerging artificial intelligence (AI) technologies, such as large language models (LLMs) and ambient listening, offer a path to automate structured data generation while reducing the workload on providers. Here, the authors propose LLM‐based workflows that balance automation with clinician verification, streamlining data entry without compromising accuracy. Realizing these benefits requires coordinated efforts among clinicians, researchers, EHR vendors, payers, and policymakers to align regulatory frameworks with AI‐driven innovations. This article outlines a strategy to enhance structured data capture within EHRs, ultimately improving patient care, research, and health care efficiency.