AI-Enabled Trial Matching and Adaptive Trials in Pediatric Oncology

Pediatric oncology represents a crucial and rapidly evolving field within precision medicine, distinguished by the rarity and diversity of childhood cancers as well as their intricate molecular underpinnings. Although notable progress has been made in diagnostic techniques and therapeutic interventions, children lag behind adults in clinical trial enrollment, constraining the pace of innovation and the equitable application of novel therapies. This limited representation stems from the challenges inherent to conducting trials within small, heterogeneous patient populations and the logistical and ethical hurdles of pediatric research. In response, artificial intelligence (AI) has begun to reshape the landscape of trial design by facilitating personalized prognosis, optimizing cohort selection, and enabling real-time adaptation. AI-driven systems are harnessing multi-modal data—encompassing genomics, imaging, and electronic health records—to refine eligibility criteria and treatment matching. However, the application of these advanced methods in pediatric oncology remains in its infancy, calling for systematic investigation and validation to address the specific needs and vulnerabilities of young patients.This Research Topic aims to drive a cross-disciplinary conversation and accelerate evidence generation on the role of AI in transforming clinical trial paradigms for pediatric oncology. By highlighting practical implementations, conceptual frameworks, and forward-thinking analyses, the initiative seeks to deepen understanding of how AI-powered trial matching, adaptive designs, and predictive analytics can address persistent barriers in pediatric cancer research. Central goals include evaluating AI’s potential to enhance trial access through refined patient matching, reduce inequities, improve adaptive protocol execution, and foster more resilient, data-driven decision-making processes in rare and complex cancer settings. Contributions are expected to clarify the translational impact of integrating AI with existing and emerging data sources and to examine strategies for overcoming regulatory, ethical, and infrastructural hurdles.The scope of this Research Topic is defined by the exploration and critical assessment of AI-enabled methodologies specifically tailored to the design and conduct of clinical trials in pediatric oncology, while acknowledging both technical limitations and ethical considerations. To gather further insights in advancing precision pediatric trial research, we welcome articles addressing, but not limited to, the following themes:- AI-driven clinical trial matching platforms and algorithms for children with cancer/- Machine learning approaches to eligibility detection via electronic health records, imaging, or multi-omics data.- Implementation case studies of AI-assisted trial enrollment or adaptive protocols in pediatric settings.- Simulation and modeling studies of adaptive trial designs leveraging AI and real-time feedback.- Integration of AI with real-world data tools, such as registries, wearables, and digital biomarkers, for trial optimization.- Examination of ethical, legal, and regulatory issues in deploying AI for pediatric clinical trials.- Conceptualizations of federated learning, synthetic control arms, and digital twins in childhood cancer research.- Approaches to enhance diversity, equity, and inclusion in pediatric oncology trials through AI. - Perspectives on explainable AI, clinician trust, and human-AI collaboration in trial contexts.- Infrastructure needs and data governance considerations for sustainable implementation of AI in multi-institutional pediatric clinical research.Please note: manuscripts consisting solely of bioinformatics, computational analysis, or predictions based on public databases — without accompanying validation in an independent clinical or patient cohort, or biological validation in vitro or in vivo — are not suitable for publication in Frontiers in Oncology. Authors with such manuscripts are encouraged to consider submission via Frontiers in Digital Health, which is a participating journal in this Research Topic.Dr. Giacomelli declares that he is affiliated with Polistudium SRL, a private company active in the field of medical research; and that he does not have any conflict of interest directly relevant to this editorial effort.Prof. Andrea Pession declares that he is a co-founder and shareholder of Biogenera SpA. Topic editors: Luca Giacomelli, Andrea Pession Source: https://www.frontiersin.org/research-topics/77737/ai-enabled-trial-matching-and-adaptive-trials-in-pediatric-oncology