Denis Horgan, Joe Paulson, Arturo Loaiza-Bonilla, Christer Svedman, Umberto Malapelle, Frédérique Penault Lorca, Hadi Mohamad Abu Rahsheed, Paul Hofman, Stan Kachnowski, Daniel Schneider, V. Subbiah
Clinical trial enrollment in oncology remains limited by increasingly complex eligibility criteria, biomarker stratification, and fragmented clinical data, contributing to prolonged recruitment timelines and low participation rates. This review examines contemporary pre-screening and screening approaches, spanning manual workflows, health-system-embedded digital tools, and emerging artificial intelligence-enabled methods. We assess the relative strengths and limitations of large language model-based strategies, including retrieval-augmented and domain-adapted approaches, in addressing scalability, accuracy, and equity challenges. Hybrid frameworks that integrate automated screening with clinician oversight appear most effective in improving trial matching efficiency, representativeness, and timely access to investigational therapies across diverse oncology populations.