AMEND++: Benchmarking Eligibility Criteria Amendments in Clinical Trials2026/01/31 by Trisha Das, Mandis Beigi, Jacob Aptekar +1
Computer Science · #cs.AI #cs.CL #cs.LG
arxiv created 2026/07/29 · arxiv updated 2026/07/30
Clinical trial amendments frequently introduce delays, increased costs, and administrative burden, with eligibility criteria being the most commonly amended component. We introduce eligibility criteria amendment prediction, a novel NLP task that aims to forecast whether the eligibility criteria of an initial trial protocol will undergo future amendments. To support this task, we release AMEND++, a benchmark suite comprising two datasets: AMEND, which captures eligibility-criteria version histories and amendment labels from public clinical trials, and \verb|AMENDLLM|, a refined subset curated using an LLM-based denoising pipeline to isolate substantive changes. We further propose Change-Aware Masked Language Modeling (CAMLM), a revision-aware pretraining strategy that leverages historical edits to learn amendment-sensitive representations. Experiments across diverse baselines show that CAMLM consistently improves amendment prediction, enabling more robust and cost-effective clinical trial design.