$\texttt{AMEND++}$: Benchmarking Eligibility Criteria Amendments in Clinical Trials

TL;DR

This paper introduces AMEND++, a benchmark suite and a novel NLP task for predicting amendments to clinical trial eligibility criteria, aiming to reduce delays and costs in trial management.

Contribution

It presents the AMEND++ benchmark, a new NLP task for amendment prediction, and proposes CAMLM, a revision-aware pretraining method that enhances prediction accuracy.

Findings

CAMLM improves amendment prediction performance.

The benchmark datasets enable robust evaluation of amendment prediction models.

Revisions can be effectively modeled using historical edit information.

Abstract

Clinical trial amendments frequently introduce delays, increased costs, and administrative burden, with eligibility criteria being the most commonly amended component. We introduce \textit{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 $\texttt{AMEND++}$, a benchmark suite comprising two datasets: $\texttt{AMEND}$, which captures eligibility-criteria version histories and amendment labels from public clinical trials, and $\verb|AMEND_LLM|$, a refined subset curated using an LLM-based denoising pipeline to isolate substantive changes. We further propose $\textit{Change-Aware Masked Language Modeling}$ (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.