AMEND++: Benchmarking Eligibility Criteria Amendments in Clinical Trials

2026-01-09

arXiv.org

AI Summary

Frequent revisions to clinical trial eligibility criteria often lead to delays and increased costs. To address this challenge, this work introduces “eligibility criterion revision prediction” as a novel natural language processing task and presents AMEND++, the first structured benchmark for this purpose. AMEND++ comprises the real-world clinical trial version history dataset AMEND and its high-quality subset AMEND_LLM, refined via large language model–based denoising. We propose Change-Aware Masked Language Modeling (CAMLM), a pretraining strategy that effectively incorporates historical editing signals. Experimental results demonstrate that CAMLM substantially enhances the revision prediction performance of multiple baseline models, offering a new approach toward more efficient and robust clinical trial design.

Technology Category

• Natural Language Processing: (Large) Language Models
• Machine Learning: Feature Construction/Reformulation
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

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.

Problem

• eligibility criteria amendment
• clinical trials
• amendment prediction
• NLP
• protocol revision

Innovation

• eligibility criteria amendment prediction
• AMEND++
• Change-Aware Masked Language Modeling
• clinical trial design
• LLM-based denoising