POET: Protocol Optimization via Eligibility Tuning

TL;DR

This paper introduces POET, a guided generation framework that uses semantic axes to assist clinicians in efficiently creating eligibility criteria for clinical trials, improving over existing methods.

Contribution

It proposes a novel guided generation approach with interpretable axes and a rubric-based evaluation framework, enhancing clinical trial eligibility criteria creation.

Findings

Guided generation outperforms unguided methods in automatic and clinician evaluations.

Semantic axes improve interpretability and usability of eligibility criteria generation.

Framework offers a practical tool for AI-assisted clinical trial design.

Abstract

Eligibility criteria (EC) are essential for clinical trial design, yet drafting them remains a time-intensive and cognitively demanding task for clinicians. Existing automated approaches often fall at two extremes either requiring highly structured inputs, such as predefined entities to generate specific criteria, or relying on end-to-end systems that produce full eligibility criteria from minimal input such as trial descriptions limiting their practical utility. In this work, we propose a guided generation framework that introduces interpretable semantic axes, such as Demographics, Laboratory Parameters, and Behavioral Factors, to steer EC generation. These axes, derived using large language models, offer a middle ground between specificity and usability, enabling clinicians to guide generation without specifying exact entities. In addition, we present a reusable rubric-based evaluation framework that assesses generated criteria along clinically meaningful dimensions. Our results show that our guided generation approach consistently outperforms unguided generation in both automatic, rubric-based and clinician evaluations, offering a practical and interpretable solution for AI-assisted trial design.