Eligibility-Aware Evidence Synthesis: An Agentic Framework for Clinical Trial Meta-Analysis

2026-04-02

AI Summary

This study addresses a critical limitation in current clinical evidence synthesis methods, which often overlook the compatibility of inclusion and exclusion criteria across trials and lack end-to-end automation. To overcome this, the authors propose EligMeta, a novel framework that integrates eligibility criterion alignment directly into meta-analysis weight computation. EligMeta leverages large language models to automatically translate natural language queries into reproducible screening rules, combining deterministic logic, semantic similarity metrics, and statistical aggregation within an interpretable and reproducible hybrid architecture. In a gastric cancer analysis, the framework precisely identified 39 relevant studies from 4,044 trials, encompassing all 13 guideline-cited trials. Furthermore, in an olaparib adverse event analysis, the new weighting scheme adjusted the hazard ratio from 2.18 to 1.97, substantially enhancing the clinical relevance of the effect estimate.

Abstract

Clinical evidence synthesis requires identifying relevant trials from large registries and aggregating results that account for population differences. While recent LLM-based approaches have automated components of systematic review, they do not support end-to-end evidence synthesis. Moreover, conventional meta-analysis weights studies by statistical precision without considering clinical compatibility reflected in eligibility criteria. We propose EligMeta, an agentic framework that integrates automated trial discovery with eligibility-aware meta-analysis, translating natural-language queries into reproducible trial selection and incorporating eligibility alignment into study weighting to produce cohort-specific pooled estimates. EligMeta employs a hybrid architecture separating LLM-based reasoning from deterministic execution: LLMs generate interpretable rules from natural-language queries and perform schema-constrained parsing of trial metadata, while all logical operations, weight computations, and statistical pooling are executed deterministically to ensure reproducibility. The framework structures eligibility criteria and computes similarity-based study weights reflecting population alignment between target and comparator trials. In a gastric cancer landscape analysis, EligMeta reduced 4,044 candidate trials to 39 clinically relevant studies through rule-based filtering, recovering all 13 guideline-cited trials. In an olaparib adverse events meta-analysis across four trials, eligibility-aware weighting shifted the pooled risk ratio from 2.18 (95% CI: 1.71-2.79) under conventional Mantel-Haenszel estimation to 1.97 (95% CI: 1.76-2.20), demonstrating quantifiable impact of incorporating eligibility alignment. EligMeta bridges automated trial discovery with eligibility-aware meta-analysis, providing a scalable and reproducible framework for evidence synthesis in precision medicine.

Problem

• evidence synthesis
• meta-analysis
• eligibility criteria
• clinical trial
• population alignment

Innovation

• eligibility-aware meta-analysis
• agentic framework
• clinical trial synthesis
• large language models
• reproducible evidence synthesis