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

arXiv cs.AI / 4/6/2026

💬 OpinionIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper introduces EligMeta, an agentic framework for end-to-end clinical trial evidence synthesis that combines automated trial discovery with eligibility-aware meta-analysis.
It argues that prior LLM approaches automate parts of systematic review but typically lack full, reproducible evidence synthesis, especially when accounting for clinical compatibility.
EligMeta improves conventional meta-analysis by deriving interpretable eligibility rules from natural-language queries and using deterministic execution for selection, weighting, and statistical pooling.
The framework computes similarity-based study weights based on eligibility alignment, enabling cohort-specific pooled estimates rather than relying only on statistical precision.
Experiments in gastric cancer and an olaparib adverse-events setting show that eligibility-aware weighting can materially change pooled effect estimates (e.g., shifting risk ratio from 2.18 to 1.97) while retaining guideline-cited trials.

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.