Eligibility-Aware Evidence Synthesis: An Agentic Framework for Clinical Trial Meta-Analysis
Summary: arXiv:2604.02678v1 Announce Type: cross
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.
Key Features of EligMeta
- Automated Trial Discovery: Integrates advanced algorithms to identify relevant clinical trials efficiently.
- Eligibility-Aware Meta-Analysis: Transforms natural language queries into precise trial selection, ensuring that studies considered for analysis align with specific eligibility criteria.
- Hybrid Architecture: Combines LLM-based reasoning with deterministic execution to maintain reproducibility in results.
- Clinically Relevant Weighting: Incorporates population alignment into study weights, enhancing the validity of pooled estimates.
Results and Impact
In a gastric cancer landscape analysis, EligMeta reduced 4,044 candidate trials to 39 clinically relevant studies through rule-based filtering, successfully 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). This demonstrated the quantifiable impact of incorporating eligibility alignment into the evidence synthesis process.
Conclusion
EligMeta bridges automated trial discovery with eligibility-aware meta-analysis, providing a scalable and reproducible framework for evidence synthesis in precision medicine. By optimizing the selection and weighting of clinical trials based on relevant eligibility criteria, this innovative framework enhances the quality and applicability of meta-analyses, ultimately advancing the field of clinical research.