# MetaMind: A multi-agent transformer-driven framework for automated network meta-analyses

## TL;DR

MetaMind is an automated system that uses AI to speed up network meta-analyses, reducing the time needed from months to days.

## Contribution

MetaMind introduces a multi-agent transformer-driven framework that automates network meta-analysis processes with minimal human input.

## Key findings

- Promptriever outperformed baseline models in retrieving relevant clinical trials from PubMed.
- MetaMind achieved high accuracy in extracting PICO elements and produced effect estimates matching manual analyses.
- The framework reduced the end-to-end NMA process to less than a week while maintaining statistical rigor.

## Abstract

Network meta-analysis (NMA) can compare several interventions at once by combining head-to-head and indirect trial evidence. However, identifying, extracting, and modelling these often takes months, delaying updates in many therapeutic areas.

To develop and validate MetaMind, an end-to-end, transformer-driven framework that automates NMA processes—including study retrieval, structured data extraction, and meta-analysis execution—while minimizing human input.

MetaMind integrates Promptriever, a fine-tuned retrieval model, to semantically retrieve high-impact clinical trials from PubMed; a multi-agent LLM architecture--Mixture of Agents (MoA)-- pipeline to extract PICO-structured (Population, Intervention, Comparison, Outcome) endpoints; and GPT-4o–generated Python and R scripts to perform Bayesian random-effects NMA and other NMA designs within a unified workflow. Validation was conducted by comparing MetaMind’s outputs against manually performed NMAs in ulcerative colitis (UC) and Crohn’s disease (CD).

Promptriever outperformed baseline SentenceTransformer with higher similarity scores (0.7403 vs. 0.7049 for UC; 0.7142 vs. 0.7049 for CD) and narrower relevance ranges. Promptriever performance achieved 82.1% recall, 91.1% precision and an F1 score of 86.4% when compared to a previously published NMA. MetaMind achieved 100% accuracy on a limited set of remission endpoints regarding PICO (Population, Intervention, Comparator, Outcome) element extraction and produced comparative effect estimates and credible intervals closely matching manual analyses.

In our validation studies, MetaMind reduced the end-to-end NMA process to less than a week, compared with the several months typically needed for manual workflows, while preserving statistical rigor. This suggests its potential for future scaling of evidence synthesis to additional therapeutic areas.