AutoForest: Automatically Generating Forest Plots from Biomedical Studies with End-to-End Evidence Extraction and Synthesis

2026-06-01

AI Summary

This work proposes AutoForest, the first end-to-end system capable of automatically generating publication-ready forest plots directly from one or multiple biomedical research papers. Addressing the labor-intensive nature of current systematic reviews—which rely on manual extraction of data from unstructured clinical text and handcrafted meta-analyses—AutoForest automates the entire pipeline: it recommends intervention-control-outcome (ICO) elements, extracts effect sizes, performs statistical synthesis, and visualizes results. The system integrates large language models for textual understanding and data extraction, couples them with established meta-analysis algorithms, and provides an interactive interface to facilitate rapid expert validation. Evaluations through real-world case studies and user research demonstrate that AutoForest substantially improves the efficiency and accuracy of evidence synthesis while significantly lowering the barrier to conducting rigorous evidence-based medicine research.

Abstract

Systematic reviews rely on forest plots to synthesise quantitative evidence across biomedical studies, but generating them remains a fragmented and labour-intensive process. Researchers must interpret complex clinical texts, manually extract outcome data from trials, define appropriate interventions and comparators, harmonise inconsistent study designs, and carry out meta-analytic computations-typically using specialised software that demands structured inputs and domain expertise. While recent work has demonstrated that large language models can extract study-level data from unstructured text, no existing system automates the complete pipeline from raw documents to synthesised forest plots. To address this gap, we introduce AutoForest, the first end-to-end system that generates publication-ready forest plots directly from biomedical papers. Given one or more study papers, AutoForest automatically suggests ICO (Intervention, Comparator, Outcome) elements, extracts outcome data, performs statistical synthesis, and renders the final forest plot. We describe the system architecture, user interface and demonstrate its effectiveness on real-world examples through a user study involving clinicians, showing how AutoForest can accelerate evidence synthesis and substantially lower the barrier to conducting meta-analyses.

Problem

• forest plots
• systematic reviews
• evidence synthesis
• meta-analysis
• biomedical studies

Innovation

• forest plot
• evidence synthesis
• large language models
• meta-analysis
• automated data extraction