AI evidence extraction

OpenExtract: Automated Data Extraction for Systematic Reviews in Health

Jim Achterberg, Bram van Dijk, Jing Meng, Saif ul Islam, Gregory Epiphaniou, C.G. Maple et al. · Studies in health technology and informatics · 2026

AI-generated evidence extraction, verified across multiple analytical personas. Not a substitute for the peer-reviewed original.

9/10

Relevance

0/4

Quality (LMQS)

Evidence

Citations

0.00

FWCI

This is an AI analysis. Read the peer-reviewed original at the publisher: https://doi.org/10.3233/shti260316

Methodology & findings

Study design

Comparative validation study where an automated pipeline (OpenExtract) was applied to a systematic literature review in digital health and its outputs were compared against human researcher extractions..

Main result

The study found that "OpenExtract achieves precision and recall scores of > 0.8 in this task, indicating that it can be effective at extracting data automatically and efficiently."

Reports effect sizes.

Research paradigm

Empiricist

Author conclusions

The authors conclude that "OpenExtract achieves precision and recall scores of > 0.8 in this task, indicating that it can be effective at extracting data automatically and efficiently" for automated data extraction in systematic literature reviews.

Risk of bias

Limited to single domain (digital health) - generalizability unclear; Single comparison baseline (human researchers) - no inter-rater reliability metrics provided; No information on human researcher expertise or standardization of their process

Data: not_statedCode: not_statedExtracted from: pdfAgreement 87%

Explore related topics

Systematic Review Automation Literature Discovery Empirical Study