OpenExtract: Automated Data Extraction for Systematic Reviews in Health.
Achterberg Jim, van Dijk Bram, Meng Jing, +8 more·Studies in health technology and informatics
This study presents OpenExtract, an open-source pipeline for automated data extraction in large-scale systematic literature reviews. The pipeline queries large language models (LLMs) to predict data entries based on relevant sections of scientific articles. To test the efficacy of OpenExtract, we apply it to a systemat…