AI for Extracting Pre-Analytical Variability Data from Biomedical Literature: Feasibility and Validation.
Targeted token reduction significantly improved extraction quality. Overall, the study shows that LLMs can serve as effective tools for supporting structured data extraction in biomedical contexts-though current limitations in reproducibility and contextual fidelity highlight the continued need for expert oversight.
Authors
- Oliver J. Bott (ORCID: https://orcid.org/0000-0002-8823-5247)
- Thomas Illig (ORCID: https://orcid.org/0000-0003-4284-5389)
- Vicky Scholz
- Sven Bichtemann
- Sara Haag
Institutions
- Leibniz University Hannover (DE)
Publication Details
- Journal
- PubMed
- Published
- 2025-09-03
- DOI
- https://doi.org/10.3233/shti251379
- Primary Topic
- Biomedical Text Mining and Ontologies
- Type
- article
- Field-Weighted Citation Impact
- 0.00