Fine-Tuning an Existing Large Language Model with Knowledge from the Medical Expert System Hepaxpert
Studies in Health Technology and Informatics · 2025
DOI: 10.3233/shti250290 ↗Kurz gefasst
Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Jakob Kainz und 6 weiteren Autor:innen. Beteiligte Einrichtung: Medexter Healthcare, Borschkegasse 7/5, 1090 Vienna, Austria. Hauptthemen laut MEDLINE: Expert Systems, Programming Languages, Natural Language Processing, Diagnosis, Computer-Assisted. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
The analysis and individual interpretation of hepatitis serology test results is a complex task in laboratory medicine, requiring either experienced physicians or specialized expert systems. This study explores fine-tuning a large language model (LLM) for hepatitis serology interpretation using a single graphics processing unit (GPU). A custom dataset based on the Hepaxpert expert system was used to train the LLM. Fine-tuning was performed on an Nvidia RTX 6000 Ada GPU via torchtune. The fine-tuned LLM showed significant performance improvements over the base model when compared to Hepaxpert using the METEOR algorithm. The findings highlight the potential of LLMs in enhancing medical expert systems as well as the significance of domain-specific fine-tuning.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Medexter Healthcare, Borschkegasse 7/5, 1090 Vienna, Austria.
- Medical University of Vienna, Center for Medical Data Science, Institute of Artificial Intelligence, Spitalgasse 23, 1090 Vienna, Austria.
Zitieren
APA
Kainz, J., Seisl, P., Grob, M., Hauptfeld, L., Wahringer, J., Rappelsberger, A., & Adlassnig, K. P. (2025). Fine-Tuning an Existing Large Language Model with Knowledge from the Medical Expert System Hepaxpert. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti250290
Vancouver
Kainz J, Seisl P, Grob M, Hauptfeld L, Wahringer J, Rappelsberger A, et al. Fine-Tuning an Existing Large Language Model with Knowledge from the Medical Expert System Hepaxpert. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti250290
BibTeX
@article{Kainz2025,
author = {Kainz, Jakob and Seisl, Philipp and Grob, Moritz and Hauptfeld, Leonhard and Wahringer, Jonas and Rappelsberger, Andrea and Adlassnig, Klaus-Peter},
title = {Fine-Tuning an Existing Large Language Model with Knowledge from the Medical Expert System Hepaxpert},
journal = {Studies in Health Technology and Informatics},
year = {2025},
doi = {10.3233/shti250290}
}
EUVIMED