Fine-Tuning an Existing Large Language Model with Knowledge from the Medical Expert System Hepaxpert...35th Medical Informatics Europe Conference (MIE 2025), May 19-21, 2025, Glasgow, Scotland.

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 si...

Descripción completa

Detalles Bibliográficos
Publicado en:	Studies in Health Technology & Informatics Vol. 327; pp. 143 - 148
Autores principales:	KAINZ, Jakob, SEISL, Philipp, GROB, Moritz, HAUPTFELD, Leonhard, WAHRINGER, Jonas, RAPPELSBERGER, Andrea, ADLASSNIG, Klaus-Peter
Formato:	research tables/charts Journal Article
Publicado:	Sage Publications Inc. 2025
Acceso en línea:	Ver este registro en EBSCOhost

Descripción
Sumario:	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.