Faculty, Staff and Student Publications
Language
English
Publication Date
1-1-2025
Journal
npj Health Systems
DOI
10.1038/s44401-025-00018-3
PMID
40321467
PMCID
PMC12045799
PubMedCentral® Posted Date
5-1-2025
PubMedCentral® Full Text Version
Post-print
Abstract
Medical coding is essential for healthcare operations yet remains predominantly manual, error-prone (up to 20%), and costly (up to $18.2 billion annually). Although large language models (LLMs) have shown promise in natural language processing, their application to medical coding has produced limited accuracy. In this study, we evaluated whether fine-tuning LLMs with specialized ICD-10 knowledge can automate code generation across clinical documentation. We adopted a two-phase approach: initial fine-tuning using 74,260 ICD-10 code-description pairs, followed by enhanced training to address linguistic and lexical variations. Evaluations using a proprietary model (GPT-4o mini) on a cloud platform and an open-source model (Llama) on local GPUs demonstrated that initial fine-tuning increased exact matching from < 1% to 97%, while enhanced fine-tuning further improved performance in complex scenarios, with real-world clinical notes achieving 69.20% exact match and 87.16% category match. These findings indicate that domain-specific fine-tuned LLMs can reduce manual burdens and improve reliability.
Keywords
Health services, Information systems and information technology
Published Open-Access
yes
Recommended Citation
Hou, Zhen; Liu, Hao; Bian, Jiang; et al., "Enhancing Medical Coding Efficiency Through Domain-Specific Fine-Tuned Large Language Models" (2025). Faculty, Staff and Student Publications. 947.
https://digitalcommons.library.tmc.edu/uthshis_docs/947