1. Fine-Tuning Open-Source Large Language Models to Improve Their Performance on Radiation Oncology Tasks: A Feasibility Study to Investigate Their Potential Clinical Applications in Radiation Oncology
- Author
-
Wang, Peilong, Liu, Zhengliang, Li, Yiwei, Holmes, Jason, Shu, Peng, Zhang, Lian, Li, Xiang, Li, Quanzheng, Laughlin, Brady S., Toesca, Diego Santos, Vora, Sujay A., Patel, Samir H., Sio, Terence T., Liu, Tianming, and Liu, Wei
- Subjects
Physics - Medical Physics ,Computer Science - Artificial Intelligence ,Computer Science - Computation and Language - Abstract
Background: The radiation oncology clinical practice involves many steps relying on the dynamic interplay of abundant text data. Large language models have displayed remarkable capabilities in processing complex text information. But their direct applications in specific fields like radiation oncology remain underexplored. Purpose: This study aims to investigate whether fine-tuning LLMs with domain knowledge can improve the performance on Task (1) treatment regimen generation, Task (2) treatment modality selection (photon, proton, electron, or brachytherapy), and Task (3) ICD-10 code prediction in radiation oncology. Methods: Data for 15,724 patient cases were extracted. Cases where patients had a single diagnostic record, and a clearly identifiable primary treatment plan were selected for preprocessing and manual annotation to have 7,903 cases of the patient diagnosis, treatment plan, treatment modality, and ICD-10 code. Each case was used to construct a pair consisting of patient diagnostics details and an answer (treatment regimen, treatment modality, or ICD-10 code respectively) for the supervised fine-tuning of these three tasks. Open source LLaMA2-7B and Mistral-7B models were utilized for the fine-tuning with the Low-Rank Approximations method. Accuracy and ROUGE-1 score were reported for the fine-tuned models and original models. Clinical evaluation was performed on Task (1) by radiation oncologists, while precision, recall, and F-1 score were evaluated for Task (2) and (3). One-sided Wilcoxon signed-rank tests were used to statistically analyze the results. Results: Fine-tuned LLMs outperformed original LLMs across all tasks with p-value <= 0.001. Clinical evaluation demonstrated that over 60% of the fine-tuned LLMs-generated treatment regimens were clinically acceptable. Precision, recall, and F1-score showed improved performance of fine-tuned LLMs.
- Published
- 2025