Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.15664 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914370686025728 |
|---|---|
| author | Johno, Hisashi Johno, Yuki Amakawa, Akitomo Sato, Junichi Tozuka, Ryota Komaba, Atsushi Watanabe, Hiroaki Watanabe, Hiroki Goto, Chihiro Morisaka, Hiroyuki Onishi, Hiroshi Nakamoto, Kazunori |
| author_facet | Johno, Hisashi Johno, Yuki Amakawa, Akitomo Sato, Junichi Tozuka, Ryota Komaba, Atsushi Watanabe, Hiroaki Watanabe, Hiroki Goto, Chihiro Morisaka, Hiroyuki Onishi, Hiroshi Nakamoto, Kazunori |
| contents | Purpose: Retrieval-augmented generation (RAG) is a technology to enhance the functionality and reliability of large language models (LLMs) by retrieving relevant information from reliable external knowledge (REK). RAG has gained interest in radiology, and we previously reported the utility of NotebookLM, an LLM with RAG (RAG-LLM), for lung cancer staging. However, since the comparator LLM differed from NotebookLM's internal model, it remained unclear whether its advantage stemmed from RAG or inherent model differences. To better isolate RAG's impact and assess its utility across different cancers, we compared NotebookLM with its internal LLM, Gemini 2.0 Flash, in a pancreatic cancer staging experiment.
Materials and Methods: A summary of Japan's pancreatic cancer staging guidelines was used as REK. We compared three groups - REK+/RAG+ (NotebookLM with REK), REK+/RAG- (Gemini 2.0 Flash with REK), and REK-/RAG- (Gemini 2.0 Flash without REK) - in staging 100 fictional pancreatic cancer cases based on CT findings. Staging criteria included TNM classification, local invasion factors, and resectability classification. In REK+/RAG+, retrieval accuracy was quantified based on the sufficiency of retrieved REK excerpts.
Results: REK+/RAG+ achieved a staging accuracy of 70%, outperforming REK+/RAG- (38%) and REK-/RAG- (35%). For TNM classification, REK+/RAG+ attained 80% accuracy, exceeding REK+/RAG- (55%) and REK-/RAG- (50%). Additionally, REK+/RAG+ explicitly presented retrieved REK excerpts, achieving a retrieval accuracy of 92%.
Conclusion: NotebookLM, a RAG-LLM, outperformed its internal LLM, Gemini 2.0 Flash, in a pancreatic cancer staging experiment, suggesting that RAG may improve LLM's staging accuracy. Furthermore, its ability to retrieve and present REK excerpts provides transparency for physicians, highlighting its applicability for clinical diagnosis and classification. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_15664 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing Pancreatic Cancer Staging with Large Language Models: The Role of Retrieval-Augmented Generation Johno, Hisashi Johno, Yuki Amakawa, Akitomo Sato, Junichi Tozuka, Ryota Komaba, Atsushi Watanabe, Hiroaki Watanabe, Hiroki Goto, Chihiro Morisaka, Hiroyuki Onishi, Hiroshi Nakamoto, Kazunori Computation and Language Purpose: Retrieval-augmented generation (RAG) is a technology to enhance the functionality and reliability of large language models (LLMs) by retrieving relevant information from reliable external knowledge (REK). RAG has gained interest in radiology, and we previously reported the utility of NotebookLM, an LLM with RAG (RAG-LLM), for lung cancer staging. However, since the comparator LLM differed from NotebookLM's internal model, it remained unclear whether its advantage stemmed from RAG or inherent model differences. To better isolate RAG's impact and assess its utility across different cancers, we compared NotebookLM with its internal LLM, Gemini 2.0 Flash, in a pancreatic cancer staging experiment. Materials and Methods: A summary of Japan's pancreatic cancer staging guidelines was used as REK. We compared three groups - REK+/RAG+ (NotebookLM with REK), REK+/RAG- (Gemini 2.0 Flash with REK), and REK-/RAG- (Gemini 2.0 Flash without REK) - in staging 100 fictional pancreatic cancer cases based on CT findings. Staging criteria included TNM classification, local invasion factors, and resectability classification. In REK+/RAG+, retrieval accuracy was quantified based on the sufficiency of retrieved REK excerpts. Results: REK+/RAG+ achieved a staging accuracy of 70%, outperforming REK+/RAG- (38%) and REK-/RAG- (35%). For TNM classification, REK+/RAG+ attained 80% accuracy, exceeding REK+/RAG- (55%) and REK-/RAG- (50%). Additionally, REK+/RAG+ explicitly presented retrieved REK excerpts, achieving a retrieval accuracy of 92%. Conclusion: NotebookLM, a RAG-LLM, outperformed its internal LLM, Gemini 2.0 Flash, in a pancreatic cancer staging experiment, suggesting that RAG may improve LLM's staging accuracy. Furthermore, its ability to retrieve and present REK excerpts provides transparency for physicians, highlighting its applicability for clinical diagnosis and classification. |
| title | Enhancing Pancreatic Cancer Staging with Large Language Models: The Role of Retrieval-Augmented Generation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2503.15664 |