Application of NotebookLM, a large language model with retrieval-augmented generation, for lung cancer staging.

Journal: Japanese journal of radiology
PMID: 39585559

Abstract

PURPOSE: In radiology, large language models (LLMs), including ChatGPT, have recently gained attention, and their utility is being rapidly evaluated. However, concerns have emerged regarding their reliability in clinical applications due to limitations such as hallucinations and insufficient referencing. To address these issues, we focus on the latest technology, retrieval-augmented generation (RAG), which enables LLMs to reference reliable external knowledge (REK). Specifically, this study examines the utility and reliability of a recently released RAG-equipped LLM (RAG-LLM), NotebookLM, for staging lung cancer.

Authors

  • Ryota Tozuka
    Department of Radiology, University of Yamanashi, 1110 Shimokato, Chuo, Yamanashi, 409-3898, Japan.
  • Hisashi Johno
    Department of Anatomy and Cell Biology, Interdisciplinary Graduate School of Medicine, University of Yamanashi, Chuo, Yamanashi, 409-3898, Japan.
  • Akitomo Amakawa
    Department of Radiology, University of Yamanashi, 1110 Shimokato, Chuo, Yamanashi, 409-3898, Japan.
  • Junichi Sato
    Department of Radiology, University of Yamanashi, 1110 Shimokato, Chuo, Yamanashi, 409-3898, Japan.
  • Mizuki Muto
    Department of Radiology, University of Yamanashi, 1110 Shimokato, Chuo, Yamanashi, 409-3898, Japan.
  • Shoichiro Seki
    Department of Radiology, University of Yamanashi, 1110 Shimokato, Chuo, Yamanashi, 409-3898, Japan.
  • Atsushi Komaba
    Department of Radiology, University of Yamanashi, 1110 Shimokato, Chuo, Yamanashi, 409-3898, Japan.
  • Hiroshi Onishi
    Department of Radiology, University of Yamanashi, Yamanashi, Japan.

Keywords

External Resources

Popular Topics
Recent Journals