Assessing Large Language Models for Oncology Data Inference From Radiology Reports.

Journal: JCO clinical cancer informatics
PMID:

Abstract

PURPOSE: We examined the effectiveness of proprietary and open large language models (LLMs) in detecting disease presence, location, and treatment response in pancreatic cancer from radiology reports.

Authors

  • Li-Ching Chen
    Department of Otolaryngology, Cheng Hsin General Hospital, Taipei, Taiwan.
  • Travis Zack
    Bakar Computational Health Sciences Institute, University of California San Francisco, San Francisco, CA.
  • Arda Demirci
    University of California, Berkeley, Berkeley, CA.
  • Madhumita Sushil
    Bakar Computational Health Sciences Institute, University of California, San Francisco, San Francisco, California, USA.
  • Brenda Miao
    Bakar Computational Health Sciences Institute, University of California, San Francisco, San Francisco, CA.
  • Corynn Kasap
    Helen Diller Family Comprehensive Cancer Center, University of California, San Francisco, San Francisco, CA.
  • Atul Butte
    Bakar Computational Health Sciences Institute, University of California, San Francisco, San Francisco, California, United States of America.
  • Eric A Collisson
    Helen Diller Family Comprehensive Cancer Center, University of California, San Francisco, San Francisco, CA.
  • Julian C Hong
    All Authors: Duke University, Durham, NC.