Generating colloquial radiology reports with large language models.

Journal: Journal of the American Medical Informatics Association : JAMIA
PMID: 39178375

Abstract

OBJECTIVES: Patients are increasingly being given direct access to their medical records. However, radiology reports are written for clinicians and typically contain medical jargon, which can be confusing. One solution is for radiologists to provide a "colloquial" version that is accessible to the layperson. Because manually generating these colloquial translations would represent a significant burden for radiologists, a way to automatically produce accurate, accessible patient-facing reports is desired. We propose a novel method to produce colloquial translations of radiology reports by providing specialized prompts to a large language model (LLM).

Authors

  • Cynthia Crystal Tang
    Department of Radiological Sciences, University of California, Irvine, Irvine, CA 92868, United States.
  • Supriya Nagesh
    Amazon Web Services, East Palo Alto, CA 94303, United States.
  • David A Fussell
    Department of Radiological Sciences, University of California, Irvine, Irvine, CA 92868, United States.
  • Justin Glavis-Bloom
    Department of Radiological Sciences, University of California, Irvine, CA.
  • Nina Mishra
    Amazon Web Services, East Palo Alto, CA 94303, United States.
  • Charles Li
    Computer Science Department, University of California Los Angeles (UCLA), Los Angeles, CA.
  • Gillean Cortes
    University of California Irvine, Radiology Department, UCI Medical Center, Orange, California, USA.
  • Robert Hill
    Department of Neurology, Yale University, New Haven, CT, USA.
  • Jasmine Zhao
    Department of Radiological Sciences, University of California, Irvine, Irvine, CA 92868, United States.
  • Angellica Gordon
    Department of Radiological Sciences, University of California, Irvine, Irvine, CA 92868, United States.
  • Joshua Wright
    Department of Radiological Sciences, University of California, Irvine, Irvine, CA 92868, United States.
  • Hayden Troutt
    Department of Radiological Sciences, University of California, Irvine, Irvine, CA 92868, United States.
  • Rod Tarrago
    Amazon Web Services, Seattle, WA 98121, United States.
  • Daniel S Chow
    Center for Artificial Intelligence in Diagnostic Medicine (CAIDM) and the University of California School of Medicine-Irvine, Irvine, CA.

Keywords

External Resources

Popular Topics
Recent Journals