Evaluation of GPT-4 ability to identify and generate patient instructions for actionable incidental radiology findings.

Journal: Journal of the American Medical Informatics Association : JAMIA
Published Date: Sep 1, 2024

Abstract

OBJECTIVES: To evaluate the proficiency of a HIPAA-compliant version of GPT-4 in identifying actionable, incidental findings from unstructured radiology reports of Emergency Department patients. To assess appropriateness of artificial intelligence (AI)-generated, patient-facing summaries of these findings.

Authors

  • Kar-Mun C Woo
    Ronald O. Perelman Department of Emergency Medicine, NYU Grossman School of Medicine, New York, NY 10016, United States.
  • Gregory W Simon
    Ronald O. Perelman Department of Emergency Medicine, NYU Grossman School of Medicine, New York, NY 10016, United States.
  • Olumide Akindutire
    Ronald O. Perelman Department of Emergency Medicine, NYU Grossman School of Medicine, New York, NY 10016, United States.
  • Yindalon Aphinyanaphongs
    Department of Population Health, New York University, New York.
  • Jonathan S Austrian
    Department of Health Informatics, Medical Center IT, NYU Langone Health, New York, NY 10016, United States.
  • Jung G Kim
    Ronald O. Perelman Department of Emergency Medicine, NYU Grossman School of Medicine, New York, NY 10016, United States.
  • Nicholas Genes
    Ronald O. Perelman Department of Emergency Medicine, NYU Grossman School of Medicine, New York, NY 10016, United States.
  • Jacob A Goldenring
    Ronald O. Perelman Department of Emergency Medicine, NYU Grossman School of Medicine, New York, NY 10016, United States.
  • Vincent J Major
    Department of Population Health, NYU Langone Health, 227 East 30th St, 6th Floor, New York, NY, 10016, USA. vincent.major@nyulangone.org.
  • Chloé S Pariente
    Department of Health Informatics, Medical Center IT, NYU Langone Health, New York, NY 10016, United States.
  • Edwin G Pineda
    MCIT Clinical Systems-ASAP application, NYU Langone Health, New York, NY 10016, United States.
  • Stella K Kang
    Department of Radiology, NYU Langone Health, New York, New York; Department of Population Health, NYU Langone Health, New York, New York. Electronic address: stella.kang@nyumc.org.

Keywords

External Resources

Popular Topics
Recent Journals