Deep-Learning Language-Modeling Approach for Automated, Personalized, and Iterative Radiology-Pathology Correlation.

Journal: Journal of the American College of Radiology : JACR
Published Date:

Abstract

PURPOSE: Radiology-pathology correlation has long been foundational to continuing education, peer learning, quality assurance, and multidisciplinary patient care. The objective of this study was to determine whether modern deep-learning language-modeling techniques could reliably match pathology reports to pertinent radiology reports.

Authors

  • Ross W Filice
    MedStar Health, MedStar Georgetown University Hospital, 3800 Reservoir Rd, NW CG201, Washington DC, 20007 (R.W.F.); and MedStar Health, National Center for Human Factors in Healthcare, Washington, DC (R.M.R.).