Qualifying Certainty in Radiology Reports through Deep Learning-Based Natural Language Processing.

Journal: AJNR. American journal of neuroradiology
Published Date: Aug 19, 2021

Abstract

BACKGROUND AND PURPOSE: Communication gaps exist between radiologists and referring physicians in conveying diagnostic certainty. We aimed to explore deep learning-based bidirectional contextual language models for automatically assessing diagnostic certainty expressed in the radiology reports to facilitate the precision of communication.

Authors

  • F Liu
    Department of Radiology, Massachusetts General Hospital, Harvard University, Boston, MA, USA. Electronic address: fliu12@mgh.harvard.edu.
  • P Zhou
    Department of Thyroid and Breast Surgery, the 960th Hospital of the People's Liberation Army of China, Jinan 250031, China.
  • S J Baccei
    Department of Radiology (F.L., P.Z., S.J.B., M.J.M., N.A., M.P.R.), University of Massachusetts Medical School, Worcester, Massachusetts.
  • M J Masciocchi
    Department of Radiology (F.L., P.Z., S.J.B., M.J.M., N.A., M.P.R.), University of Massachusetts Medical School, Worcester, Massachusetts.
  • N Amornsiripanitch
    Department of Radiology (F.L., P.Z., S.J.B., M.J.M., N.A., M.P.R.), University of Massachusetts Medical School, Worcester, Massachusetts.
  • C I Kiefe
    From the Department of Population and Quantitative Health Sciences (F.L., C.I.K.), University of Massachusetts Medical School, Worcester, Massachusetts.
  • M P Rosen
    Department of Radiology (F.L., P.Z., S.J.B., M.J.M., N.A., M.P.R.), University of Massachusetts Medical School, Worcester, Massachusetts max.rosen@umassmemorial.org.

Keywords

External Resources

Popular Topics
Recent Journals