Extraction of radiographic findings from unstructured thoracoabdominal computed tomography reports using convolutional neural network based natural language processing.

Journal: PloS one
Published Date:

Abstract

BACKGROUND: Heart failure (HF) is a major cause of morbidity and mortality. However, much of the clinical data is unstructured in the form of radiology reports, while the process of data collection and curation is arduous and time-consuming.

Authors

  • Mohit Pandey
    Dalio Institute of Cardiovascular Imaging, Weill Cornell Medicine, New York, USA.
  • Zhuoran Xu
    1 Dalio Institute of Cardiovascular Imaging New York-Presbyterian Hospital New York NY.
  • Evan Sholle
    Information Technologies & Services Department, Weill Cornell Medicine, New York, New York, United States of America.
  • Gabriel Maliakal
    Dalio Institute of Cardiovascular Imaging, Weill Cornell Medicine, New York, USA.
  • Gurpreet Singh
    Department of Chemical and Biomolecular Engineering, National University of Singapore, Singapore 117585, Singapore.
  • Zahra Fatima
    Dalio Institute of Cardiovascular Imaging, Weill Cornell Medicine, New York, New York, United States of America.
  • Daria Larine
    Jaffe Food Allergy Institute, Icahn School of Medicine at Mount Sinai, New York, New York, United States of America.
  • Benjamin C Lee
    Dalio Institute of Cardiovascular Imaging, Weill Cornell Medicine, New York, New York.
  • Jing Wang
    Endoscopy Center, Peking University Cancer Hospital and Institute, Beijing, China.
  • Alexander R van Rosendael
    Department of Radiology, New York-Presbyterian Hospital and Weill Cornell Medicine, New York, NY, USA.
  • Lohendran Baskaran
  • Leslee J Shaw
    Division of Cardiology, Emory University School of Medicine, Atlanta, GA, USA.
  • James K Min
    3 Department of Radiology, Weill Cornell Medicine , New York, New York.
  • Subhi J Al'Aref
    Dalio Institute of Cardiovascular Imaging, Weill Cornell Medicine, New York, USA.