Deep Learning to Predict Mortality After Cardiothoracic Surgery Using Preoperative Chest Radiographs.

Journal: The Annals of thoracic surgery
Published Date: May 21, 2022

Abstract

BACKGROUND: The Society of Thoracic Surgeons Predicted Risk of Mortality (STS-PROM) estimates mortality risk only for certain common procedures (eg, coronary artery bypass or valve surgery) and is cumbersome, requiring greater than 60 inputs. We hypothesized that deep learning can estimate postoperative mortality risk based on a preoperative chest radiograph for cardiac surgeries in which STS-PROM scores were available (STS index procedures) or unavailable (non-STS index procedures).

Authors

  • Vineet K Raghu
    Department of Computer Science, University of Pittsburgh, Pittsburgh, PA, USA.
  • Philicia Moonsamy
    Division of Cardiac Surgery, Massachusetts General Hospital, Boston, Massachusetts.
  • Thoralf M Sundt
    Division of Cardiac Surgery, Massachusetts General Hospital, Boston, Massachusetts.
  • Chin Siang Ong
    Division of Cardiac Surgery, Johns Hopkins Hospital, Baltimore, Maryland.
  • Sanjana Singh
    Cardiovascular Imaging Research Center, Massachusetts General Hospital, Boston, Massachusetts.
  • Alexander Cheng
    Cardiovascular Imaging Research Center, Massachusetts General Hospital, Boston, Massachusetts.
  • Min Hou
    College of Pharmacy, Jiangxi University of Chinese Medicine, Nanchang 330004, China.
  • Linda Denning
    Division of Cardiac Surgery, Brigham and Women's Hospital, Boston, Massachusetts.
  • Thomas G Gleason
    Division of Cardiac Surgery, University of Pittsburgh Medical Center, Pittsburgh, Pennsylvania.
  • Aaron D Aguirre
  • Michael T Lu
    Cardiovascular Imaging Research Center, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston.

Keywords

External Resources

Popular Topics
Recent Journals