Massive external validation of a machine learning algorithm to predict pulmonary embolism in hospitalized patients.

Journal: Thrombosis research
Published Date:

Abstract

BACKGROUND: Pulmonary embolism (PE) is a life-threatening condition associated with ~10% of deaths of hospitalized patients. Machine learning algorithms (MLAs) which predict the onset of pulmonary embolism (PE) could enable earlier treatment and improve patient outcomes. However, the extent to which they generalize to broader patient populations impacts their clinical utility.

Authors

  • Jieru Shen
    Dascena, Inc., Houston, TX, United States.
  • Satish Casie Chetty
    Dascena, Inc., Houston, TX, United States. Electronic address: dchetty@dascena.com.
  • Sepideh Shokouhi
    Dascena, Inc., Houston, TX, United States.
  • Jenish Maharjan
    Dascena, Inc., Houston, TX, United States. Electronic address: jmaharjan@dascena.com.
  • Yevheniy Chuba
    Dascena, Inc., Houston, TX, United States.
  • Jacob Calvert
    Dascena Inc., Hayward, California, USA.
  • Qingqing Mao
    Dascena Inc., Hayward, California, USA.