Predicting post-operative right ventricular failure using video-based deep learning.

Journal: Nature communications
PMID: 34465780

Abstract

Despite progressive improvements over the decades, the rich temporally resolved data in an echocardiogram remain underutilized. Human assessments reduce the complex patterns of cardiac wall motion, to a small list of measurements of heart function. All modern echocardiography artificial intelligence (AI) systems are similarly limited by design - automating measurements of the same reductionist metrics rather than utilizing the embedded wealth of data. This underutilization is most evident where clinical decision making is guided by subjective assessments of disease acuity. Predicting the likelihood of developing post-operative right ventricular failure (RV failure) in the setting of mechanical circulatory support is one such example. Here we describe a video AI system trained to predict post-operative RV failure using the full spatiotemporal density of information in pre-operative echocardiography. We achieve an AUC of 0.729, and show that this ML system significantly outperforms a team of human experts at the same task on independent evaluation.

Authors

  • Rohan Shad
    Department of Cardiothoracic Surgery, Stanford University, Stanford, CA, USA.
  • Nicolas Quach
    Department of Cardiothoracic Surgery, Stanford University, Stanford, CA, USA.
  • Robyn Fong
    Department of Cardiothoracic Surgery, Stanford University, Stanford, CA, USA.
  • Patpilai Kasinpila
    Department of Cardiothoracic Surgery, Stanford University, Stanford, CA, USA.
  • Cayley Bowles
    Department of Cardiothoracic Surgery, Stanford University, Stanford, CA, USA.
  • Miguel Castro
    AdventHealth Tampa, Digestive Health Institute, Tampa, FL, USA.
  • Ashrith Guha
    Department of Cardiovascular Medicine, Houston Methodist DeBakey Heart Centre, Houston, TX, USA.
  • Erik E Suarez
    Department of Cardiothoracic Surgery, Houston Methodist DeBakey Heart Centre, Houston, TX, USA.
  • Stefan Jovinge
    Department of Cardiovascular Surgery, Spectrum Health Grand Rapids, Grand Rapids, MI, USA.
  • Sangjin Lee
    Department of Cardiovascular Surgery, Spectrum Health Grand Rapids, Grand Rapids, MI, USA.
  • Theodore Boeve
    Department of Cardiovascular Surgery, Spectrum Health Grand Rapids, Grand Rapids, MI, USA.
  • Myriam Amsallem
    Department of Cardiovascular Medicine, Stanford University, Stanford, CA, USA.
  • Xiu Tang
    Department of Cardiovascular Medicine, Stanford University, Stanford, CA, USA.
  • Francois Haddad
    Division of Cardiovascular Medicine (F.H.), in the Department of Medicine, Stanford University, CA.
  • Yasuhiro Shudo
    Department of Cardiothoracic Surgery, Stanford University, Stanford, CA, USA.
  • Y Joseph Woo
    Department of Cardiothoracic Surgery, Stanford University, Stanford, CA, USA.
  • Jeffrey Teuteberg
    Department of Cardiovascular Medicine, Stanford University, Stanford, CA, USA.
  • John P Cunningham
    Department of Statistics, Grossman Center for the Statistics of Mind Zuckerman Mind, Brain Behavior Institute, Center for Theoretical Neuroscience, Columbia University, New York City, United States. Electronic address: jpc2181@columbia.edu.
  • Curtis P Langlotz
    Stanford University, University Medical Line, Stanford, CA, 94305, US.
  • William Hiesinger
    Department of Cardiothoracic Surgery, Stanford University, Stanford, CA, USA. willhies@stanford.edu.

Keywords

External Resources

Popular Topics
Recent Journals