Congenital Heart Surgery Machine Learning-Derived In-Depth Benchmarking Tool.

Journal: The Annals of thoracic surgery
PMID: 38065331

Abstract

BACKGROUND: We previously showed that machine learning-based methodologies of optimal classification trees (OCTs) can accurately predict risk after congenital heart surgery and assess case-mix-adjusted performance after benchmark procedures. We extend this methodology to provide interpretable, easily accessible, and actionable hospital performance analysis across all procedures.

Authors

  • George E Sarris
    Athens Heart Surgery Institute, Greece.
  • Daisy Zhuo
    Interpretable AI, Boston, Massachusetts.
  • Luca Mingardi
    Operations Research Center, Massachusetts Institute of Technology, Cambridge, MA 02139, USA.
  • Jack Dunn
    Dimitris Bertsimas, Jack Dunn, Colin Pawlowski, John Silberholz, Alexander Weinstein, and Ying Daisy Zhuo, Massachusetts Institute of Technology, Cambridge; Eddy Chen, Massachusetts General Hospital Cancer Center; Harvard Medical School; Aymen A. Elfiky, Dana-Farber Cancer Institute; Brigham and Women's Hospital; Harvard Medical School, Boston, MA.
  • Jordan Levine
    Interpretable AI, Boston, MA.
  • Zdzislaw Tobota
    Department for Pediatric Cardiothoracic Surgery, 49805Children's Memorial Health Institute, Warsaw, Poland.
  • Bohdan Maruszewski
    Department for Pediatric Cardiothoracic Surgery, 49805Children's Memorial Health Institute, Warsaw, Poland.
  • Jose Fragata
    Hospital de Santa Marta and NOVA University, Lisbon, Portugal.
  • Dimitris Bertsimas
    Dimitris Bertsimas, Jack Dunn, Colin Pawlowski, John Silberholz, Alexander Weinstein, and Ying Daisy Zhuo, Massachusetts Institute of Technology, Cambridge; Eddy Chen, Massachusetts General Hospital Cancer Center; Harvard Medical School; Aymen A. Elfiky, Dana-Farber Cancer Institute; Brigham and Women's Hospital; Harvard Medical School, Boston, MA.

Keywords

External Resources

Popular Topics
Recent Journals