Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Pediatric Mitral Valve Surgery: Current Practice from the European Congenital Heart Surgeons Association Congenital Database Analysis.

The Journal of thoracic and cardiovascular surgery·2026
Same author

Towards optimal valve prescription for transcatheter aortic valve replacement (TAVR) surgery: a machine learning approach.

Health care management science·2026
Same author

Effectiveness of MIDCAB vs. OPCAB in LAD revascularization procedures in octogenerians: Results from the KROK registry.

Kardiologia polska·2026
Same author

Current availability and status of paediatric cardiac transplantation and mechanical circulatory support in twenty-eight European countries.

European journal of pediatrics·2026
Same author

Adding the Missing Link-Integration of Anesthesia and Perfusion Variables into Europe's Largest Congenital Cardiac Surgery Outcomes Database: Methods and First List of Candidate Variables by an ECHSA-EACTAIC-EBCP Collaboration.

Journal of cardiothoracic and vascular anesthesia·2026
Same author

Patient-Specific In-vivo Dynamic Motion of Ascending Thoracic Aortic Aneurysms from Cine CTA.

IEEE transactions on bio-medical engineering·2026

Related Experiment Video

Updated: Oct 13, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.4K

Benchmarking in Congenital Heart Surgery Using Machine Learning-Derived Optimal Classification Trees.

Dimitris Bertsimas1, Daisy Zhuo2,3, Jordan Levine2,3

  • 1Operations Research Center and Sloan School of Management, 2167Massachusetts Institute of Technology, Cambridge, MA, USA.

World Journal for Pediatric & Congenital Heart Surgery
|November 16, 2021
PubMed
Summary
This summary is machine-generated.

Optimal classification trees (OCTs) now define benchmarking standards for congenital heart surgery (CHS) outcomes. This machine learning approach allows for case-adjusted hospital performance evaluation, aiding quality improvement.

Keywords:
Congenital heart diseasecongenital heart surgerydatabase (all types)outcomesrisk analysis/modelingstatisticsstatistics-survival analysis

More Related Videos

Creation of Patient-Specific Silicone Cardiac Models with Applications in Pre-surgical Plans and Hands-on Training
09:15

Creation of Patient-Specific Silicone Cardiac Models with Applications in Pre-surgical Plans and Hands-on Training

Published on: February 10, 2022

3.8K
A Simplified Model for Heterotopic Heart Valve Transplantation in Rodents
06:33

A Simplified Model for Heterotopic Heart Valve Transplantation in Rodents

Published on: September 21, 2021

2.5K

Related Experiment Videos

Last Updated: Oct 13, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.4K
Creation of Patient-Specific Silicone Cardiac Models with Applications in Pre-surgical Plans and Hands-on Training
09:15

Creation of Patient-Specific Silicone Cardiac Models with Applications in Pre-surgical Plans and Hands-on Training

Published on: February 10, 2022

3.8K
A Simplified Model for Heterotopic Heart Valve Transplantation in Rodents
06:33

A Simplified Model for Heterotopic Heart Valve Transplantation in Rodents

Published on: September 21, 2021

2.5K

Area of Science:

  • Cardiovascular Surgery
  • Machine Learning in Healthcare
  • Quality Improvement Metrics

Background:

  • Previous work demonstrated the efficacy of optimal classification trees (OCTs) in predicting risk following congenital heart surgery (CHS).
  • This study extends OCT methodology to establish benchmarking standards for CHS, enabling case-adjusted hospital performance assessment.

Purpose of the Study:

  • To apply OCT methodology for defining benchmarking standards in congenital heart surgery (CHS).
  • To enable case-adjusted, hospital-specific performance evaluation after CHS.
  • To identify patient cohorts demonstrating over- or underperformance within hospitals.

Main Methods:

  • Analysis of the European Congenital Heart Surgeons Association Congenital Database (31,792 patients) for 10 benchmark procedure groups.
  • Development of OCT models to predict hospital mortality (HM), prolonged mechanical ventilatory support time (MVST), and length of hospital stay (LOS).
  • Creation of a "virtual hospital" benchmark using aggregate data to assess individual hospital performance against case-adjusted standards.

Main Results:

  • Average raw rates: HM 4.4%, MVST 15.3%, LOS 15.5%.
  • Compared to benchmarks, 17.0% of centers overperformed and 26.4% underperformed in predicted outcomes.
  • Significant variations in over- and underperformance were observed for MVST (34.0% over, 28.3% under) and LOS (26.4% over, 43.4% under).
  • OCT analysis identified specific patient cohorts within hospitals exhibiting distinct performance levels.

Conclusions:

  • OCT benchmarking provides a robust method for assessing case-adjusted hospital performance in CHS.
  • The approach allows for both overall and patient cohort-specific performance evaluations.
  • OCT analysis serves as a valuable tool for hospital self-assessment and targeted quality improvement initiatives in CHS care.