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 Experiment Videos

Artificial Intelligence for Predicting Perioperative Outcomes in Cardiac Surgery: A Systematic Review.

Jason Ha1, Hunaid A Vohra1

  • 1University of Bristol, United Kingdom.

Innovations (Philadelphia, Pa.)
|July 14, 2026
PubMed
Summary

Artificial intelligence (AI) models show better prediction for cardiac surgery outcomes than traditional scores. However, issues with validation and transparency need addressing for clinical use.

Related Concept Videos

Cardiomyopathy VII: Pre and Post Operative Nursing Management01:28

Cardiomyopathy VII: Pre and Post Operative Nursing Management

Patients with hypertrophic cardiomyopathy (HCM) and left ventricular outflow tract (LVOT) obstruction who remain symptomatic despite optimal medical therapy may undergo a septal myectomy (Morrow procedure). This procedure involves excising a portion of the hypertrophied septum below the aortic valve using a heart-lung machine to improve blood flow through the LVOT. Effective preoperative and postoperative nursing management ensures successful patient outcomes, minimizes complications, and...

You might also read

Related Articles

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

Sort by
Same author

Metaverse-Based Virtual Reality for Remote Anatomy Education: Pilot Randomized Controlled Trial.

JMIR formative research·2026
Same author

Molecular imaging of atherosclerotic plaque vulnerability: a narrative review.

The international journal of cardiovascular imaging·2026
Same author

Outcomes of robotically-assisted aortic valve surgery: A systematic review.

Perfusion·2026
Same author

Risk factors and clinical impact of transvalvular gradient following surgical repair of degenerative mitral regurgitation.

International journal of cardiology·2025
Same author

Society of cardiothoracic surgery in great Britain and Ireland guidance for adult mitral valve disease and interventions.

BMJ surgery, interventions, & health technologies·2025
Same author

An Analysis of Trainees' Operative Experiences Over the Past 16 Years Based on the Requirements of the New 2021 Cardiothoracic Surgery Curriculum in the United Kingdom and Ireland.

European journal of cardio-thoracic surgery : official journal of the European Association for Cardio-thoracic Surgery·2025

Area of Science:

  • Cardiology
  • Medical Informatics
  • Artificial Intelligence

Background:

  • Cardiac surgery presents significant risks of complications and mortality.
  • Artificial intelligence (AI) and machine learning (ML) are emerging tools for improving perioperative risk prediction.
  • Clinical decision-making in cardiac surgery can be enhanced by AI-driven insights.

Purpose of the Study:

  • To systematically review the clinical applications of AI models in cardiac surgery.
  • To evaluate the predictive performance of AI in cardiac surgery outcomes.
  • To identify limitations hindering the implementation of AI in cardiac surgery.

Main Methods:

  • A systematic review of PubMed and Embase databases was conducted for studies from January 2020 to July 2025.
Keywords:
artificial intelligencecardiac surgerycardiothoracic surgerydeep learningmachine learning

Related Experiment Videos

  • 178 studies met inclusion criteria, focusing on AI applications for predicting clinical outcomes in cardiac surgery patients.
  • Key outcomes assessed included model performance metrics and clinical utility.

    • Main Results:

    • AI models, particularly Random Forest, Logistic Regression, and XGBoost, outperformed traditional risk scores in predicting complications and mortality.
    • Commonly predicted outcomes included acute kidney injury and stroke.
    • Limited external validation (26%) and adherence to TRIPOD guidelines (19%) were noted, with SHapley Additive exPlanations being the most common interpretability method (37%).

    Conclusions:

    • AI models offer superior predictive capabilities for cardiac surgery compared to existing risk scores.
    • Addressing concerns related to validation, transparency, and generalizability is crucial for AI implementation.
    • Further research should focus on robust validation and transparent reporting of AI models in cardiac surgery.