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

Cardiac surgery risk models: a position article.

David M Shahian1, Eugene H Blackstone, Fred H Edwards

  • 1Lahey Clinic, Burlington, Massachusetts 01805, USA. david.m.shahian@lahey.org

The Annals of Thoracic Surgery
|October 30, 2004
PubMed
Summary
This summary is machine-generated.

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

Development of a Novel Society of Thoracic Surgeons Aortic Surgery Mortality and Morbidity Risk Model.

The Annals of thoracic surgery·2024
Same author

The Society of Thoracic Surgeons 2024 Risk Models for Lung Cancer Resection: Continued Refinement and Improved Outcomes.

The Annals of thoracic surgery·2024
Same author

The Society of Thoracic Surgeons Preoperative Beta Blocker Working Group Interim Report.

The Annals of thoracic surgery·2024
Same author

Hematocrit and Renal Failure in Aortic Arch Surgery: A Society of Thoracic Surgeons Database Study.

The Annals of thoracic surgery·2024
Same author

2024 Update of The Society of Thoracic Surgeons Short-term Esophagectomy Risk Model: More Inclusive and Improved Calibration.

The Annals of thoracic surgery·2024
Same author

Association Between Functional Tricuspid Regurgitation and Mortality Following Cardiac Surgery.

JACC. Advances·2024
Same journal

Late outcomes of postoperative complete heart block after congenital heart surgery: recovery or re-heart block?

The Annals of thoracic surgery·2026
Same journal

Coronary artery bypass grafting based on computed tomography-derived fractional flow reserve versus angiography: Early results.

The Annals of thoracic surgery·2026
Same journal

Beyond R0: Margin Cytology and Local Control After Sublobar Resection.

The Annals of thoracic surgery·2026
Same journal

Deferred AVR During CABG in Moderate Aortic Stenosis: Lower Index Risk or Deferred Cumulative Risk?

The Annals of thoracic surgery·2026
Same journal

The Renaissance of Transapical TAVR: From Competing Access Route to Enabling Platform for Hybrid Heart Therapy.

The Annals of thoracic surgery·2026
Same journal

A Moving Target: Interpreting Post-TAVI Reintervention in a Rapidly Evolving Era.

The Annals of thoracic surgery·2026
See all related articles

Accurate risk adjustment models are crucial for observational medical studies to account for patient differences. These models help assess predictors, guide treatment, and improve healthcare quality.

Area of Science:

  • Medical research
  • Health outcomes analysis
  • Biostatistics

Background:

  • Medical outcome variations stem from disease severity, treatment efficacy, or random chance.
  • Observational studies require risk adjustment to control for case mix differences.
  • Standard logistic regression is common, but other methods like Bayesian and machine learning models exist.

Purpose of the Study:

  • To highlight the necessity of risk adjustment in observational medical outcome studies.
  • To discuss the critical factors for developing accurate and useful risk adjustment models.
  • To outline the diverse applications of risk models in healthcare.

Main Methods:

  • Review of statistical and machine learning techniques for risk adjustment.
  • Discussion of essential components for robust model development and validation.

Related Experiment Videos

  • Exploration of the role of predictor variables and endpoint definitions.

    • Main Results:

    • Risk adjustment is essential for interpreting medical outcomes in non-randomized studies.
    • Model accuracy depends on database selection, variable inclusion, precise definitions, and rigorous validation.
    • Various statistical and machine learning approaches can be employed for risk adjustment.

    Conclusions:

    • Effective risk adjustment models are vital for accurate assessment of health outcomes.
    • Proper model development, validation, and auditing are critical for reliable results.
    • Risk models have broad applications, including quality assessment and continuous improvement in healthcare.