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

Evaluating the C-section rate of different physician practices: using machine learning to model standard practice.

Rich Caruana1, Radu S Niculescu, R Bharat Rao

  • 1Cornell University, Computer Science, Ithaca, NY 14853, USA. caruana@cs.cornell.edu

AMIA ... Annual Symposium Proceedings. AMIA Symposium
|January 20, 2004
PubMed
Summary

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

Hypothesis Generation via Interpretable Machine Learning: A Case Study on Risk Factors for Postradiation Therapy Lung Cancer Recurrence.

Advances in radiation oncology·2026
Same author

A Machine Learning Approach to Determine the Optimal Age for Total Hip Arthroplasty: When Is Risk for Adverse Outcomes Lowest?

The Journal of the American Academy of Orthopaedic Surgeons·2026
Same author

The most important features in generalized additive models might be groups of features.

Scientific reports·2026
Same author

Exploring the optimal age for total knee arthroplasty to minimize risk of adverse outcomes: machine learning analysis of a statewide cohort.

Arthroplasty (London, England)·2026
Same author

The hidden risk of round numbers and sharp thresholds in clinical practice.

NPJ digital medicine·2025
Same author

Comparing Community-Level Social Determinants of Health With Patient Race in Total Hip Arthroplasty Outcomes.

Arthritis care & research·2025

Cesarean section (C-section) rates vary significantly among physician groups. Machine learning analysis revealed that both patient risk and physician practice contribute to these differences.

Area of Science:

  • Healthcare Management
  • Medical Informatics
  • Obstetrics and Gynecology

Background:

  • Population C-section rate is 16.8% among 22,175 expectant mothers.
  • Significant variation exists in C-section rates across 17 physician groups (13% to 23%).

Purpose of the Study:

  • To determine if C-section rate variations are due to patient risk or physician practice.
  • To retrospectively analyze factors influencing C-section delivery rates.

Main Methods:

  • Applied machine learning models to retrospective data.
  • Trained models to predict standard obstetric practice.
  • Evaluated individual physician practice C-section rates using predictive models.

Main Results:

Related Experiment Videos

  • Identified variations in intrinsic patient risk among physician groups.
  • Demonstrated significant differences in physician practice regarding C-section rates.
  • Both patient factors and physician behavior contribute to observed C-section rate disparities.

    • Conclusions:

    • Variations in C-section rates are attributable to both patient population characteristics and physician practice patterns.
    • Machine learning can effectively differentiate between patient-driven and practice-driven rate variations.