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

Classification algorithms for hip fracture prediction based on recursive partitioning methods.

Hua Jin1, Ying Lu, Steven T Harris

  • 1Department of Radiology University of California, San Francisco 94143-0946, USA.

Medical Decision Making : an International Journal of the Society for Medical Decision Making
|July 24, 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

Validation of 3D-DXA-derived proximal femur measurements against QCT across international clinical cohorts.

Bone·2026
Same author

Monte Carlo Resampling Validates Use of Bone Mineral Density Change as Surrogate to Replace Fracture in Future Randomized Trials of Osteoporosis Treatments: Results From SABER.

Journal of bone and mineral research : the official journal of the American Society for Bone and Mineral Research·2026
Same author

Response to Letter to the Editor regarding "The relationship between treatment-related changes in total hip BMD measured after 12, 18, and 24 mo and fracture risk reduction in osteoporosis clinical trials: the FNIH-ASBMR-SABRE project".

Journal of bone and mineral research : the official journal of the American Society for Bone and Mineral Research·2026
Same author

Treatment-related changes in total hip bone mineral density are applicable to trials of varied study designs and to drugs with differing mechanisms of action: meta-regression results from the FNIH-ASBMR SABRE study.

Journal of bone and mineral research : the official journal of the American Society for Bone and Mineral Research·2025
Same author

Association of exercise and race/ethnicity with atypical femur fracture.

JBMR plus·2025
Same author

The relationship between baseline bone mineral density and fracture incidence in the placebo groups of randomized controlled trials using individual patient data from the FNIH-ASBMR-SABRE project.

Journal of bone and mineral research : the official journal of the American Society for Bone and Mineral Research·2024
Same journal

Flexible Survival Extrapolation with Blended Hazards: Accounting for Treatment Effect Waning in Health Technology Assessment.

Medical decision making : an international journal of the Society for Medical Decision Making·2026
Same journal

A Microsimulation Model for Chronic Kidney Disease Progression in Type 2 Diabetes Patients in the United States: Michigan Model for Diabetes-Chronic Kidney Disease Model.

Medical decision making : an international journal of the Society for Medical Decision Making·2026
Same journal

Cardiovascular Risk Estimation and Statin Adherence: A Historical Cohort Study.

Medical decision making : an international journal of the Society for Medical Decision Making·2026
Same journal

Taste or Scale? Methodological Approach to Health Preferences Comparison across Groups.

Medical decision making : an international journal of the Society for Medical Decision Making·2026
Same journal

Mind the Gap: Impact of New Labels on Public Perceptions and Calculated Risk of Adverse Outcomes after a Melanoma In Situ Diagnosis-A Secondary Analysis of an Online Randomized Experiment.

Medical decision making : an international journal of the Society for Medical Decision Making·2026
Same journal

A Metamodel-Based General-Purpose Autocalibration Tool for Simulation Models.

Medical decision making : an international journal of the Society for Medical Decision Making·2026
See all related articles

This study introduces a cost-saving classification algorithm for predicting hip fractures, enhancing the robustness of decision trees. The new method achieves similar accuracy to optimal rules, making it clinically useful.

Area of Science:

  • Medical Informatics
  • Biostatistics
  • Machine Learning

Background:

  • Classification and regression trees (CART) are widely used for predictive modeling.
  • Existing CART algorithms may not account for variable costs, potentially leading to inefficient clinical applications.
  • Predicting 5-year hip fracture risk is crucial for targeted interventions.

Purpose of the Study:

  • To present two modifications to the classification and regression tree algorithm.
  • To develop a cost-saving classification approach for predicting hip fracture risk.
  • To evaluate the diagnostic utility and efficiency of the modified algorithm.

Main Methods:

  • Modified the classification and regression tree algorithm to improve split robustness.
  • Developed a cost-saving classification strategy by selecting noninferior splits based on variable cost and parent split usage.

Related Experiment Videos

  • Applied the algorithm to predict 5-year hip fracture risk using 43 variables from the Study of Osteoporotic Fractures.
  • Conducted a 6-fold cross-validation to compare the cost-saving rule with the optimal rule.

    • Main Results:

    • Generated both a robust optimal classification rule and a statistically noninferior cost-saving rule.
    • The cost-saving alternative classification demonstrated equivalent diagnostic utility to the optimal classification.
    • The modified algorithm can identify subjects with elevated 5-year hip fracture risk efficiently using dual X-ray absorptiometry and clinical data.

    Conclusions:

    • The modified classification and regression tree algorithm offers a cost-effective approach for clinical risk prediction.
    • The cost-saving strategy maintains diagnostic efficiency, providing a practical alternative to more complex methods.
    • This approach can aid in identifying high-risk individuals for hip fracture without compromising accuracy.