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

Assessing fracture risk using gradient boosting machine (GBM) models.

Elizabeth J Atkinson1, Terry M Therneau, L Joseph Melton

  • 1Divisions of Biomedical Statistics and Informatics, College of Medicine, Mayo Clinic, Rochester, MN, USA. atkinson@mayo.edu

Journal of Bone and Mineral Research : the Official Journal of the American Society for Bone and Mineral Research
|February 28, 2012
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Fractures: Bone Repair01:27

Fractures: Bone Repair

Treatment for a fracture is based on the type of break, the bone affected, and the patient's age.
Minor fractures with no bone displacement are treated by immobilizing the fractured bone using a cast or splint. However, in the case of fractures with displaced bones, the broken bones are repositioned before immobilization to ensure successful healing without deformation and loss of function. The realignment of fractured bone ends is performed through a process called reduction. If the procedure...

You might also read

Related Articles

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

Sort by
Same author

Determinants of Quality of Life in Patients with Immune-Checkpoint-Inhibitor Induced Secondary Adrenal Insufficiency.

The Journal of clinical endocrinology and metabolism·2026
Same author

Presentation and Clinical Patterns of Bilateral Adrenal Lesions: A Retrospective Cohort Study.

The Journal of clinical endocrinology and metabolism·2026
Same author

Deep Learning-Based Comparison of Knee Minimum Joint Space Width in Patients With Rheumatoid Arthritis and Osteoarthritis Before Total Knee Arthroplasty.

The Journal of rheumatology·2026
Same author

Vitamin B6 predicts poor outcomes in geographically distinct populations with primary sclerosing cholangitis.

Journal of hepatology·2026
Same author

Impact of Mild Autonomous Cortisol Secretion on Bone Density, Metabolism, and Microstructure: A Cross-sectional Study.

The Journal of clinical endocrinology and metabolism·2026
Same author

Compositional and functional differences of gut microbiome and metabolome inform pathogenesis of cholestatic liver disease.

Gut microbes·2026

Gradient boosting machine (GBM) modeling significantly improves bone fracture prediction by integrating diverse quantitative computed tomography (QCT) and high-resolution peripheral QCT (HR-pQCT) data, outperforming traditional methods.

Area of Science:

  • Osteoporosis research
  • Medical imaging analysis
  • Machine learning in healthcare

Background:

  • Quantitative computed tomography (QCT) has limitations in predicting bone fractures compared to standard areal bone mineral density (aBMD).
  • Advanced bone imaging techniques offer rich data on bone density, geometry, and microstructure.
  • Improved fracture prediction is crucial for preventing osteoporotic fractures.

Purpose of the Study:

  • To evaluate the efficacy of gradient boosting machine (GBM) modeling in enhancing fracture prediction.
  • To determine if GBM can integrate diverse QCT and HR-pQCT measurements for improved accuracy.
  • To assess the generalizability of GBM models across different fracture types and cohorts.

Main Methods:

  • Utilized two cohorts of postmenopausal women: one with distal forearm fractures and another with vertebral deformities.

Related Experiment Videos

  • Employed gradient boosting machine (GBM) modeling to integrate multiple bone density, geometry, and microstructure variables from QCT and HR-pQCT.
  • Assessed model performance using area under the receiver operating characteristic curve (AUC) for fracture discrimination.

    • Main Results:

    • Individual bone variables showed limited predictive power (median AUC 0.61).
    • GBM models incorporating all variables achieved AUCs close to 1.0.
    • Cross-cohort predictions demonstrated strong performance (AUCs 0.80-0.95), outperforming traditional parametric models (AUC 0.81).

    Conclusions:

    • Gradient boosting machine (GBM) modeling substantially enhances bone fracture prediction accuracy.
    • This machine learning approach effectively leverages comprehensive data from advanced bone imaging.
    • GBM offers a promising avenue for deeper insights into fracture propensity and improved clinical risk assessment.