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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Digital Revitalization of a Legacy Linear Ion Trap System.

Analytical chemistry·2026
Same author

Lower septic revision rates following cementless compared with cemented robotic-assisted total knee arthroplasty using a single implant design : a five-year survivorship analysis.

The bone & joint journal·2026
Same author

Jumbo Femoral Heads in Total Hip Arthroplasty: Improved Early Stability Without Added Complications.

The Journal of arthroplasty·2026
Same author

Learning curve in image-based robotic assisted total knee arthroplasty: a MAKO-robot experience.

European journal of orthopaedic surgery & traumatology : orthopedie traumatologie·2026
Same author

Early Postoperative Gait Metrics After Superior Transverse Anatomic Reconstruction (STAR) versus Direct Anterior Total Hip Arthroplasty: A Prospective Comparative Study.

The Journal of arthroplasty·2026
Same author

Diverging Surgeon Distribution in Primary Versus Revision Arthroplasty: A National Analysis.

The Journal of arthroplasty·2026

Related Experiment Video

Updated: Aug 4, 2025

In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy
07:43

In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy

Published on: July 2, 2021

3.1K

An Interpretable Machine Learning Model for Predicting 10-Year Total Hip Arthroplasty Risk.

Seong Jun Jang1, Mark A Fontana2, Kyle N Kunze3

  • 1Weill Cornell College of Medicine, New York, New York; Department of Orthopaedic Surgery, Hospital for Special Surgery, New York, New York.

The Journal of Arthroplasty
|April 5, 2023
PubMed
Summary

A new machine learning model accurately predicts the risk of total hip arthroplasty (THA) within 10 years. Deep learning-automated radiographic measurements significantly improved prediction accuracy compared to demographic and clinical data alone.

Keywords:
Artificial intelligencedeep learninghip dysplasiamachine learningosteoarthritistotal hip arthroplasty

More Related Videos

The Use of Mixed Reality in Custom-Made Revision Hip Arthroplasty: A First Case Report
07:45

The Use of Mixed Reality in Custom-Made Revision Hip Arthroplasty: A First Case Report

Published on: August 4, 2022

3.4K
The Transition to an Anterior-Based Muscle Sparing Approach Improves Early Postoperative Function but is Associated with a Learning Curve
09:51

The Transition to an Anterior-Based Muscle Sparing Approach Improves Early Postoperative Function but is Associated with a Learning Curve

Published on: September 7, 2022

2.7K

Related Experiment Videos

Last Updated: Aug 4, 2025

In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy
07:43

In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy

Published on: July 2, 2021

3.1K
The Use of Mixed Reality in Custom-Made Revision Hip Arthroplasty: A First Case Report
07:45

The Use of Mixed Reality in Custom-Made Revision Hip Arthroplasty: A First Case Report

Published on: August 4, 2022

3.4K
The Transition to an Anterior-Based Muscle Sparing Approach Improves Early Postoperative Function but is Associated with a Learning Curve
09:51

The Transition to an Anterior-Based Muscle Sparing Approach Improves Early Postoperative Function but is Associated with a Learning Curve

Published on: September 7, 2022

2.7K

Area of Science:

  • Orthopedics
  • Medical Imaging
  • Machine Learning

Background:

  • Rising demand for total hip arthroplasty (THA) necessitates improved risk prediction.
  • Accurate prediction aids shared decision-making between patients and clinicians.

Purpose of the Study:

  • To develop and validate a predictive model for 10-year THA risk.
  • To assess the contribution of deep learning (DL)-automated radiographic measurements.

Main Methods:

  • Utilized data from the Osteoarthritis Initiative, including demographic, clinical, and baseline pelvic radiographs.
  • Developed DL algorithms for osteoarthritis and dysplasia measurements.
  • Trained generalized additive models to predict THA within 10 years.

Main Results:

  • The model incorporating DL radiographic measurements achieved an AUROC of 0.81 and AUPRC of 0.28.
  • DL-automated hip measurements alone yielded an AUROC of 0.77 and AUPRC of 0.22.
  • Key predictors included minimum joint space, hip pain, and analgesic use.

Conclusions:

  • Machine learning models integrating DL radiographic measurements enhance 10-year THA prediction accuracy.
  • The model's weighted variables align with clinical assessments of THA pathology.