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

Knee Joint01:23

Knee Joint

The knee joint is the most complicated joint in the body. It consists of three articulations– two tibiofemoral and one patellofemoral. As is characteristic of synovial joints, the knee joint has a thin articular capsule that partially surrounds this joint cavity. Additionally, several ligaments, muscles, and cartilaginous structures support the movement of the knee.
A total of seven ligaments support the knee joint. The patellar ligament, which is also attached to the quadriceps femoris group...
  1. Home
  3. Predicting The Onset Of End-stage Knee Osteoarthritis Over Two- And Five-years Using Machine Learning.
  1. Home
  3. Predicting The Onset Of End-stage Knee Osteoarthritis Over Two- And Five-years Using Machine Learning.

Related Experiment Video

Standardized Histomorphometric Evaluation of Osteoarthritis in a Surgical Mouse Model
07:32

Standardized Histomorphometric Evaluation of Osteoarthritis in a Surgical Mouse Model

Published on: May 6, 2020

12.1K

Predicting the onset of end-stage knee osteoarthritis over two- and five-years using machine learning.

Zubeyir Salis1, Jeffrey B Driban2, Timothy E McAlindon3

  • 1Division of Rheumatology, Geneva University Hospitals and Faculty of Medicine, University of Geneva, Geneva, Switzerland; School of Human Sciences, the University of Western Australia, Perth, WA, Australia; Centre for Big Data Research in Health, the University of New South Wales, Kensington, NSW, Australia.

Seminars in Arthritis and Rheumatism
|March 21, 2024

View abstract on PubMed

Summary
This summary is machine-generated.

A new machine learning tool accurately predicts end-stage knee osteoarthritis (KOA) progression within 2-5 years, improving KOA clinical trial efficiency. This tool offers a reliable method for identifying participants likely to develop severe KOA.

Keywords:
Health care quality, access, and evaluationLearning curvePatient outcome assessmentTechnology assessment, Biomedical

More Related Videos

Tissue Collection and RNA Extraction from the Human Osteoarthritic Knee Joint
06:06

Tissue Collection and RNA Extraction from the Human Osteoarthritic Knee Joint

Published on: July 22, 2021

5.9K
Author Spotlight: Fu's Subcutaneous Needling for Knee Osteoarthritis Pain
07:19

Author Spotlight: Fu's Subcutaneous Needling for Knee Osteoarthritis Pain

Published on: March 24, 2023

4.7K

Related Experiment Videos

Standardized Histomorphometric Evaluation of Osteoarthritis in a Surgical Mouse Model
07:32

Standardized Histomorphometric Evaluation of Osteoarthritis in a Surgical Mouse Model

Published on: May 6, 2020

12.1K
Tissue Collection and RNA Extraction from the Human Osteoarthritic Knee Joint
06:06

Tissue Collection and RNA Extraction from the Human Osteoarthritic Knee Joint

Published on: July 22, 2021

5.9K
Author Spotlight: Fu's Subcutaneous Needling for Knee Osteoarthritis Pain
07:19

Author Spotlight: Fu's Subcutaneous Needling for Knee Osteoarthritis Pain

Published on: March 24, 2023

4.7K

Area of Science:

  • Orthopedics
  • Biomedical Engineering
  • Data Science

Background:

  • Identifying participants for knee osteoarthritis (KOA) trials is challenging.
  • Current methods using total knee replacement (TKR) are unreliable.
  • A robust metric for severe KOA is needed, leading to the end-stage KOA (esKOA) measure.

Purpose of the Study:

  • To develop and validate a machine-learning tool for predicting esKOA onset within 2-5 years.
  • To enhance the efficiency of KOA clinical trials by identifying at-risk individuals.
  • To provide a more reliable predictor than TKR for severe KOA progression.

Main Methods:

  • Utilized Osteoarthritis Initiative (OAI) data for model training (3,114 participants) and validation (606 participants).
  • Externally validated models using Multicentre Osteoarthritis Study (MOST) data (1,602 participants).
  • Defined esKOA by radiographic severity and symptom intensity; considered 51 predictors.

    • Main Results:

    • Achieved high Area Under Curve (AUC) values in external validation for predicting esKOA: Right knee (2.5 yrs: 0.847, 5 yrs: 0.853), Left knee (2.5 yrs: 0.824, 5 yrs: 0.807).
    • Models with fewer predictors showed comparable performance.
    • An online tool for esKOA prediction is available.

    Conclusions:

    • Developed a robust, externally validated machine learning tool for predicting esKOA onset.
    • The tool is proficient in identifying individuals likely to progress to esKOA within 2-5 years.
    • This tool can significantly improve the efficiency and design of future KOA clinical trials.