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 Video

Updated: Jul 19, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Predicting Patient-Reported Outcome Measures, Satisfaction, Healthcare Utilization, Mortality, and Return to Work

Shujaa T Khan1, Anukriti Sharma2, Shlok V Patel1

  • 1Department of Orthopedic Surgery, Cleveland Clinic, Cleveland, OH, USA.

The Journal of Arthroplasty
|July 14, 2026
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

Insulin autoimmune hypoglycemia unmasking monoclonal gammopathy in type 2 diabetes.

JCEM case reports·2026
Same author

The Trauma-specific Frailty Index Identifies Orthopaedic Trauma Patients at Risk for Stepdown Admission, Skilled Nursing Facility Discharge, and Prolonged Hospitalization.

Geriatric orthopaedic surgery & rehabilitation·2026
Same author

Minimal Clinically Important Difference and Patient Acceptable Symptomatic State after arthroscopic posterior labral repair in a non-military cohort.

JSES international·2026
Same author

Psychosocial Outcomes in Telemedicine and Long-Acting Incretin-Specific Behavioral Intervention.

Obesity science & practice·2026
Same author

Wearable-derived sleep architecture and chronic musculoskeletal pain: a national cohort study.

Pain management·2026
Same author

Preoperative psychiatric diagnosis predicts functional failure and dissatisfaction after total hip arthroplasty: a study of 11,766 patients.

Archives of orthopaedic and trauma surgery·2026

Machine learning models can predict outcomes after total knee arthroplasty (TKA), including patient satisfaction and return to work. These models show moderate to strong performance, aiding in preoperative planning and resource allocation for TKA success.

Area of Science:

  • Orthopedic Surgery
  • Health Informatics
  • Machine Learning in Healthcare

Background:

  • Patient-reported outcome measures (PROMs) and healthcare utilization are key metrics for evaluating total knee arthroplasty (TKA) success.
  • Predictive models can enhance preoperative planning, patient counseling, and resource allocation for TKA.
  • This study focused on developing and validating machine learning (ML) models to predict various postoperative outcomes following primary TKA.

Purpose of the Study:

  • To develop and validate machine learning models for predicting postoperative outcomes after primary total knee arthroplasty (TKA).
  • To assess the models' ability to predict patient-reported outcomes, satisfaction, healthcare utilization, mortality, and return to work.
  • To identify key predictors influencing these postoperative outcomes.
Keywords:
KneeMachine LearningOsteoarthritisPatient-Reported Outcome MeasuresPredictive ModelingTotal Knee Arthroplasty

Related Experiment Videos

Last Updated: Jul 19, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Main Methods:

  • Analysis of a prospective cohort of 14,900 patients undergoing primary unilateral TKA.
  • Development of Random Forest and XGBoost models using baseline demographic, clinical, socioeconomic, and surgical variables.
  • Evaluation of model performance using root mean square error for continuous outcomes and accuracy for categorical outcomes.

Main Results:

  • Machine learning models demonstrated moderate to strong predictive performance across various outcomes.
  • Accuracy for predicting 1-year mortality was 73% and return to work was 78%.
  • Key predictors included baseline Knee injury and Osteoarthritis Outcome Score (KOOS) Joint Replacement score, patient-reported outcome phenotype, age, BMI, Area Deprivation Index, race, and surgery start time.

Conclusions:

  • Machine learning models show significant potential for predicting patient outcomes after TKA.
  • These models can help identify distinct patient profiles based on socioeconomic and functional factors.
  • External validation is recommended prior to widespread clinical implementation of these predictive tools.