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: Oct 23, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.0K

A Novel, Potentially Universal Machine Learning Algorithm to Predict Complications in Total Knee Arthroplasty.

Sai K Devana1, Akash A Shah1, Changhee Lee2

  • 1Department of Orthopaedic Surgery, University of California, Los Angeles, USA.

Arthroplasty Today
|August 17, 2021
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

How to benchmark medical AI agents.

PLoS medicine·2026
Same author

Causal inference and digital twins: a roadmap for the future of clinical trials.

NPJ digital medicine·2026
Same author

The novelty of anticoagulation in LVAD Therapy: Current Practice, the Role of Direct Oral Anticoagulants, and Future Directions.

Journal of cardiovascular pharmacology·2026
Same author

Translation readiness of model-based synthetic tabular data in healthcare: a systematic review and governance audit.

Journal of the American Medical Informatics Association : JAMIA·2026
Same author

Evaluation of Baseline and Interim-Therapy PET Features for Prognostication in High-Risk Pediatric Hodgkin Lymphoma: A Retrospective Analysis of the AHOD1331 Trial.

Journal of nuclear medicine : official publication, Society of Nuclear Medicine·2026
Same author

Deep learning-based natural language processing for critical care identification in pediatric emergency department.

BMC emergency medicine·2026

AutoPrognosis (AP) demonstrated superior prediction of complications after total knee arthroplasty (TKA) compared to traditional machine learning (ML) methods. This novel automated framework offers improved accuracy for predicting TKA outcomes.

Area of Science:

  • Orthopedic Surgery
  • Medical Informatics
  • Machine Learning

Background:

  • Accurate prediction models for total knee arthroplasty (TKA) outcomes are lacking.
  • Machine learning (ML) offers predictive power, but algorithm selection is challenging.
  • AutoPrognosis (AP) is a novel automated ML framework designed for robust prognostic modeling.

Purpose of the Study:

  • To compare the predictive performance of AutoPrognosis (AP) against various machine learning (ML) methods for complications after TKA.
  • To evaluate discriminative power, calibration, and feature importance of different predictive models.

Main Methods:

  • Utilized 38 preoperative variables from 156,750 primary TKAs (2015-2017).
  • Compared logistic regression (LR), XGBoost, Gradient Boosting, AdaBoost, Random Forest, and AP.
Keywords:
AutoPrognosisKnee replacementMachine learningPredictive modeling

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

3.6K

Related Experiment Videos

Last Updated: Oct 23, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.0K
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

3.6K
  • Assessed model performance using area under the receiver operating curve (AUC) and Brier score.

    • Main Results:

    • AP achieved the highest discriminative performance (AUC 0.679) compared to LR (0.617) and other ML models.
    • AP demonstrated comparable calibration (Brier score 0.007) to other ML methods.
    • Identified distinct important predictors for AP versus LR, suggesting nonlinear relationships.

    Conclusions:

    • AutoPrognosis (AP) exhibits superior discriminative ability in predicting TKA complications over conventional ML algorithms.
    • AP offers similar calibration to other ML methods, indicating reliable outcome predictions.
    • The findings suggest AP effectively captures nonlinear relationships crucial for TKA outcome prediction.