JoVE - Journal of Visualized Experiments
JoVE Visualize
Contact Us

Predicting Major Preoperative Risk Factors for Retears After Arthroscopic Rotator Cuff Repair Using Machine Learning Algorithms

  • 0Department of Orthopedic Surgery, Seoul St. Mary's Hospital, The Catholic University of Korea, Banpo-Daero 222, Secho-gu, Seoul 06591, Republic of Korea.
Journal of Clinical Medicine +

|

March 27, 2025

|

March 27, 2025

View abstract on PubMed

Summary

This summary is machine-generated.

Machine learning models accurately predicted rotator cuff retears, identifying tear size, full-thickness tears, BMI, female sex, and pain scores as key risk factors after arthroscopic rotator cuff repair (ARCR). These findings enhance understanding of retear predictors.

Area Of Science

  • Orthopedic Surgery
  • Biomedical Engineering
  • Data Science in Medicine

Background

  • Rotator cuff tears are common, and retears after surgical repair pose a significant challenge.
  • Predicting retears is crucial for optimizing patient outcomes and surgical planning.

Purpose Of The Study

  • To identify and rank risk factors for retears following arthroscopic rotator cuff repair (ARCR).
  • To compare the predictive accuracy of machine learning models against traditional logistic regression.

Main Methods

  • Analysis of 788 primary ARCR cases with 27 preoperative variables.
  • Application of Extreme Gradient Boosting (XGBoost), Random Forest (RF), Support Vector Machine (SVM), Neural Network (NN), and logistic regression (LR) models.
  • Model performance evaluated using Area Under the Curve (AUC) with 8:2 training/testing split and three-fold validation.

Main Results

  • The overall retear rate was 11.9%.
  • RF (AUC=0.9790) and XGBoost (AUC=0.9785) were the top-performing models.
  • Key risk factors identified: tear size (ML/AP dimensions), full-thickness tears, Body Mass Index (BMI), female sex, and Visual Analogue Scale (VAS) pain score.

Conclusions

  • Machine learning models significantly outperform traditional logistic regression in predicting rotator cuff retears.
  • Tear size, full-thickness tears, BMI, female sex, and VAS pain score are the most influential risk factors for retears after ARCR.

Keywords: