Related Experiment Video
Updated: Jun 20, 2025
07:33
In Vitro Application of a Wireless Sensor in Flexion-Extension Gap Balance of Unicompartmental Knee Arthroplasty
Published on: May 5, 2023
561
Artificial intelligence in total and unicompartmental knee arthroplasty
Umile Giuseppe Longo1,2, Sergio De Salvatore3,4, Federica Valente5
1Fondazione Policlinico Universitario Campus Bio-Medico, Via Alvaro del Portillo, Rome, 200 - 00128, Italy. g.longo@unicampus.it.
BMC Musculoskeletal Disorders
|July 21, 2024
Summary
Artificial intelligence (AI) and machine learning (ML) can enhance knee replacement surgery by improving patient-specific risk predictions. This review explores AI/ML
Area of Science:
- Orthopedic Surgery
- Medical Informatics
- Artificial Intelligence
Background:
- Artificial intelligence (AI) and machine learning (ML) offer potential advancements in orthopedic procedures like total knee arthroplasty (TKA) and unicompartmental knee arthroplasty (UKA).
- These technologies can generate patient-specific risk models to improve decision-making and predict outcomes.
- Current applications and potential of AI/ML in TKA outcome prediction and risk identification require systematic evaluation.
Purpose of the Study:
- To systematically review and evaluate the application of AI/ML models in predicting TKA outcomes.
- To identify patient populations at higher risk for adverse outcomes following TKA.
- To assess the potential of AI/ML in enhancing patient-centered care in TKA.
Main Methods:
- An extensive literature search was conducted across MEDLINE, Scopus, Cinahl, Google Scholar, and EMBASE using the PIOS approach.
- The PRISMA guideline was followed for reporting, and a modified MINORS checklist was used for quality assessment.
- Data from 49 eligible articles, encompassing 2,595,780 patients, were analyzed, with studies screened from inception to June 2022.
Main Results:
- The most frequently identified AI/ML models were Random Forest (RF) (38.77%), Gradient Boosting Machine (GBM) (36.73%), Artificial Neural Network (ANN) (34.7%), Logistic Regression (LR) (32.65%), and Support Vector Machine (SVM) (26.53%).
- The average patient age was 70.2 ± 7.9 years.
- AI/ML models demonstrated potential for more accurate predictions and efficient data processing in TKA.
Conclusions:
- AI/ML models show significant promise for improving the accuracy of outcome prediction in total knee arthroplasty.
- These tools can streamline data analysis, reduce bias, and support personalized, risk-based patient care.
- Further research and application of AI/ML can lead to enhanced decision-making and improved patient outcomes in knee replacement surgery.
