An overview of artificial intelligence and machine learning in shoulder surgery
1Department of Orthopedic Surgery, Seoul St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, Korea.
Clinics in Shoulder and Elbow
|May 23, 2025
Summary
Machine learning (ML) enhances orthopedic surgery by improving predictions for shoulder arthroplasty and rotator cuff tears (RCTs). This AI application optimizes surgical planning, diagnosis, and patient outcomes.
Area of Science:
- Orthopedic Surgery
- Artificial Intelligence
- Machine Learning
Background:
- Machine learning (ML), a subset of artificial intelligence (AI), offers advanced algorithms for pattern recognition and prediction from data.
- ML is increasingly transforming orthopedic surgery, particularly in managing shoulder arthroplasty and rotator cuff tears (RCTs).
Purpose of the Study:
- To review the fundamental paradigms of ML (supervised, unsupervised, reinforcement learning) and their applications in orthopedic surgery.
- To explore ML's role in shoulder arthroplasty for predicting outcomes, complications, and guiding implant selection.
- To examine ML's utility in diagnosing and managing RCTs, including predicting reparability and functional recovery.
Main Methods:
- Review of ML paradigms including supervised, unsupervised, and reinforcement learning.
- Analysis of ML algorithms like XGBoost, neural networks, and generative adversarial networks.
- Evaluation of ML model performance in predicting surgical outcomes, diagnostic accuracy, and functional recovery.
Main Results:
- ML models achieve over 90% accuracy in predicting orthopedic complications and demonstrate high diagnostic accuracy (AUC > 0.90) for RCTs using deep learning.
- ML aids in personalized surgical planning for shoulder arthroplasty, optimizing implant selection and predicting outcomes.
- ML models accurately predict RCT reparability (85%) and postoperative functional outcomes, including range of motion and patient-reported measures.
Conclusions:
- ML significantly enhances diagnostic accuracy and predictive capabilities in managing shoulder arthroplasty and RCTs.
- ML facilitates data-driven, personalized treatment strategies, optimizing surgical planning and improving patient outcomes in orthopedics.
- Challenges in data variability, interpretability, and clinical integration remain, with future directions including federated learning and explainable AI.
