Creative Commons source reading · Machine learning for performance
Artificial intelligence algorithms in orthopaedics: A narrative review of methods and clinical applications
Jamie Rosen; Jemima Russell; Prerna Kartik; Martinique Vella‐Baldacchino
Originally published in J Exp Orthop · 2025-10-01
From the article
Selected source text. JournalOS removes markup and shortens excerpts where indicated. The full article provides the complete context.
Abstract
AbstractThis narrative review evaluates the role of artificial intelligence (AI) algorithms in orthopaedic surgery and distinguishes itself by explaining how the main algorithmic approaches function and illustrating each with orthopaedic examples. Machine learning methods, including regression, classification and reinforcement learning, have been applied to fracture detection, prediction of revision risk and modelling of outcomes after arthroplasty and sports injury. Deep learning and convolutional neural networks have improved fracture classification, implant surveillance and segmentation of cartilage and meniscal tissue on magnetic resonance imaging. Neural networks such as FracNet and YOLO‐based systems demonstrate growing capability in trauma imaging. Natural language processing has automated the extraction of operative and…
DISCUSSION
AI is reshaping orthopaedic workflows, with the most rapid progress in imaging interpretation, operative planning and outcome prediction. In fracture detection and arthroplasty imaging, models have demonstrated performance comparable to that of subspecialist clinicians. However, findings remain inconsistent, reflecting differences in data sets, fracture types and modelling approaches [29, 47, 57, 67]. ChatGPT‐4o recently showed strong binary discrimination in knee osteoarthritis radiographs (F1 = 0.88) but poor grading accuracy (AI [35% correct] vs. surgeons [89.6% correct]), highlighting inconsistencies in AI radiographic classification [113]. Progress will depend on the use and validation of representative orthopaedic training data. Recent reporting frameworks TRIPOD+AI, PROBAST+AI and DECIDE−AI can help ensure such studies are…
CONCLUSION
AI is reshaping orthopaedics. It not only improves imaging interpretation and predictive modelling but also helps ease clinical and administrative burdens. While studies have shown better diagnostic accuracy and more efficient workflows, this progress is not without challenges. Bias remains a concern. Transparency is often limited, and stronger rules and oversight are needed for safe implementation. AI should be viewed as a tool to complement a surgeon and support decision‐making when integrated appropriately. With proper testing, responsible rollout and collaboration between experts, it has the potential to raise the standard of patient care in orthopaedics and beyond. Achieving this will require ongoing evaluation and shared accountability.
Editorial reading guide
- What data created and tested the model, and was evaluation independent?
- What is the cost of a false positive, false negative or out-of-distribution decision?
