Accuracy of Key Sonographic Markers for Juxta-Articular Fractures: A Prospective Study Using Explainable Machine Learning

The authors aimed to evaluate the diagnostic accuracy of sonographic features for juxta-articular fractures and identify key predictors using machine learning techniques. They found that a triad of features—subperiosteal hematoma, arc-shaped fracture end, and heterogeneous intra-articular effusion—provided high diagnostic accuracy, with a sensitivity of 93.0% and specificity of 97.2%, demonstrating strong agreement with CT results. This radiation-free approach could enhance early screening and triage for suspected fractures.