Interpretable Machine Learning-Based Differential Diagnosis of Hip and Knee Osteoarthritis Using Routine Preoperative Clinical and Laboratory Data

Osteoarthritis (OA) of the hip (coxarthrosis) and knee (gonarthrosis) is a leading cause of disability worldwide. Differential diagnosis typically relies on imaging modalities such as X-rays and Magnetic Resonance Imaging (MRI). However, advanced imaging can be expensive and inaccessible, highlighting the need for non-invasive diagnostic tools. This study aimed to develop and validate an interpretable machine learning model to distinguish between hip and knee osteoarthritis using standard preoperative clinical and laboratory data. This model is designed to assist physicians in prioritizing whether to order a hip or a knee X-ray first, thereby saving time and medical resources. The study utilized retrospective data from 1792 patients treated at the City Clinical Hospital in Almaty, Kazakhstan. After applying inclusion and exclusion criteria, five machine learning algorithms were used for training and evaluation: Decision Tree, Random Forest, Logistic Regression, XGBoost, and CatBoost. SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) were employed to interpret predictions and determine the contribution of each feature. The XGBoost model demonstrated the best performance, achieving an accuracy of 93.85%, a precision of 95.15%, a recall of 90.51%, and an F1-score of 92.41%. SHAP analysis revealed that age, glucose and leukocyte levels, urea, and BMI made the greatest contributions to the model’s predictions, while local analysis using LIME indicated that age, leukocyte levels, glucose, erythrocytes, and platelets were the most influential features. These findings support the use of machine learning for cost-effective early osteoarthritis triage using routine preoperative data.