Prediction of Change in Pelvic Tilt After Total Hip Arthroplasty Using Machine Learning

Abstract

BackgroundA postoperative change in pelvic flexion following total hip arthroplasty (THA) is considered to be one of the causes of dislocation. This study aimed to predict the change of pelvic flexion after THA integrating preoperative and postoperative information with artificial intelligence. MethodsThis study involved 415 hips which underwent primary THA. Pelvic flexion angle (PFA) is defined as the angle created by the anterior pelvic plane and the horizontal/vertical planes in the supine/standing positions, respectively. Changes in PFA from preoperative supine position to standing position at 5 years after THA were recorded and which were defined as a 5-year change in PFA. Machine learning analysis was performed to predict 5-year change in PFA less than −20° using demographic, blood biochemical, and radiographic data as explanatory variables. Decision trees were constructed based on the important predictors for 5-year change in PFA that can be handled by humans in clinical practice. ResultsAmong several machine learning models, random forest showed the highest accuracy (area under the curve = 0.852). Lumbo-lordotic angle, femoral anteversion angle, body mass index, pelvic tilt, and sacral slope were most important random forest predictors. By integrating these preoperative predictors with those obtained 1 year after the surgery, we developed a clinically applicable decision tree model that can predict 5-year change in PFA with area under the curve = 0.914. ConclusionA machine learning model to predict 5-year change in PFA after THA has been developed by integrating preoperative and postoperative patient information, which may have capabilities for preoperative planning of THA.