Reoperation is the most significant complication following any surgical procedure. Developing machine learning methods that predict the need for reoperation will allow for improved shared surgical decision making and patient-specific and preoperative optimisation. Yet, no precise machine learning models have been published to perform well in predicting the need for reoperation within 30 days following primary total shoulder arthroplasty (TSA). This study aimed to build, train, and evaluate a fair (unbiased) and explainable ensemble machine learning method that predicts return to the operating room following primary TSA with an accuracy of 0.852 and AUC of 0.91.
Keywords: TSA; fair and explainable machine learning; total shoulder arthroplasty.