Artificial Intelligence and Machine Learning in Prediction of Total Hip Arthroplasty Outcome: A Bibliographic Review

Abstract

This study investigates the current research trends on the adoption of artificial intelligence and machine learning techniques to predict the outcome of total hip arthroplasty (THA) or total hip replacement (THR) procedure using bibliometric analysis. A total of 102 publications from articles, review, and conference papers were included. The study analysed the network of authors, keywords, citations, and collaboration between authors on the application of artificial intelligence and machine learning to predict the outcome of THA. Regression-based and tree-based machine learning techniques were utilized in the majority of research because they are simpler to comprehend when there are elements involved in the prediction of results. All models had moderate to excellent (AUROC values from 0.71 to 0.97) discrimination ability in making the prediction.