Machine Learning in the Analysis of Hip Osteoarthritis and Total Hip Arthroplasty Gaits: A Systematic Review

An accurate diagnosis of Hip Osteoarthritis (HOA) and prediction of Total Hip Arthroplasty (THA) outcomes is crucial for reliable treatment decision-making and rehabilitation strategy. Gait analysis (GA) is commonly employed for gait disorders examination in clinical settings but is still limited due to the enormous size of data and accuracy. Machine Learning (ML) methodology has seen rapid growth in the past decade but its development in the context of HOA and THA GA has not been previously examined. The aim of this review is to evaluate the literature in the use of ML frameworks for GA of HOA and THA subjects. Five databases namely PubMed, Embase, IEEE Xplore, ACM Digital Library, and Scopus were searched in accordance to PRISMA framework. Relevant publications published until May 2025 were retrieved and information on reliability, applicability, and interpretability were extracted for quality assessment. Nineteen studies were selected, with fourteen articles focused on classification and five articles on outcome prediction. Eight classification studies utilized kinematic features with two employing Deep Learning (DL) methods. Four outcome prediction articles utilized spatio-temporal parameters and mostly focused on post-THA gaits. Scarce datasets, small sample size, and limited design explanation are the main hindrances revealed in the quality assessment. Nevertheless, this review demonstrated the recent uptrend in the utilization of ML techniques and evidently improved applicability through consensus on the important gait features for HOA and post-THA gait analysis. Reliability and interpretability are still major concerns before ML models are widely accepted by medical practitioners. It is recommended that future re search should take into account dataset quality and transparent validation protocol, model interpretability, and results explainability.