This article by Hidaka et al. examines the development and accuracy of an artificial intelligence (AI) system designed to predict the progression of hip osteoarthritis (OA). To evaluate the system’s performance, data from 361 patients with hip OA (each with a Kellgren-Lawrence [KL] grade of 0–2) were used. In total, 1,697 images were analyzed. The system was tasked with predicting whether individual patients would progress to a KL grade ≥3 over a period of 3, 4, or 5 years. Alongside the imaging data, the system was also provided with various patient metrics, such as height, sex, and body weight. The system's performance was assessed using sensitivity, specificity, and accuracy. For predicting OA progression within 3 years, the mean accuracy, specificity, and sensitivity were 81.8%, 88.0%, and 66.7%, respectively. For 4-year predictions, these values were 79.8%, 85.0%, and 71.6%. For 5-year predictions, the results were 78.5%, 80.4%, and 76.9%. Additionally, the area under the receiver operating characteristic curve (AUC) was calculated for each timeframe: 0.836 for both 3 and 4 years, and 0.846 for 5 years. Predicting the progression of OA remains a clinical challenge, but this AI model, despite being trained on a limited dataset, shows promising potential to support clinicians in making more informed decisions.