AI Predicts Osteoarthritis Progression with New X-Ray Tool

Researchers at the University of Surrey in the UK have developed an innovative artificial intelligence (AI) tool that can predict how a person’s knee X-ray will appear in one year. This advancement aims to significantly enhance the understanding and management of osteoarthritis, a degenerative joint disorder that affects over 500 million individuals worldwide and stands as the leading cause of disability among older adults.

The new AI technology provides both a visual forecast and a personalized risk score, enabling healthcare providers and patients to better grasp the disease’s progression. This system is noted for its speed and interpretability, outperforming earlier models and offering the potential to be adapted for other health conditions, such as lung and heart diseases.

Advanced Predictive Capabilities

The research, presented at the International Conference on Medical Image Computing and Computer Assisted Intervention in 2025, showcases a powerful AI model capable of generating realistic future X-rays alongside a personalized risk score. This dual output allows both doctors and patients to visualize how osteoarthritis may evolve over time. The model was trained on nearly 50,000 knee X-rays from approximately 5,000 patients, establishing it as one of the largest datasets of its kind.

This AI tool operates about nine times faster than similar technologies, demonstrating greater efficiency and accuracy. At its core is an advanced generative model known as a diffusion model, which creates a future version of a patient’s X-ray. It identifies 16 key points in the joint to monitor for potential changes, enhancing transparency by indicating the specific areas of the knee being tracked.

Impact on Patient Care and Communication

According to David Butler, the study’s lead author, “We’re used to medical AI tools that give a number or a prediction, but not much explanation. Our system not only predicts the likelihood of your knee getting worse — it actually shows you a realistic image of what that future knee could look like.” He further emphasizes the motivational aspect of comparing current and projected X-rays, stating, “Seeing the two X-rays side by side is a powerful motivator. It helps doctors act sooner and gives patients a clearer picture of why sticking to their treatment plan or making lifestyle changes really matters.”

The researchers believe this combination of speed and precision can facilitate quicker integration of the technology into clinical practice. As a result, clinicians will be better equipped to identify high-risk patients earlier and tailor their care accordingly.

Future applications of similar AI tools may include predicting lung damage in smokers or monitoring the progression of heart disease, potentially providing the same visual insights and early warnings that this system offers for osteoarthritis. The research underscores a promising shift in how healthcare providers communicate risks and enhance treatment strategies for osteoarthritic knee care and related conditions.

The findings were published in the journal Medical Image Computing and Computer Assisted Intervention, under the title “Risk Estimation of Knee Osteoarthritis Progression via Predictive Multi-task Modelling from Efficient Diffusion Model Using X-Ray Images.” Researchers are actively seeking collaborations to bring this technology into routine hospital and healthcare settings, aiming to improve patient outcomes on a broader scale.