AI Predicts Osteoarthritis Progression with New Imaging Tool

Scientists from the University of Surrey in the UK have introduced an innovative artificial intelligence tool capable of predicting how a person’s knee X-ray will appear in one year. This advancement aims to improve the tracking of osteoarthritis progression, a degenerative joint disorder affecting over 500 million people globally and recognized as the leading cause of disability among older adults.

The new AI tool delivers both a visual forecast and a risk score, enhancing the understanding of the disease for both doctors and patients. Presented recently at the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2025), this technology stands out for being faster and more interpretable than previous systems.

How the AI Works

The researchers have developed a robust AI model that generates realistic “future” X-rays alongside a personalized risk score that estimates the progression of osteoarthritis. These outputs provide a visual roadmap, enabling doctors and patients to anticipate how the condition may evolve over time.

Trained on nearly 50,000 knee X-rays from about 5,000 patients, this model is one of the largest datasets of its kind. It predicts disease progression approximately nine times faster than comparable AI tools, boasting greater efficiency and accuracy.

At the heart of this system is an advanced generative model referred to as a diffusion model. This technology creates a “future” version of a patient’s X-ray and identifies 16 key points in the joint, highlighting areas of potential change. The model’s transparency is a significant feature, as it allows clinicians to see precisely which parts of the knee are being monitored, fostering confidence in the AI’s predictions.

Impact on Patient Care

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.”

Butler emphasizes the motivational aspect of comparing two X-rays side by side — one from the present and one projected for next year. This visual comparison can encourage doctors to intervene sooner and helps patients grasp the importance of adhering to treatment plans or making necessary lifestyle changes. “We think this can be a turning point in how we communicate risk and improve osteoarthritic knee care and other related conditions,” he adds.

The researchers are optimistic that similar AI tools could one day be adapted to predict lung damage in smokers or track the progression of heart disease. This would provide comparable visual insights and early warnings, similar to those offered for osteoarthritis.

The research team is actively seeking collaborations to integrate this technology into hospitals and everyday healthcare settings. Enhanced visibility through this AI tool could enable clinicians to identify high-risk patients sooner and customize their care in ways that were not previously feasible.

The full study is 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.”