An AI that predicts what a person’s knee X-ray will look like in a year, helping track osteoarthritis progression, has been developed. The tool, which comes from researchers at the University of Surrey, provides both a visual forecast and a risk score, offering doctors and patients a clearer understanding of the disease.
The technology is faster and more interpretable than earlier systems and it could soon expand to predict other conditions like lung or heart disease.
Tackling the disease
Osteoarthritis, a degenerative joint disorder that affects more than 500 million people globally, is the leading cause of disability among older adults. The main symptoms of osteoarthritis are joint pain and stiffness, and problems moving the joint.
Selecting AI
Central to the AI system is an advanced generative model known as a diffusion model. It creates a “future” version of a patient’s X-ray and identifies 16 key points in the joint to highlight areas being tracked for potential changes. This feature enhances transparency by showing clinicians exactly which parts of the knee the AI is monitoring, helping build confidence and understanding in its predictions.
Training AI
The AI system was trained on nearly 50,000 knee X-rays from about 5,000 patients, making it one of the largest datasets of its kind. It can predict disease progression roughly nine times faster than similar AI tools and operates with greater efficiency and accuracy.
The researchers believe this combination of speed and precision could help integrate the technology into clinical practice more quickly.
According to lead researcher David Butler: “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 adds: “Seeing the two X-rays side by side — one from today and one for next year — 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. We think this can be a turning point in how we communicate risk and improve osteoarthritic knee care and other related conditions.”
Going forwards
Similar AI tools might one day predict lung damage in smokers or track the progression of heart disease, providing the same kind of visual insights and early warning that this system offers for osteoarthritis.
The research was presented at the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2025). The research also appears in the journal Medical Image Computing and Computer Assisted Intervention, titled “Risk Estimation of Knee Osteoarthritis Progression via Predictive Multi-task Modelling from Efficient Diffusion Model Using X-Ray Images.”
