AI Predicts Knee Osteoarthritis Progression for Better Care

Scientists at the University of Surrey in the UK have developed an innovative artificial intelligence (AI) tool that predicts how a person’s knee X-ray may change over the course of a year. This advancement aims to improve the management of osteoarthritis, a degenerative joint disease that affects more than 500 million individuals globally and is the leading cause of disability among older adults.

Enhancing Understanding of Osteoarthritis Progression

The newly created AI technology not only generates a visual forecast of future knee conditions but also provides a risk score. This dual approach helps both doctors and patients better comprehend the progression of osteoarthritis. The tool was introduced at the International Conference on Medical Image Computing and Computer Assisted Intervention in March 2025, showcasing its potential to transform clinical practices.

This advanced AI model creates realistic representations of future X-rays, complemented by a personalised risk score that estimates the likelihood of disease progression. The researchers trained the system on nearly 50,000 knee X-rays sourced from around 5,000 patients, making it one of the most extensive datasets for this purpose. The AI operates approximately nine times faster than its predecessors, with enhanced efficiency and accuracy.

At the heart of this system is a sophisticated generative model known as a diffusion model. This technology not only produces a “future” X-ray but also identifies 16 key points in the knee joint, highlighting areas that may be subject to changes. By doing so, it enhances transparency and allows clinicians to understand precisely which regions the AI is monitoring, fostering confidence in its predictions.

Transforming Patient Care and Communication

According to David Butler, the lead author of the study, “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 that the ability to view two X-rays side by side—one from the present and one projected for the next year—serves as a compelling motivator for both doctors and patients.

Butler further noted that this visual representation can encourage patients to adhere to their treatment plans or implement lifestyle changes, ultimately improving outcomes. “We think this can be a turning point in how we communicate risk and enhance osteoarthritic knee care and other related conditions,” he added.

The implications of this technology extend beyond osteoarthritis. Researchers envision that similar AI models could one day predict conditions such as lung damage in smokers or track the progression of heart disease. By offering visual insights and early warnings, this technology could significantly enhance patient monitoring and care.

Currently, the researchers are exploring collaborations to integrate this tool into hospitals and routine healthcare practices. The increased visibility it provides helps clinicians identify high-risk patients earlier and tailor their care more effectively than previously possible. The findings of this research are detailed in the journal Medical Image Computing and Computer Assisted Intervention, under the paper titled “Risk Estimation of Knee Osteoarthritis Progression via Predictive Multi-task Modelling from Efficient Diffusion Model Using X-Ray Images.”

This groundbreaking research represents a significant leap forward in understanding and managing osteoarthritis, which could ultimately lead to better patient outcomes and more informed decision-making in clinical settings.