AI Predicts Knee Osteoarthritis Progression with New Tool

Scientists at the University of Surrey in the United Kingdom have introduced an innovative artificial intelligence (AI) tool capable of predicting the future condition of a person’s knee X-ray. This development aims to enhance the tracking of osteoarthritis progression, a degenerative joint disorder that affects over 500 million people worldwide and stands as the leading cause of disability among older adults.

The AI tool provides both a visual forecast and a personalized risk score, thereby offering patients and healthcare professionals a clearer understanding of the disease’s trajectory. The research was recently presented at the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2025), showcasing the capabilities of this advanced system.

How the AI Tool Works

The newly developed AI model generates realistic “future” X-rays along with a risk score that estimates how osteoarthritis may progress. This approach not only visualizes potential changes but also enhances doctors’ and patients’ understanding of the disease. Trained on nearly 50,000 knee X-rays from approximately 5,000 patients, it is one of the largest datasets utilized for this purpose.

The system operates roughly nine times faster than similar AI tools, boasting improved efficiency and accuracy. At its core is a generative model known as a diffusion model, which creates a “future” X-ray version of a patient’s knee. The tool identifies 16 key points in the joint to highlight areas of concern, thereby increasing transparency and allowing clinicians to monitor specific regions effectively.

According to David Butler, the lead author of the study, the AI tool offers a significant advancement in medical AI technology. “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 explained.

Implications for Patient Care

The ability to visualize future conditions can serve as a powerful motivator for both doctors and patients. By comparing current and projected X-rays, patients can better understand the importance of adhering to treatment plans and making necessary lifestyle adjustments. Butler emphasized, “Seeing the two X-rays side by side… helps doctors act sooner and gives patients a clearer picture of why sticking to their treatment plan really matters.”

Beyond osteoarthritis, researchers envision similar AI tools could eventually predict lung damage in smokers or track the progression of heart disease, providing early warnings and visual insights for various conditions.

Currently, the research team is seeking collaborations to integrate this technology into clinical practices. The enhanced visibility offered by the AI tool can help clinicians identify high-risk patients earlier and personalize care in ways previously deemed impractical.

The findings feature in the journal Medical Image Computing and Computer Assisted Intervention, with the research paper titled “Risk Estimation of Knee Osteoarthritis Progression via Predictive Multi-task Modelling from Efficient Diffusion Model Using X-Ray Images.” This work represents a significant step forward in the use of AI for healthcare, potentially transforming how osteoarthritis and other conditions are managed.