AI Tool Revolutionizes Osteoarthritis Predictions for Patients

Researchers at the University of Surrey in the UK have developed a cutting-edge artificial intelligence (AI) tool that can predict the appearance of a person’s knee X-ray a year in advance, significantly aiding in the tracking of osteoarthritis progression. This degenerative joint condition affects over 500 million people worldwide and remains the leading cause of disability among older adults.

The innovative system offers both a visual forecast and a personalized risk score, enhancing the understanding of disease progression for both doctors and patients. This technology operates faster and with greater interpretability than previous models, with plans for future expansion to predict other conditions, such as lung and heart disease. The research was recently unveiled at the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2025).

Transformative AI Model for Osteoarthritis

The newly developed AI model generates realistic “future” X-rays alongside a risk score that estimates the progression of osteoarthritis. These outputs provide clinicians and patients with a visual roadmap of how the disease may evolve. Trained on nearly 50,000 knee X-rays from approximately 5,000 patients, this model represents one of the largest datasets utilized for this purpose, predicting disease progression roughly nine times faster than comparable AI tools.

Central to the system is an advanced generative model known as a diffusion model. This model creates a “future” version of a patient’s X-ray while identifying 16 key points in the joint to monitor potential changes. This transparency allows clinicians to see which parts of the knee are being observed, fostering greater confidence in the AI’s predictions.

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.”

Enhancing Patient Care through Visual Insights

The ability to juxtapose current and predicted X-rays serves as a powerful motivator for both doctors and patients. Butler emphasizes that viewing these images side by side can prompt healthcare providers to act more decisively and helps patients understand the importance of adhering to treatment plans and making necessary lifestyle changes.

The researchers believe this advancement could transform the communication of risk associated with osteoarthritis and related conditions. The AI’s capabilities may one day extend to predicting lung damage in smokers or monitoring heart disease, providing similar visual insights and timely warnings.

In light of this, the research team is actively seeking collaborations with healthcare facilities to integrate this technology into routine clinical practice. Enhanced visibility into disease progression will enable clinicians to identify high-risk patients sooner and tailor their care in ways that were previously impractical.

The findings of this groundbreaking research are 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.” This innovative tool represents a significant step forward in the management of osteoarthritis and potentially other chronic conditions, promising to improve outcomes for millions of patients globally.