AI Predicts Osteoarthritis Progression with New Imaging Tool

Scientists at the University of Surrey in the UK have developed an innovative AI tool that forecasts the future condition of a person’s knee X-ray, specifically aimed at tracking the progression of osteoarthritis. This degenerative joint disorder affects more than 500 million people worldwide and is the leading cause of disability among older adults. The new AI model provides a visual forecast alongside a risk score, enhancing both doctors’ and patients’ understanding of the disease.

The research was unveiled at the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2025). The team presented a powerful AI model that generates realistic “future” X-rays and calculates a personalized risk score to estimate the speed of disease progression. Together, these outputs offer a clear roadmap for both patients and clinicians, demonstrating how osteoarthritis may evolve over time.

One of the standout features of the new AI tool is its speed and efficiency. Trained on nearly 50,000 knee X-rays from about 5,000 patients, it can predict disease progression approximately nine times faster than existing AI tools. The system employs a sophisticated generative model known as a diffusion model, which creates a “future” version of the patient’s X-ray by identifying 16 key points in the knee joint. This capability not only enhances the interpretability of the AI’s predictions but also helps clinicians understand which areas are being monitored for potential changes.

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.” He emphasized that visualizing the current and predicted states of the knee side by side serves as a powerful motivator. It encourages doctors to intervene sooner and provides patients with a compelling reason to adhere to their treatment plans or consider necessary lifestyle changes.

The implications of this research extend beyond osteoarthritis. The researchers suggest that similar AI technologies could one day predict lung damage in smokers or monitor the progression of heart disease, delivering early warnings and visual insights into various health conditions. The team is currently seeking collaborations to integrate this advanced technology into hospitals and everyday healthcare practices.

This enhanced visibility allows clinicians to identify high-risk patients sooner and tailor their care more effectively than ever before. The findings have been 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.”

Dr. Tim Sandle, the Editor-at-Large for science news at Digital Journal, highlights the significance of this advancement in medical imaging and AI, noting its potential to revolutionize patient care in osteoarthritis and beyond.