Artificial intelligence is rapidly transforming healthcare, particularly in diagnostic imaging and predictive analytics. As digital health services expand worldwide, AI-driven tools are helping clinicians detect diseases earlier, improve patient engagement, and support more personalized treatment strategies.
Researchers at the University of Surrey have developed an AI-powered system that predicts how a patient’s knee joint may deteriorate due to osteoarthritis. The technology uses machine learning models to generate a realistic knee X-ray projection up to one year into the future, along with a clinical risk score estimating disease progression.
Osteoarthritis affects more than 500 million people globally, according to the Global Burden of Disease Study, and remains a leading cause of disability among older adults. Early detection and preventive care are key to reducing long-term healthcare costs and improving patient quality of life.
The Surrey team trained the system using nearly 50,000 knee X-rays from around 5,000 patients. Researchers report that the system improved prediction accuracy compared to several existing methods while operating faster and with lower computational complexity, supporting potential clinical adoption.
Unlike traditional medical AI tools that mainly provide numerical risk predictions, the system produces visual projections showing side-by-side comparisons of current and predicted X-rays. Built on diffusion-based generative AI, it also highlights 16 structural knee points most likely to deteriorate, improving explainability and supporting clinical validation.
