Eleanor Bolton

Research Topic: Interpretable AI/ML of clinical, blood and imaging biomarkers to predict arthritis development in individuals at risk of rheumatoid arthritis

Supervisors: Georgios Aivaliotis, Andy Bulpitt, Kulveer Mankia

About Eleanor: I graduated from the University of Oxford with a first class degree in Cells and Systems Biology. My final year project involved investing the effect of light exercise on lung inhomogeneity, using a computational model of the lungs. I then worked as a Data Analyst for two years in industry, whilst competing at an international level in athletics and cross country running.

Project Description: Rheumatoid Arthritis is a chronic autoimmune disorder affecting approximately 18 million people globally in 2020, with higher prevalence among women and older adults. By 2050, RA prevalence is expected to rise to 31.7 million, particularly in developed countries where risk factors like obesity and smoking are more common. Early detection and intervention are crucial to managing RA and preventing long-term complications. However, traditional diagnostic tools, including imaging and serological markers, often struggle to identify those at risk during the early stages.

With advancements in artificial intelligence, there is potential to improve risk prediction for RA progression. My research focuses on developing DL models using multimodal data from the Leeds Anti-CCP+ cohort to enhance risk prediction in individuals predisposed to RA. This approach aims to support earlier intervention, ultimately improving patient outcomes and addressing the increasing burden of RA globally.