Machine learning for early and personalised risk assessment for pathological myopia

This project aims to assess if vascular analysis in retinal images can be used for personalised and early myopic degeneration/pathological myopia risk prediction. The retinal image data will be combined with clinical measurements of refractive error to develop a comprehensive AI based model that evaluates the risk of irreversible vision loss due to pathological myopia.

The primary aim of this project is to enable the development of a risk assessment tool to facilitate early and personalised interventions for pathological myopia using non-invasive imaging of the eye. The technology that will be developed will have direct translational applications for risk assessment in various other diseases including retinal disorders, glaucoma, Alzheimer.

This project directly aligns with two themes of EPSRC: (i) AI and data-science for engineering, health, and government (ASG); (ii) Clinical technologies. This project has the potential to reduce irreversible blindless caused by refractive error by identifying patients who are at a higher risk and providing more rigorous myopia management.