Research datasets and clinical translation

We have secured funding and the appropriate approvals to build large, multimodal ophthalmic datasets using routinely collected clinical data in Manchester. These datasets will support the development and evaluation of the next generation of AI models in ophthalmology and oculomics.

A pilot project with Born in Bradford is exploring the feasibility of ophthalmic imaging within an established population cohort. The pilot provides an opportunity to understand how imaging can be collected effectively and acceptably in a prospective research setting.

For AI to improve care, technical performance is only one part of the problem. Models must address meaningful clinical questions, perform reliably in relevant populations, and fit safely into real healthcare pathways.

My work therefore combines methodological development with prospective evaluation, patient involvement, information governance, and collaboration between clinicians, academics, and industry partners.