Deciphering AMD by deep phenotyping and machine learning- PINNACLE
Principal Investigator: Professor Andrew Lotery
Approved Research ID: 45477
Approval date: May 29th 2019
Age-related-macular-degeneration (AMD) is a very common cause of blindness. Unfortunately, doctors don't know who will progress to the sight threatening stage of the disease. Some patients progress slowly or not at all and others quickly. We can teach computers to analyse high resolution images of the inside of the eye. We have access to hundreds of thousands of such images from patients with AMD and patients who don't have AMD. These images together with those from UK Biobank will form a training data set, allowing us to train computers to identify what eye changes appear in patients with AMD. Once the computers have learnt this, we expect they will identify new changes we haven't thought of. Using this approach we think we will be able to better predict which patients will progress. This should help us develop better treatments and enter the most appropriate patients into clinical trials. It should allow us to better understand why AMD develops too.