Machine Learning in nAMD

  • Research type

    Research Study

  • Full title

    Machine Learning for Personalised Medicine in Neovascular Age-related Macular Degeneration

  • IRAS ID

    264359

  • Contact name

    Konstantinos Balaskas

  • Contact email

    k.balaskas@nhs.net

  • Sponsor organisation

    Moorfields Eye Hospital NHS Foundation Trust

  • Duration of Study in the UK

    1 years, 0 months, 1 days

  • Research summary

    Age-related Macular Degeneration is the main cause of vision loss in the UK. Although there are effective treatments in the form of eye injections, there are many factors affecting how well patients respond to these treatments. Not all these factors are well understood and especially how they interact with each other and how this can help predict treatment response. The main three sources of information that can help clinicians predict response to treatment and adjust the treatment regimen to the specific needs of each patient are: clinical information (such as age, vision), details from imaging tests (such as optical coherence tomography) and the genetic make-up of each patient. Novel methods of Artificial Intelligence for analysing complex information can help make sense of all this data and single out the factors that can help tailor treatments to the needs of each patient. One such method is Machine Learning. In this project we will collect clinical and imaging

    information from patients already attending Moorfields clinics for treatment of Neovascular AMD (nAMD) with injections. We will additionally collect a blood sample from each patient for genetic testing. We will use novel methods for analysing images and exporting detailed information from them. We will then feed all this information into a Machine Learning tool that we will develop. This will help make sense of all this complex information and reveal which factors play a key role in how our patients respond to treatment. The project will allow using Artificial Intelligence to ‘personalise’ our treatments for patients with nAMD and give accurate predictions for the outcomes of treatment in terms of vision.
    This project will pilot the development of an Artificial Intelligence pipeline. It will help to show that developing a large dataset of clinical, imaging and genetic data in a form that is suitable for Machine Learning can lead to exciting new insights into the disease behaviour and allow ‘personalising’ patient care. It will act as proof-of-concept, applied on nAMD at a first stage. At a later stage, the research team will seek funding to develop a comprehensive Artificial Intelligence pipeline. This will involve many eye conditions beyond nAMD, with emphasis on high-volume disease, and will utilise the extensive datasets available within Moorfields in order to develop Artificial Intelligence tools for personalising care, tailoring it to the needs of each individual patient.

  • REC name

    South Central - Berkshire B Research Ethics Committee

  • REC reference

    19/SC/0337

  • Date of REC Opinion

    21 Jun 2019

  • REC opinion

    Favourable Opinion