Plain English Summary
Background and study aims
Regular injections of the drug aflibercept into the eye are the most common treatment option for neovascular (wet) age related macular degeneration (AMD) in the UK. Aflibercept treatment typically begins with three injections given at monthly intervals (loading dose), followed by regular review for up to and often beyond 2 years. It is clear that some patients respond to very well after the first three injections, with the retina being completely “dry” (that is without any retinal fluid in the subfoveal area). If the retina is completely dry, it is unlikely additional treatment can improve the visual outcome. In previous studies, it was suggested that these good responders account for about 35-40% of all patients in clinical trials. Recent data suggests that it might be as high as 50% as patients are now presenting earlier to retinal clinics. However, at present, it is impossible to predict the good responders to aflibercept treatment in order to provide patients with better information at the start of treatment. The aim of this study is to use artificial intelligence to evaluate markers of response. The accuracy of artificial intelligence to identify markers of response on optical coherence tomography (OCT) and OCT angiography (OCTA) will be compared to human graders.
Who can participate?
Patients aged 50 to 100 with new onset wet AMD being treated with the loading doses of aflibercept
What does the study involve?
The OCT and OCTA scans done to assess response to aflibercept treatment are collected and analysed by retinal specialists as well as by artificial intelligence.
What are the possible benefits and risks of participating?
The study may not be of benefit to the participant but it will provide better information to retinal specialists for the future management of patients. There is no risk to the participants as these tests are routinely done in the management of patients with AMD having treatment with aflibercept.
Where is the study run from?
Moorfields Eye Hospital (UK)
When is the study starting and how long is it expected to run for?
July 2019 to December 2021
Who is funding the study?
Who is the main contact?
Prof. Sobha Sivaprasad
Prof Sobha Sivaprasad
NIHR Moorfields Biomedical Research Centre
Moorfields Eye Hospital & UCL Institute of Ophthalmology
162 City Road
Can deep phenotyping using retinal images predict response to intravitreal aflibercept therapy in patients with neovascular age-related macular degeneration?
Can artificial intelligence predict treatment response with aflibercept for neovascular age-related macular degeneration better than human graders?
Approved 13/09/2019, London – Stanmore REC (Health Research Authority, Ground Floor, NRES/HRA, Skipton House, SE1 6LH, UK; Email: firstname.lastname@example.org), REC Ref: 19/LO/1385
Diagnostic accuracy study
Primary study design
Secondary study design
Patient information sheet
Not available in web format, please use contact details to request a patient information sheet
Wet age-related macular degeneration
The OCT and OCTA images taken at baseline and various time points until after the third aflibercept injection for wet AMD will be evaluated by retinal specialists and artificial intelligence to develop a prognostic model to define response to treatment. The total duration of observation is up to 20 weeks post first aflibercept injection.
Duration of follow-up is also up to a maximum of 20 weeks.
Primary outcome measure
Diagnostic accuracy of artificial intelligence over human graders in assessing the response of loading phase of intravitreal aflibercept injections for wet age-related macular degeneration
Secondary outcome measures
1. The analyses will be repeated excluding patients who appeared in the training set and the primary validation set
2. Performance of the AI will be evaluated using higher-quality images with no media opacity (eg, cataracts) as noted by professional graders
3. AUC subgroups will be computed stratified by age and sex, smoking or medical history
4. The analysis will be repeated by calculating the AUC, sensitivity, and specificity of the AI and the proportion of concordant and discordant eyes on the external validation datasets, compared with the reference standards
Overall trial start date
Overall trial end date
Reason abandoned (if study stopped)
Participant inclusion criteria
Inclusion criteria for both retrospective and prospective parts:
1. Adults who are ≥ 50 years and ≤ 100 years
2. Treatment naïve neovascular AMD at baseline
3. Media clarity, pupillary dilation and patient cooperation for adequate imaging
4. Ability to give informed consent
Inclusion criteria for retrospective part only in addition to the above:
1. Have received 3 loading injections of intravitreal aflibercept therapy at monthly intervals as per standard care
2. Review up to 10 weeks after the 3rd loading dose with or without injection at this visit
3. Had Heidelberg OCT at least at baseline and after the loading phase but ideally 4 Heidelberg OCTs for the 4 visits
4. Heidelberg OCTA images if available for baseline and any visit thereafter (2nd, 3rd or 4th visit) provided there is a baseline OCTA (optional criteria)
Target number of participants
Participant exclusion criteria
1. Co-existent ocular disease: any other ocular condition that, in the opinion of the investigator, might affect or alter visual acuity during the course of the study
2. Any patient who has opted out of their information being used for research nationally or locally at any site
Recruitment start date
Recruitment end date
Countries of recruitment
Trial participating centre
Moorfields Eye Hospital
162 City Road
Moorfields Eye Hospital
162 City Road
+44 (0)20 7253 3411 ext 2036
Boehringer Ingelheim Pharmaceuticals, Inc., BI, BIPI
Funding Body Type
private sector organisation
Funding Body Subtype
Trusts, charities, foundations (both publically funded and privately funded)
United States of America
Results and Publications
Publication and dissemination plan
The protocol will be published after ethics approval. Planned publication of the results in a high-impact peer-reviewed journal.
IPD sharing statement
The data sharing plans for the current study are unknown and will be made available at a later date.
Intention to publish date
Participant level data
To be made available at a later date
Basic results (scientific)