Research examples

Here we list a selection of academic papers and research projects that apply advanced analytics, including machine learning and artificial intelligence, to ophthalmic datasets for patient benefit. Many of these examples involve members of the INSIGHT team or our partners. Some links are to external sites.

​​​​

Alzheimer’s​

​

• Artificial intelligence and machine learning for Alzheimer’s disease: let’s not forget about the retina (January 2021)
   

• Insights into Systemic Disease through Retinal Imaging-Based Oculomics (April 2020)​​
   

 

Artificial Intelligence and machine learning

​​​​​

• Foundation models in ophthalmology (BMJ, 2024)

 

• A foundation model for generalised disease detection using retinal images (Nature, 2023)

​​​

• A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis (The Lancet Digital Health, 2019)
  ​

• Reporting guidelines for clinical trials evaluating artificial intelligence interventions are needed (Nature Medicine, 2019)
  ​

• Reinventing the eye exam (The Lancet, 2019)

Regulatory reports on Artificial Intelligence as a Medical Device:
 

• Software and artificial intelligence (AI) as a medical device (Guidance from the Medicines and Healthcare products Regulatory Agency [MHRA], updated July 2024)
   

• The Regulation of Artificial Intelligence as a Medical Device (publishing.service.gov.uk) This report was led by Alastair Denniston with support from Parag Vyas on behalf of the RHC142 and supported by a team of Civil Servants within BEIS. Key contributors from the BEIS team were Katie Francis, Cara Nicol and Tanuj Jain. (Report published 2022)

 

Cataracts

​

• Artificial Intelligence for Cataract Detection and Management (March 2020)

 

Covid-19

​

• See details of a Covid-19-related dataset from INSIGHT on the HDR Innovation Gateway
   

Diabetic retinopathy

​

Here are examples of research using eye datasets to investigate the effectiveness of current treatments and the potential for new screening techniques powered by artificial intelligence:

​​

• Integrated image-based deep learning and language models for primary diabetes care (Nature Medicine, 2024)
   

• An open-source data set of anti-VEGF therapy in diabetic macular oedema patients over 4 years and their visual acuity outcomes (June 2020)

​

Glaucoma

​

• A CNN-aided method to predict glaucoma progression using DARC (Detection of Apoptosing Retinal Cells) (May 2020)
   

• Artificial Intelligence Algorithms to Diagnose Glaucoma and Detect Glaucoma Progression: Translation to Clinical Practice (November 2020)
   

• The potential application of artificial intelligence for diagnosis and management of glaucoma in adults​ (June 2020)

 

Health data poverty

​

• ​Equity in medical devices: independent review - final report (2024). Highlights STANDING Together as a tool for dataset curators, developers, and regulators to ensure data diversity. STANDING Together is an initiative led by colleagues at University Hospitals Birmingham NHS Foundation Trust and University of Birmingham, including INSIGHT Strategic Advisor Alastair Denniston.
   

• ‘A Global Review of Publicly Available Datasets for Ophthalmic Imaging: Recognising Barriers to Access, Usability and Generalisability’ (October 2020)

 

Personalised medicine

​

• ‘Delivering personalized medicine in retinal care: from artificial intelligence algorithms to clinical application’ (September 2020)

​

Retinal disease​

​

• Artificial Intelligence to Facilitate Clinical Trial Recruitment in Age-Related Macular Degeneration (Ophthalmology Science, 2024)​

​

• Clinically relevant deep learning for detection and quantification of geographic atrophy from optical coherence tomography: a model development and external validation study (Gongyu Zhang, Dun Jack Fu, Bart Liefers, Livia Faes, Sophie Glinton, Siegfried Wagner et al., The Lancet Digital Health, September 2021)
   

• Predicting wet age-related macular degeneration (AMD) using DARC (detecting apoptosing retinal cells) AI (artificial intelligence) technology (December 2020)
   

• OCT-based deep learning algorithm for the evaluation of treatment indication with anti-vascular endothelial growth factor medications (January 2018)
   

• Prediction of Causative Genes in Inherited Retinal Disorders from Spectral-Domain Optical Coherence Tomography Utilizing Deep Learning Techniques (April 2019)
   

• Fully automated detection of retinal disorders by image-based deep learning (January 2019)
   

• Eye2Gene - a web app to assist genetic diagnosis of inherited retinal disease with artificial intelligence
  (project led by Nikolas Pontikos of UCL Institute of Ophthalmology and Moorfields Eye Hospital Reading Centre)
   

• Using AI in new ways to investigate retinal diseases (project funded by Moorfields Eye Charity from October 2019)

​​