Data Use Application 015
Lead applicant organisation name
Name of the legal entity that signs the contract to access the data.
University College London; Moorfields Eye Hospital NHS Foundation Trust. Lead applicant: Ariel Ong, Doctoral Fellow, Honorary Clinical Fellow and Research student PhD
Project title
The title of the project/research study request that the applicant is investigating through the use of health data.
Benchmarking Human and Artificial Intelligence Model Performance for Retinal Disease
Lay summary
A concise and clear description of the project. This should outline the problem, objective and the expected outcomes in language that is understandable to the general public.
Millions of people around the world suffer from serious vision loss due to retinal diseases like age-related macular degeneration. Early and accurate diagnosis is critical for preventing vision loss. However, current methods of diagnosis are not perfect. There can be differences in how various doctors interpret retinal images, and experts can sometimes make mistakes. These diagnostic errors, ambiguity, and variability can lead to delays or errors in treatment.
This project aims to explore whether and how artificial intelligence (AI) can help clinicians diagnose retinal diseases more quickly, accurately, and consistently. We will use securely stored, anonymised patient data from Moorfields Eye Hospital to conduct our research.
We will compare the performance of human experts, AI systems, and a combination of both when interpreting different types of retinal images. By simulating a clinical environment, we plan to study how AI can best support doctors in making diagnoses. Our research will pay special attention to when and why diagnostic errors occur and how much opinions differ between clinicians. We will also investigate potential challenges that might arise from using AI, such as clinicians relying too much on computer recommendations or differences in how doctors use these recommendations. Understanding these issues is essential to ensure that any new tool is both safe and effective. This will help us understand whether AI can help reduce these errors and improve the interpretation of images, particularly in complex cases.
Public benefit statement
A description in plain English of the anticipated outcomes, or impact of project on the general public.
The anticipated impact of this work is significant. We will determine whether and how AI can help clinicians to detect retinal diseases earlier and more reliably. This will improve patient care by preserving vision and could also inform guidelines for integrating AI tools into everyday eye care practice. Our findings may also help pave the way for AI-assisted diagnosis in other areas of medicine, supporting doctors with robust, real-world decision-making tools that enhance overall patient care.
Latest approval date
The last date the data access request for this project was approved by a data custodian.
15 May 2025
Dataset(s) name
The name of the dataset(s) being accessed.
Bespoke: macular OCT imaging dataset
Access type
Determines whether the data will be accessed with an Trusted Research Environment (TRE) or via data release.
Data provisioned to the research applicant through INSIGHT's Secure Research Environment.
Data sensitivity level
The level of identifiability of the data being accessed, as defined by Understanding Patient Data.
Anonymised