A-EYE: A Mixed Quantitative and Qualitative Study to Develop and Evaluate the Application of Artificial Intelligence (AI) Methods Using Retinal Imaging for the Identification of Adverse Retinal Changes Associated With Cancer Therapies. (A-EYE)

This is a data collection study involving the gathering of clinical data and OCT (optical coherence tomography) scans from 350 patients.

The purpose of this study is to gather data to help develop an AI algorithm to detect eye abnormalities specifically those related to certain cancer treatments.

At the end of the study interviews will be held with expert ophthalmologists to assess the acceptability of implementing AI into clinical practice.

Study Overview

• Status: Recruiting
• Conditions: All Comers
• Intervention / Treatment: Other: No Intervention

Detailed Description

Many cancer patients will access new treatments through clinical trials. These treatments have often never been tested in humans and therefore, are likely to have unknown side effects. Some of these side effects include changes to the eye, such as blindness.

Ahead of patients taking part in these trials there is often little planning done to manage potential side effects on the eye. Additionally, accessing the expertise of eye specialists is not always available and often referral to a specialist is only given when eye symptoms have become advanced. These delays in identifying side effects on the eye also delays treatment and follow-up management. Providing patients access to this expertise would help in the detection and management of treatment side effects, however, due to demands on resources this access is not always readily available.

The aim of this study is to create an artificial intelligence (AI) program that can detect changes to the eye related to disease, which, in the future, can be specifically used in cancer patient care. Additionally, developing an AI program to detect cancer related side effects to the eye will go a significant way in easing the burden on the health care system and improve side effects from new cancer treatments.

This study will involve the collection of eye scans and medical data from participants at the Manchester Royal Eye Hospital. These will then be used to develop AI methods to detect changes in the eye related to those seen by patients on cancer treatment. The AI will then be compared with the assessments of eye specialists to assess if they give similar results.

• Study Type: Observational
• Enrollment (Anticipated): 350

Contacts and Locations

• Study Contact: Name: Tariq Aslam; Phone Number: 0161 276 1234; Email: tariq.aslam@manchester.ac.uk

Study Locations

• United Kingdom
  • Manchester, United Kingdom
    • Recruiting
    • Manchester Royal Eye Hospital
    • Contact: Tariq Aslam; Email: tariq.aslam@manchester.ac.uk

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years and older (Adult, Older Adult)
• Accepts Healthy Volunteers: No
• Genders Eligible for Study: All

• Sampling Method: Probability Sample

Study Population

Participants will be patients at the Manchester Royal Eye Hospital who meet the eligibility criteria.

Description

Inclusion Criteria:

Patients are eligible for the study if all inclusion criteria are met:

1. Voluntary informed consent.
2. Aged at least 18 years.
3. Fully registered patient attending the Manchester Royal Eye Hospital
4. Patients are having an optical diagnostic imaging as part of their standard of care.

Exclusion Criteria:

Patients are excluded from the study if any of the following criteria apply:

1. Patient who are deemed clinically unable to be scanned by healthcare professional.

Study Plan

How is the study designed?

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Time Frame
Measure of the diagnostic accuracy of the AI algorithm against gold standard clinical assessment associated with cancer treatment.	12 months

Secondary Outcome Measures

Outcome Measure	Time Frame
Sensitivity of the AI in identifying clinically relevant lesions as defined by an ophthalmologist. Specificity of the AI in identifying clinically relevant lesions as defined by an ophthalmologist.	12 months

Other Outcome Measures

Outcome Measure	Time Frame
F1 score of the proposed algorithm compared against baseline algorithms.	13 months
Recorded questionnaire/ interview with ophthalmologist and cancer specialists.	9 months
Number of novel relationships identified	12 months

Collaborators and Investigators

• Sponsor: University of Manchester
• Collaborators: Institute of Cancer Research, United Kingdom

Study record dates

Study Major Dates

• Study Start (Actual): June 18, 2021
• Primary Completion (Anticipated): December 31, 2022
• Study Completion (Anticipated): December 31, 2022

Study Registration Dates

• First Submitted: May 17, 2021
• First Submitted That Met QC Criteria: May 24, 2021
• First Posted (Actual): May 25, 2021

Study Record Updates

• Last Update Posted (Actual): November 9, 2022
• Last Update Submitted That Met QC Criteria: November 8, 2022
• Last Verified: November 1, 2022

More Information

Terms related to this study

• Other Study ID Numbers: NHS001768

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No