Can artificial intelligence accelerate the diagnosis of inherited retinal diseases? Protocol for a data-only retrospective cohort study (Eye2Gene)

Abstract

IntroductionInherited retinal diseases (IRD) are a leading cause of visual impairment and blindness in the working age population. Mutations in over 300 genes have been found to be associated with IRDs and identifying the affected gene in patients by molecular genetic testing is the first step towards effective care and patient management. However, genetic diagnosis is currently slow, expensive and not widely accessible. The aim of the current project is to address the evidence gap in IRD diagnosis with an AI algorithm, Eye2Gene, to accelerate and democratise the IRD diagnosis service.Methods and analysisThe data-only retrospective cohort study involves a target sample size of 10 000 participants, which has been derived based on the number of participants with IRD at three leading UK eye hospitals: Moorfields Eye Hospital (MEH), Oxford University Hospital (OUH) and Liverpool University Hospital (LUH), as well as a Japanese hospital, the Tokyo Medical Centre (TMC). Eye2Gene aims to predict causative genes from retinal images of patients with a diagnosis of IRD. For this purpose, 36 most common causative IRD genes have been selected to develop a training dataset for the software to have enough examples for training and validation for detection of each gene. The Eye2Gene algorithm is composed of multiple deep convolutional neural networks, which will be trained on MEH IRD datasets, and externally validated on OUH, LUH and TMC.Ethics and disseminationThis research was approved by the IRB and the UK Health Research Authority (Research Ethics Committee reference 22/WA/0049) ‘Eye2Gene: accelerating the diagnosis of IRDs’ Integrated Research Application System (IRAS) project ID: 242050. All research adhered to the tenets of the Declaration of Helsinki. Findings will be reported in an open-access format.

Quantification of Fundus Autofluorescence Features in a Molecularly Characterized Cohort of More Than 3000 Inherited Retinal Disease Patients from the United Kingdom

“…A dataset of 736 blue-FAF images (55-degree) from 573 patients from MEH were annotated with four different image features, optic disc, regions of hyper- and hypo-autofluorescence (AF), and perimacular ring of increased signal, and a further set of 206 blue-FAF images (55-degree) from 127 patients from the Royal Liverpool Hospital (RLH) were annotated with the retina vessel tree. A grading protocol was defined for IRD retinal feature annotations ( Table 1) 12 . The Dice similarity coefficient score was used to assess inter-grader agreement 13 .…”

Behind the mask: a critical perspective on the ethical, moral, and legal implications of AI in ophthalmology

“…However, the ownership of the data used for training and validation, as well as the AI algorithm itself, is not explicitly stated. This situation underscores the need for clear policies and regulations regarding the ownership and use of health data and AI algorithms in ophthalmology [ 26 ]. Companies and institutions have started to consider patients as “data traders,” who provide information about their health in exchange for remuneration [ 27 ].…”

Reshaping the use of Artificial Intelligence in Ophthalmology: Sometimes you Need to go Backwards

“…A valid example is the Eye2gene project from Moorfield group, whose aim is to provide automatic diagnosis of inherited eye diseases. 12 An additional example of a validated AI tool is the recently proposed software for the analysis of photoreceptor loss progression in geographic atrophy. This model has been used to support evidence suggesting a slowing effect of Pegcetacoplan in the expansion of the atrophic area.…”