Prospective evaluation of an artificial intelligence-enabled algorithm for automated diabetic retinopathy screening of 30 000 patients

Heydon, Peter, Egan, Catherine, Bolter, Louis, Chambers, Ryan, Anderson, John, Aldington, Steve, Stratton, Irene M, Scanlon, Peter H ORCID: 0000-0001-8513-710X, Webster, Laura, Mann, Samantha, du Chemin, Alan, Owen, Christopher G, Tufail, Adnan and Rudnicka, Alicja Regina (2021) Prospective evaluation of an artificial intelligence-enabled algorithm for automated diabetic retinopathy screening of 30 000 patients. British Journal of Ophthalmology, 105 (5). pp. 723-728. doi:10.1136/bjophthalmol-2020-316594

Preview

Text 8522-Heydon,-Scanlon,-et-al-(2020)-Prospective-evaluation-of-an-artificial-intelligence-enabled-algorithm-for-automated-diabetic-retinopathy-screening.pdf - Published Version Available under License Creative Commons Attribution Non-commercial 4.0. Download (310kB) | Preview

Abstract

Background/aims: Human grading of digital images from diabetic retinopathy (DR) screening programmes represents a significant challenge, due to the increasing prevalence of diabetes. We evaluate the performance of an automated artificial intelligence (AI) algorithm to triage retinal images from the English Diabetic Eye Screening Programme (DESP) into test-positive/technical failure versus test-negative, using human grading following a standard national protocol as the reference standard. Methods: Retinal images from 30 405 consecutive screening episodes from three English DESPs were manually graded following a standard national protocol and by an automated process with machine learning enabled software, EyeArt v2.1. Screening performance (sensitivity, specificity) and diagnostic accuracy (95% CIs) were determined using human grades as the reference standard. Results: Sensitivity (95% CIs) of EyeArt was 95.7% (94.8% to 96.5%) for referable retinopathy (human graded ungradable, referable maculopathy, moderate-to-severe non-proliferative or proliferative). This comprises sensitivities of 98.3% (97.3% to 98.9%) for mild-to-moderate non-proliferative retinopathy with referable maculopathy, 100% (98.7%,100%) for moderate-to-severe non-proliferative retinopathy and 100% (97.9%,100%) for proliferative disease. EyeArt agreed with the human grade of no retinopathy (specificity) in 68% (67% to 69%), with a specificity of 54.0% (53.4% to 54.5%) when combined with non-referable retinopathy. Conclusion: The algorithm demonstrated safe levels of sensitivity for high-risk retinopathy in a real-world screening service, with specificity that could halve the workload for human graders. AI machine learning and deep learning algorithms such as this can provide clinically equivalent, rapid detection of retinopathy, particularly in settings where a trained workforce is unavailable or where large-scale and rapid results are needed.

Item Type:	Article
Article Type:	Article
Uncontrolled Keywords:	Clinical Trial; Degeneration; Diagnostic tests/Investigation; Epidemiology; Imaging; Medical Education; Public health; Retina; Telemedicine; Treatment Medical
Subjects:	R Medicine > RA Public aspects of medicine > RA645.A-Z Individual diseases or groups of diseases, A-Z > RA645.D54 Diabetes R Medicine > RE Ophthalmology
Divisions:	Schools and Research Institutes > School of Health and Social Care
Research Priority Areas:	Health, Life Sciences, Sport and Wellbeing
Depositing User:	Susan Turner
Date Deposited:	02 Jul 2020 13:30
Last Modified:	04 Feb 2022 16:30
URI:	https://eprints.glos.ac.uk/id/eprint/8522

University Staff: Request a correction | Repository Editors: Update this record