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

Autor: Christopher G. Owen, Laura Webster, Peter Heydon, Irene M Stratton, Catherine A Egan, Adnan Tufail, Louis Bolter, John Anderson, Alain Du Chemin, Alicja R. Rudnicka, Peter H Scanlon, Samantha Mann, S J Aldington, Ryan Chambers
Rok vydání: 2020
Předmět:
Male
Epidemiology
Imaging
0302 clinical medicine
Image Processing
Computer-Assisted
Mass Screening
Prospective Studies
Child
Aged
80 and over
Public health
Diabetic retinopathy
Clinical Science
Middle Aged
Clinical Trial
Telemedicine
Sensory Systems
Female
Diagnostic tests/Investigation
Algorithm
Algorithms
Retinopathy
Adult
medicine.medical_specialty
Adolescent
030209 endocrinology & metabolism
Retina
Young Adult
03 medical and health sciences
Cellular and Molecular Neuroscience
Artificial Intelligence
Diabetes mellitus
medicine
Humans
Aged
Retrospective Studies
Diabetic Retinopathy
business.industry
Diabetic retinopathy screening
Reproducibility of Results
RA645.D54
medicine.disease
Triage
Clinical trial
Ophthalmology
Medical Education
Degeneration
030221 ophthalmology & optometry
Maculopathy
RE
Treatment Medical
Artificial intelligence
business
Follow-Up Studies
Zdroj: The British Journal of Ophthalmology
ISSN: 1468-2079
0007-1161
Popis: 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.
Databáze: OpenAIRE
Externí odkaz: