Library Header Image
LSE Research Online LSE Library Services

A study of whether automated diabetic retinopathy image assessment could replace manual grading steps in the English National Screening Programme

Kapetanakis, V. V., Rudnicka, A. R., Liew, G., Owen, C. G., Lee, A., Louw, V., Bolter, L., Anderson, J., Egan, C., Salas-Vega, S., Rudisill, C., Taylor, P. and Tufail, A. (2015) A study of whether automated diabetic retinopathy image assessment could replace manual grading steps in the English National Screening Programme. Journal of Medical Screening, 22 (3). pp. 112-118. ISSN 0969-1413

Full text not available from this repository.
Identification Number: 10.1177/0969141315571953


Objectives Diabetic retinopathy screening in England involves labour intensive manual grading of digital retinal images. We present the plan for an observational retrospective study of whether automated systems could replace one or more steps of human grading. Methods Patients aged 12 or older who attended the Diabetes Eye Screening programme, Homerton University Hospital (London) between 1 June 2012 and 4 November 2013 had macular and disc-centred retinal images taken. All screening episodes were manually graded and will additionally be graded by three automated systems. Each system will process all screening episodes, and screening performance (sensitivity, false positive rate, likelihood ratios) and diagnostic accuracy (95% confidence intervals of screening performance measures) will be quantified. A sub-set of gradings will be validated by an approved Reading Centre. Additional analyses will explore the effect of altering thresholds for disease detection within each automated system on screening performance. Results 2,782/20,258 diabetes patients were referred to ophthalmologists for further examination. Prevalence of maculopathy (M1), pre-proliferative retinopathy (R2), and proliferative retinopathy (R3) were 7.9%, 3.1% and 1.2%, respectively; 4749 (23%) patients were diagnosed with background retinopathy (R1); 1.5% were considered ungradable by human graders. Conclusions Retinopathy prevalence was similar to other English diabetic screening programmes, so findings should be generalizable. The study population size will allow the detection of differences in screening performance between the human and automated grading systems as small as 2%. The project will compare performance and economic costs of manual versus automated systems.

Item Type: Article
Official URL:
Additional Information: © 2015 The Authors
Divisions: Social Policy
LSE Health
Subjects: R Medicine > RA Public aspects of medicine
Sets: Departments > Social Policy
Research centres and groups > LSE Health
Date Deposited: 03 Jun 2015 10:51
Last Modified: 20 Apr 2021 02:35

Actions (login required)

View Item View Item