london euretina

This meeting has been awarded 20 CME credits

Security Notice

Please note that Kuoni are our only destination management company. Other venders indicating that are operating for the society should be ignored. We never use western union as a payment portal


Evaluation of an automated image analysis software for the detection of diabetic retinopathy to reduce the ophthalmologist workload

Poster Details

First Author: C.Hernaez-Ortega SPAIN

Co Author(s):    A. Navea   E. Soto-Pedre   J. Morales   S. Millan   P. Perez   C. Desco   0   0 0   0 0   0 0   0 0

Abstract Details


To assess the safety of an automated ‘‘disease/no disease’’ grading system for diabetic retinopathy within a systematic screening program.


Cross-sectional observational epidemiologic study.Fundación Oftalmológica del Mediterráneo (FOM), Valencia, Spain.European Innovative Biomedicine Institute (EIBI), Cantabria, Spain.


A single central field digital image per eye was obtained from consecutive patients attending a regional primary care based diabetic retinopathy screening program in Valencia (Spain). Photographers were trained nurse assistants. The sensitivity and specificity of the automated system (iGrading- Medalytix Ltd, Manchester UK - operating as more than one microaneurysm detection for disease presence) grader were determined against a manual grading as gold standard.


5517 patients were screened at twenty-seven Health Centers of four Health Departments. The median age was 69 years (IQR 16 years) and 56% were male. The software classified 44.5% of the patients as having no retinopathy. Detection of retinopathy was achieved with 94.5% sensitivity (95% CI 92.6- 96.5) and 69.1% specificity (95% CI 67.6- 70.6).


Automated grading of diabetic retinopathy based on a single field plus one microaneurysm detection for disease presence approach seems to be adequate not only in terms of workload reduction but also in terms of safety.

Back to previous
EURETINA, Temple House, Temple Road, Blackrock, Co Dublin. | Phone: 00353 1 2100092 | Fax: 00353 1 2091112 | Email:

Privacy policyHotel Terms and Conditions Cancellation policy