E-Mail karger@karger.com
Original Paper
Ophthalmologica 2015;233:96–103
DOI: 10.1159/000368426
Screening for Diabetic Retinopathy in the Central
Region of Portugal. Added Value of Automated
‘Disease/No Disease’ Grading
Luisa Ribeiro
a
Carlos Manta Oliveira
b
Catarina Neves
a
João Diogo Ramos
b
Hélder Ferreira
c
José Cunha-Vaz
a, d
a
AIBILI, CORC – Association for Innovation and Biomedial Research on Light and Image, Coimbra Ophthalmology
Reading Center,
b
Retmarker SA,
c
Regional Health Administration of the Central Region of Portugal, and
d
Faculty of
Medicine of University of Coimbra, Coimbra, Portugal
Introduction
At 20 years after diagnosis, more than 90% of patients
with type I diabetes and more than 60% of those with type
2 diabetes will have some degree of diabetic retinopathy
(DR) [1, 2]. DR is a common and serious condition. It is
the leading cause of blindness among working-age adults
in the USA [3]. Vision loss related to eye disease among
people with diabetes is an important disability that threat-
ens independence and can lead to depression, reduced
mobility and reduced quality of life [4]. With early detec-
tion, DR can be treated with modalities that have been
proven to decrease the risk of severe vision loss by more
than 90% [5] and because of these benefits some profes-
sional organizations such as the American Diabetes As-
sociation and the American Academy of Ophthalmology
have established guidelines for DR screening. However,
less than 50% of diabetic patients in the USA meet these
recommendations [6–8].
DR meets the criteria for screening, allowing early de-
tection of DR lesions and timely referral for treatment. It
is detectable in a presymptomatic stage, and the develop-
ment of vision loss can be prevented if treatment is given
timely to treat sight-threatening complications such as
diabetic macular edema and proliferative DR. Further-
more, screening for DR has been shown to be cost-effec-
Key Words
Diabetic retinopathy · Screening · Automated grading ·
Fundus photography
Abstract
Purpose: To describe the procedures of a nonmydriatic dia-
betic retinopathy (DR) screening program in the Central Re-
gion of Portugal and the added value of the introduction of
an automated disease/no disease analysis. Methods: The
images from the DR screening program are analyzed in a
central reading center using first an automated disease/no
disease analysis followed by human grading of the disease
cases. The grading scale used is as follows: R0 – no retinop-
athy, RL – nonproliferative DR, M – maculopathy, RP – pro-
liferative DR and NC – not classifiable. Results: Since the
introduction of automated analysis in July 2011, a total of
89,626 eyes (45,148 patients) were screened with the follow-
ing distribution: R0 – 71.5%, RL – 22.7%, M – 2.2%, RP – 0.1%
and NC – 3.5%. The implemented automated system
showed the potential for human grading burden reduction
of 48.42%. Conclusions: Screening for DR using automated
analysis allied to a simplified grading scale identifies DR vi-
sion-threatening complications well while decreasing hu-
man burden. © 2014 S. Karger AG, Basel
Received: September 2, 2014
Accepted: September 5, 2014
Published online: November 26, 2014
Ophthalmologica
Luisa Ribeiro
AIBILI, Azinhaga de Santa Comba, Celas
PT–3000-548 Coimbra (Portugal)
E-Mail lr @ aibili.pt
© 2014 S. Karger AG, Basel
0030–3755/14/2332–0096$39.50/0
www.karger.com/oph