Diabetic Retinopathy Diagnosis based on Convolutional Neural Network in the Russian Population: A Multicenter Prospective Study

Daria Gognieva; Larisa Moshetova; Dmitry Sychev; Maria Budzinskaya; Vladislav Pavlov; Yusef Yusef; Magomed Abdullaev; Baraah Al-Dwa; Alina Bektimirova; Natalia Kuznetsova; Alexander Suvorov; Petr Chomakhidze; Irina Vorobyeva; Madina Durzhinskaya; Philipp Kopylov

doi:10.2174/0115733998268034231101091236

Diabetic Retinopathy Diagnosis based on Convolutional Neural Network in the Russian Population: A Multicenter Prospective Study

Authors: Gognieva D.¹, Moshetova L.², Sychev D.², Budzinskaya M.³, Pavlov V.³, Yusef Y.³, Abdullaev M.¹, Al-Dwa B.¹, Bektimirova A.¹, Kuznetsova N.¹, Suvorov A.¹, Chomakhidze P.¹, Vorobyeva I.¹, Durzhinskaya M.¹, Kopylov P.¹
Affiliations:
1. World-Class Research Center "Digital Biodesign and Personalized Healthcare", I.M. Sechenov First Moscow State Medical University (Sechenov University), Moscow, Russia
2. Federal State Budgetary Educational Institution of Further Professional Education "Russian Medical Academy of Continuous Professional Education" of the Ministry of Healthcare of the Russian Federation, Moscow, Russia
3. Research Institute of Eye Diseases Named After M.M. Krasnov, Federal State Budgetary Institution, Moscow, Russia
Issue: Vol 20, No 8 (2024)
Section: Medicine
URL: https://snv63.ru/1573-3998/article/view/643034
DOI: https://doi.org/10.2174/0115733998268034231101091236
ID: 643034

Cite item

Full Text

Abstract
About the authors
References
Supplementary files
Statistics

Abstract

Background::Diabetic retinopathy is the most common complication of diabetes mellitus and is one of the leading causes of vision impairment globally, which is also relevant for the Russian Federation.

Objective::To evaluate the diagnostic efficiency of a convolutional neural network trained for the detection of diabetic retinopathy and estimation of its severity in fundus images of the Russian population.

Methods::In this cross-sectional multicenter study, the training data set was obtained from an open source and relabeled by a group of independent retina specialists; the sample size was 60,000 eyes. The test sample was recruited prospectively, 1186 fundus photographs of 593 patients were collected. The reference standard was the result of independent grading of the diabetic retinopathy stage by ophthalmologists.

Results::Sensitivity and specificity were 95.0% (95% CI; 90.8-96.4) and 96.8% (95% CI; 95.5- 99.0), respectively; positive predictive value 98.8% (95% CI; 97.6-99.2); negative predictive value 87.1% (95% CI, 83.4-96.5); accuracy 95.9% (95% CI; 93.3-97.1); Kappa score 0.887 (95% CI; 0.839-0.946); F1score 0.909 (95% CI; 0.870-0.957); area under the ROC-curve 95.9% (95% CI; 93.3-97.1). There was no statistically significant difference in diagnostic accuracy between the group with isolated diabetic retinopathy and those with hypertensive retinopathy as a concomitant diagnosis.

Conclusion::The method for diagnosing DR presented in this article has shown its high accuracy, which is consistent with the existing world analogues, however, this method should prove its clinical efficiency in large multicenter multinational controlled randomized studies, in which the reference diagnostic method would be unified and less subjective than an ophthalmologist.

Keywords

Diabetes mellitus, diabetic retinopathy, diagnostics, screening, neural networks, machine learning.

Supplementary files

Supplementary Files

Action

1. JATS XML

Download

Username
Password
Remember me

Forgot password?	Register

Username
Password
Remember me

Forgot password?	Register

Diabetic Retinopathy Diagnosis based on Convolutional Neural Network in the Russian Population: A Multicenter Prospective Study

Full Text

Abstract

Keywords

About the authors

Supplementary files