Diagnostic accuracy of a device for the automated detection of diabetic retinopathy in a primary care setting

Frank D. Verbraak, Michael D. Abramoff, Gonny C. F. Bausch, Caroline Klaver, Giel Nijpels, Reinier O. Schlingemann, Amber A. van der Heijden

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

OBJECTIVE To determine the diagnostic accuracy in a real-world primary care setting of a deep learning–enhanced device for automated detection of diabetic retinopathy (DR). RESEARCH DESIGN AND METHODS Retinal images of people with type 2 diabetes visiting a primary care screening program were graded by a hybrid deep learning–enhanced device (IDx-DR-EU-2.1; IDx, Amsterdam, the Netherlands), and its classification of retinopathy (vision-threatening [vt]DR, more than mild [mtm]DR, and mild or more [mom]DR) was compared with a reference standard. This reference standard consisted of grading according to the International Clinical Classification of DR by the Rotterdam Study reading center. We determined the diagnostic accuracy of the hybrid deep learning–enhanced device (IDx-DR-EU-2.1) against the reference standard. RESULTS A total of 1,616 people with type 2 diabetes were imaged. The hybrid deep learning–enhanced device’s sensitivity/specificity against the reference standard was, respectively, for vtDR 100% (95% CI 77.1–100)/97.8% (95% CI 96.8–98.5) and for mtmDR 79.4% (95% CI 66.5–87.9)/93.8% (95% CI 92.1–94.9). CONCLUSIONS The hybrid deep learning–enhanced device had high diagnostic accuracy for the detection of both vtDR (although the number of vtDR cases was low) and mtmDR in a primary care setting against an independent reading center. This allows its’ safe use in a primary care setting.
LanguageEnglish
Pages651-656
JournalDiabetes Care
Volume42
Issue number4
DOIs
Publication statusPublished - 2019

Cite this

@article{857863700a604582bc709bcee7d7a3f5,
title = "Diagnostic accuracy of a device for the automated detection of diabetic retinopathy in a primary care setting",
abstract = "OBJECTIVE To determine the diagnostic accuracy in a real-world primary care setting of a deep learning–enhanced device for automated detection of diabetic retinopathy (DR). RESEARCH DESIGN AND METHODS Retinal images of people with type 2 diabetes visiting a primary care screening program were graded by a hybrid deep learning–enhanced device (IDx-DR-EU-2.1; IDx, Amsterdam, the Netherlands), and its classification of retinopathy (vision-threatening [vt]DR, more than mild [mtm]DR, and mild or more [mom]DR) was compared with a reference standard. This reference standard consisted of grading according to the International Clinical Classification of DR by the Rotterdam Study reading center. We determined the diagnostic accuracy of the hybrid deep learning–enhanced device (IDx-DR-EU-2.1) against the reference standard. RESULTS A total of 1,616 people with type 2 diabetes were imaged. The hybrid deep learning–enhanced device’s sensitivity/specificity against the reference standard was, respectively, for vtDR 100{\%} (95{\%} CI 77.1–100)/97.8{\%} (95{\%} CI 96.8–98.5) and for mtmDR 79.4{\%} (95{\%} CI 66.5–87.9)/93.8{\%} (95{\%} CI 92.1–94.9). CONCLUSIONS The hybrid deep learning–enhanced device had high diagnostic accuracy for the detection of both vtDR (although the number of vtDR cases was low) and mtmDR in a primary care setting against an independent reading center. This allows its’ safe use in a primary care setting.",
author = "Verbraak, {Frank D.} and Abramoff, {Michael D.} and Bausch, {Gonny C. F.} and Caroline Klaver and Giel Nijpels and Schlingemann, {Reinier O.} and {van der Heijden}, {Amber A.}",
year = "2019",
doi = "10.2337/dc18-0148",
language = "English",
volume = "42",
pages = "651--656",
journal = "Diabetes Care",
issn = "0149-5992",
publisher = "American Diabetes Association Inc.",
number = "4",

}

Diagnostic accuracy of a device for the automated detection of diabetic retinopathy in a primary care setting. / Verbraak, Frank D.; Abramoff, Michael D.; Bausch, Gonny C. F.; Klaver, Caroline; Nijpels, Giel; Schlingemann, Reinier O.; van der Heijden, Amber A.

In: Diabetes Care, Vol. 42, No. 4, 2019, p. 651-656.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Diagnostic accuracy of a device for the automated detection of diabetic retinopathy in a primary care setting

AU - Verbraak, Frank D.

AU - Abramoff, Michael D.

AU - Bausch, Gonny C. F.

AU - Klaver, Caroline

AU - Nijpels, Giel

AU - Schlingemann, Reinier O.

AU - van der Heijden, Amber A.

PY - 2019

Y1 - 2019

N2 - OBJECTIVE To determine the diagnostic accuracy in a real-world primary care setting of a deep learning–enhanced device for automated detection of diabetic retinopathy (DR). RESEARCH DESIGN AND METHODS Retinal images of people with type 2 diabetes visiting a primary care screening program were graded by a hybrid deep learning–enhanced device (IDx-DR-EU-2.1; IDx, Amsterdam, the Netherlands), and its classification of retinopathy (vision-threatening [vt]DR, more than mild [mtm]DR, and mild or more [mom]DR) was compared with a reference standard. This reference standard consisted of grading according to the International Clinical Classification of DR by the Rotterdam Study reading center. We determined the diagnostic accuracy of the hybrid deep learning–enhanced device (IDx-DR-EU-2.1) against the reference standard. RESULTS A total of 1,616 people with type 2 diabetes were imaged. The hybrid deep learning–enhanced device’s sensitivity/specificity against the reference standard was, respectively, for vtDR 100% (95% CI 77.1–100)/97.8% (95% CI 96.8–98.5) and for mtmDR 79.4% (95% CI 66.5–87.9)/93.8% (95% CI 92.1–94.9). CONCLUSIONS The hybrid deep learning–enhanced device had high diagnostic accuracy for the detection of both vtDR (although the number of vtDR cases was low) and mtmDR in a primary care setting against an independent reading center. This allows its’ safe use in a primary care setting.

AB - OBJECTIVE To determine the diagnostic accuracy in a real-world primary care setting of a deep learning–enhanced device for automated detection of diabetic retinopathy (DR). RESEARCH DESIGN AND METHODS Retinal images of people with type 2 diabetes visiting a primary care screening program were graded by a hybrid deep learning–enhanced device (IDx-DR-EU-2.1; IDx, Amsterdam, the Netherlands), and its classification of retinopathy (vision-threatening [vt]DR, more than mild [mtm]DR, and mild or more [mom]DR) was compared with a reference standard. This reference standard consisted of grading according to the International Clinical Classification of DR by the Rotterdam Study reading center. We determined the diagnostic accuracy of the hybrid deep learning–enhanced device (IDx-DR-EU-2.1) against the reference standard. RESULTS A total of 1,616 people with type 2 diabetes were imaged. The hybrid deep learning–enhanced device’s sensitivity/specificity against the reference standard was, respectively, for vtDR 100% (95% CI 77.1–100)/97.8% (95% CI 96.8–98.5) and for mtmDR 79.4% (95% CI 66.5–87.9)/93.8% (95% CI 92.1–94.9). CONCLUSIONS The hybrid deep learning–enhanced device had high diagnostic accuracy for the detection of both vtDR (although the number of vtDR cases was low) and mtmDR in a primary care setting against an independent reading center. This allows its’ safe use in a primary care setting.

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85063631850&origin=inward

UR - https://www.ncbi.nlm.nih.gov/pubmed/30765436

U2 - 10.2337/dc18-0148

DO - 10.2337/dc18-0148

M3 - Article

VL - 42

SP - 651

EP - 656

JO - Diabetes Care

T2 - Diabetes Care

JF - Diabetes Care

SN - 0149-5992

IS - 4

ER -