TY - JOUR
T1 - Validation of Automated Screening for Referable Diabetic Retinopathy With an Autonomous Diagnostic Artificial Intelligence System in a Spanish Population
AU - Shah, Abhay
AU - Clarida, Warren
AU - Amelon, Ryan
AU - Hernaez-Ortega, Maria C.
AU - Navea, Amparo
AU - Morales-Olivas, Jesus
AU - Dolz-Marco, Rosa
AU - Verbraak, Frank
AU - Jorda, Pablo P.
AU - van der Heijden, Amber A.
AU - Peris Martinez, Cristina
N1 - Funding Information:
The author(s) declared the following potential conflicts of interest with respect to the research, authorship, and/or publication of this article: R.A. and W.C. are directors of research and development at IDx Technologies Inc. A.S. is a research and development software engineer at IDx Technologies Inc. W.C., R.A., and A.S. are shareholders in IDx Technologies Inc. All authors, FOM and EIBI, with the exception of A.N., P.P.J, A.A.v.d.H., and C.P.M received financial support from IDx Technologies Inc. No other potential conflicts of interest relevant to this article were reported. Contents are solely the responsibility of the authors.
Funding Information:
The author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: The study was funded by IDx Technologies Inc., Coralville, USA.
Funding Information:
The authors thank Enrique Soto-Pedre (European Innovative Biomedicine Institute (EIBI), Cantabria, Spain) for designing the protocol used in this study and for recruitment and providing instructions to the ophthalmologists for manual grading of the exams. The author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: The study was funded by IDx Technologies Inc., Coralville, USA.
Publisher Copyright:
© 2020 Diabetes Technology Society.
PY - 2020
Y1 - 2020
N2 - Purpose: The purpose of this study is to compare the diagnostic performance of an autonomous artificial intelligence (AI) system for the diagnosis of referable diabetic retinopathy (RDR) to manual grading by Spanish ophthalmologists. Methods: Subjects with type 1 and 2 diabetes participated in a diabetic retinopathy (DR) screening program in 2011 to 2012 in Valencia (Spain), and two images per eye were collected according to their standard protocol. Mydriatic drops were used in all patients. Retinal images—one disc and one fovea centered—were obtained under the Medical Research Ethics Committee approval and de-identified. Exams were graded by the autonomous AI system (IDx-DR, Coralville, Iowa, United States), and manually by masked ophthalmologists using adjudication. The outputs of the AI system and manual adjudicated grading were compared using sensitivity and specificity for diagnosis of both RDR and vision-threatening diabetic retinopathy (VTDR). Results: A total of 2680 subjects were included in the study. According to manual grading, prevalence of RDR was 111/2680 (4.14%) and of VTDR was 69/2680 (2.57%). Against manual grading, the AI system had a 100% (95% confidence interval [CI]: 97%-100%) sensitivity and 81.82% (95% CI: 80%-83%) specificity for RDR, and a 100% (95% CI: 95%-100%) sensitivity and 94.64% (95% CI: 94%-95%) specificity for VTDR. Conclusion: Compared to manual grading by ophthalmologists, the autonomous diagnostic AI system had high sensitivity (100%) and specificity (82%) for diagnosing RDR and macular edema in people with diabetes in a screening program. Because of its immediate, point of care diagnosis, autonomous diagnostic AI has the potential to increase the accessibility of RDR screening in primary care settings.
AB - Purpose: The purpose of this study is to compare the diagnostic performance of an autonomous artificial intelligence (AI) system for the diagnosis of referable diabetic retinopathy (RDR) to manual grading by Spanish ophthalmologists. Methods: Subjects with type 1 and 2 diabetes participated in a diabetic retinopathy (DR) screening program in 2011 to 2012 in Valencia (Spain), and two images per eye were collected according to their standard protocol. Mydriatic drops were used in all patients. Retinal images—one disc and one fovea centered—were obtained under the Medical Research Ethics Committee approval and de-identified. Exams were graded by the autonomous AI system (IDx-DR, Coralville, Iowa, United States), and manually by masked ophthalmologists using adjudication. The outputs of the AI system and manual adjudicated grading were compared using sensitivity and specificity for diagnosis of both RDR and vision-threatening diabetic retinopathy (VTDR). Results: A total of 2680 subjects were included in the study. According to manual grading, prevalence of RDR was 111/2680 (4.14%) and of VTDR was 69/2680 (2.57%). Against manual grading, the AI system had a 100% (95% confidence interval [CI]: 97%-100%) sensitivity and 81.82% (95% CI: 80%-83%) specificity for RDR, and a 100% (95% CI: 95%-100%) sensitivity and 94.64% (95% CI: 94%-95%) specificity for VTDR. Conclusion: Compared to manual grading by ophthalmologists, the autonomous diagnostic AI system had high sensitivity (100%) and specificity (82%) for diagnosing RDR and macular edema in people with diabetes in a screening program. Because of its immediate, point of care diagnosis, autonomous diagnostic AI has the potential to increase the accessibility of RDR screening in primary care settings.
KW - artificial intelligence
KW - diabetic retinopathy
KW - diabetic retinopathy screening
KW - population screening
UR - http://www.scopus.com/inward/record.url?scp=85082139738&partnerID=8YFLogxK
U2 - 10.1177/1932296820906212
DO - 10.1177/1932296820906212
M3 - Article
C2 - 32174153
AN - SCOPUS:85082139738
VL - 15
SP - 655
EP - 663
JO - Journal of diabetes science and technology
JF - Journal of diabetes science and technology
SN - 1932-2968
IS - 3
ER -