PURPOSE: To determine if combining clinical, demographic, and imaging data improves automated diagnosis of nonproliferative diabetic retinopathy (NPDR). DESIGN: Cross-sectional imaging and machine learning study. METHODS: This was a retrospective study performed at a single academic medical center in the United States. Inclusion criteria were age > 18 and a diagnosis of diabetes mellitus (DM). Exclusion criteria were non-DR retinal disease and inability to image the macula. Optical coherence tomography (OCT) and OCT angiography (OCTA) were performed, and data on age, gender, hypertension, hyperlipidemia, and hemoglobin A1c were collected. Machine learning techniques were then applied. Multiple pathophysiologically important features were automatically extracted from each layer on OCT and each OCTA plexus and combined with clinical data in a random forest classifier to develop the system, whose results were compared to the clinical grading of NPDR, the gold standard. RESULTS: 111 patients with DM II were included in the study, 36 with DM without DR, 53 with mild NPDR, and 22 with moderate NPDR. When OCT images alone were analyzed by the system, accuracy of diagnosis was 76%, sensitivity 85%, specificity 87%, and area under the curve (AUC) was 0.78. When OCT and OCTA data together were analyzed, accuracy was 92%, sensitivity 95%, specificity 98%, and AUC 0.92. When all data modalities were combined, the system achieved an accuracy of 96%, sensitivity 100%, specificity 94%, and AUC 0.96. CONCLUSIONS: Combining common clinical data points with OCT and OCTA data enhances the power of computer-aided diagnosis of NPDR.
PURPOSE: To determine if combining clinical, demographic, and imaging data improves automated diagnosis of nonproliferative diabetic retinopathy (NPDR). DESIGN: Cross-sectional imaging and machine learning study. METHODS: This was a retrospective study performed at a single academic medical center in the United States. Inclusion criteria were age > 18 and a diagnosis of diabetes mellitus (DM). Exclusion criteria were non-DR retinal disease and inability to image the macula. Optical coherence tomography (OCT) and OCT angiography (OCTA) were performed, and data on age, gender, hypertension, hyperlipidemia, and hemoglobin A1c were collected. Machine learning techniques were then applied. Multiple pathophysiologically important features were automatically extracted from each layer on OCT and each OCTA plexus and combined with clinical data in a random forest classifier to develop the system, whose results were compared to the clinical grading of NPDR, the gold standard. RESULTS: 111 patients with DM II were included in the study, 36 with DM without DR, 53 with mild NPDR, and 22 with moderate NPDR. When OCT images alone were analyzed by the system, accuracy of diagnosis was 76%, sensitivity 85%, specificity 87%, and area under the curve (AUC) was 0.78. When OCT and OCTA data together were analyzed, accuracy was 92%, sensitivity 95%, specificity 98%, and AUC 0.92. When all data modalities were combined, the system achieved an accuracy of 96%, sensitivity 100%, specificity 94%, and AUC 0.96. CONCLUSIONS: Combining common clinical data points with OCT and OCTA data enhances the power of computer-aided diagnosis of NPDR.
Authors: Tristan T Hormel; Thomas S Hwang; Steven T Bailey; David J Wilson; David Huang; Yali Jia Journal: Prog Retin Eye Res Date: 2021-03-22 Impact factor: 21.198
Authors: A Sharafeldeen; M Elsharkawy; F Khalifa; A Soliman; M Ghazal; M AlHalabi; M Yaghi; M Alrahmawy; S Elmougy; H S Sandhu; A El-Baz Journal: Sci Rep Date: 2021-02-25 Impact factor: 4.379
Authors: Martin Pfister; Hannes Stegmann; Kornelia Schützenberger; Bhavapriya Jasmin Schäfer; Christine Hohenadl; Leopold Schmetterer; Martin Gröschl; René M Werkmeister Journal: Ann N Y Acad Sci Date: 2021-02-26 Impact factor: 5.691
Authors: Nihaal Mehta; Cecilia S Lee; Luísa S M Mendonça; Khadija Raza; Phillip X Braun; Jay S Duker; Nadia K Waheed; Aaron Y Lee Journal: JAMA Ophthalmol Date: 2020-10-01 Impact factor: 8.253