Tyson N Kim1,2, Michael T Aaberg3, Patrick Li3, Jose R Davila3, Malavika Bhaskaranand4, Sandeep Bhat4, Chaithanya Ramachandra4, Kaushal Solanki4, Frankie Myers5, Clay Reber5, Rohan Jalalizadeh3, Todd P Margolis6, Daniel Fletcher5, Yannis M Paulus7,8. 1. Department of Ophthalmology and Visual Sciences, University of Michigan, Ann Arbor, MI, USA. tyson.kim@ucsf.edu. 2. Department of Ophthalmology, University of California San Francisco, San Francisco, CA, USA. tyson.kim@ucsf.edu. 3. Department of Ophthalmology and Visual Sciences, University of Michigan, Ann Arbor, MI, USA. 4. Eyenuk Inc, Woodland Hills, CA, USA. 5. Department of Bioengineering, University of California Berkeley, Berkeley, CA, USA. 6. Department of Ophthalmology and Visual Sciences, Washington University School of Medicine, St. Louis, MO, USA. 7. Department of Ophthalmology and Visual Sciences, University of Michigan, Ann Arbor, MI, USA. ypaulus@med.umich.edu. 8. Department of Biomedical Engineering, University of Michigan, Ann Arbor, MI, USA. ypaulus@med.umich.edu.
Abstract
PURPOSE: The aim of this study is to investigate the efficacy of a mobile platform that combines smartphone-based retinal imaging with automated grading for determining the presence of referral-warranted diabetic retinopathy (RWDR). METHODS: A smartphone-based camera (RetinaScope) was used by non-ophthalmic personnel to image the retina of patients with diabetes. Images were analyzed with the Eyenuk EyeArt® system, which generated referral recommendations based on presence of diabetic retinopathy (DR) and/or markers for clinically significant macular oedema. Images were independently evaluated by two masked readers and categorized as refer/no refer. The accuracies of the graders and automated interpretation were determined by comparing results to gold standard clinical diagnoses. RESULTS: A total of 119 eyes from 69 patients were included. RWDR was present in 88 eyes (73.9%) and in 54 patients (78.3%). At the patient-level, automated interpretation had a sensitivity of 87.0% and specificity of 78.6%; grader 1 had a sensitivity of 96.3% and specificity of 42.9%; grader 2 had a sensitivity of 92.5% and specificity of 50.0%. At the eye-level, automated interpretation had a sensitivity of 77.8% and specificity of 71.5%; grader 1 had a sensitivity of 94.0% and specificity of 52.2%; grader 2 had a sensitivity of 89.5% and specificity of 66.9%. DISCUSSION: Retinal photography with RetinaScope combined with automated interpretation by EyeArt achieved a lower sensitivity but higher specificity than trained expert graders. Feasibility testing was performed using non-ophthalmic personnel in a retina clinic with high disease burden. Additional studies are needed to assess efficacy of screening diabetic patients from general population.
PURPOSE: The aim of this study is to investigate the efficacy of a mobile platform that combines smartphone-based retinal imaging with automated grading for determining the presence of referral-warranted diabetic retinopathy (RWDR). METHODS: A smartphone-based camera (RetinaScope) was used by non-ophthalmic personnel to image the retina of patients with diabetes. Images were analyzed with the Eyenuk EyeArt® system, which generated referral recommendations based on presence of diabetic retinopathy (DR) and/or markers for clinically significant macular oedema. Images were independently evaluated by two masked readers and categorized as refer/no refer. The accuracies of the graders and automated interpretation were determined by comparing results to gold standard clinical diagnoses. RESULTS: A total of 119 eyes from 69 patients were included. RWDR was present in 88 eyes (73.9%) and in 54 patients (78.3%). At the patient-level, automated interpretation had a sensitivity of 87.0% and specificity of 78.6%; grader 1 had a sensitivity of 96.3% and specificity of 42.9%; grader 2 had a sensitivity of 92.5% and specificity of 50.0%. At the eye-level, automated interpretation had a sensitivity of 77.8% and specificity of 71.5%; grader 1 had a sensitivity of 94.0% and specificity of 52.2%; grader 2 had a sensitivity of 89.5% and specificity of 66.9%. DISCUSSION: Retinal photography with RetinaScope combined with automated interpretation by EyeArt achieved a lower sensitivity but higher specificity than trained expert graders. Feasibility testing was performed using non-ophthalmic personnel in a retina clinic with high disease burden. Additional studies are needed to assess efficacy of screening diabetic patients from general population.
Authors: David S Boyer; Young Hee Yoon; Rubens Belfort; Francesco Bandello; Raj K Maturi; Albert J Augustin; Xiao-Yan Li; Harry Cui; Yehia Hashad; Scott M Whitcup Journal: Ophthalmology Date: 2014-06-04 Impact factor: 12.079
Authors: Sophia Y Wang; Chris A Andrews; William H Herman; Thomas W Gardner; Joshua D Stein Journal: Ophthalmology Date: 2016-11-30 Impact factor: 12.079
Authors: John M Lachin; Neil H White; Dean P Hainsworth; Wanjie Sun; Patricia A Cleary; David M Nathan Journal: Diabetes Date: 2014-09-09 Impact factor: 9.461