Sanil Joseph1,2,3, Renu P Rajan4, Balagiri Sundar4, Soundarya Venkatachalam1, John H Kempen5,6,7, Ramasamy Kim8. 1. Lions Aravind Institute of Community Ophthalmology, Aravind Eye Care System, Madurai, India. 2. Centre for Eye Research Australia, Royal Victorian Eye and Ear Hospital, East Melbourne, Vic, Australia. 3. Department of Surgery (Ophthalmology), The University of Melbourne, Melbourne, Vic, Australia. 4. Aravind Eye Hospital and Postgraduate Institute of Ophthalmology, Madurai, India. 5. Department of Ophthalmology, , Massachusetts Eye and Ear and Harvard Medical School; Schepens Eye Research Institute, Boston, MA, USA. 6. MCM Eye Unit, MyungSung Christian Medical Center (MCM) Multispecialty Hospital and MyungSung Medical School, Addis Ababa, Ethiopia. 7. Department of Ophthalmology, Faculty of Medicine, Addis Ababa University, Addis Ababa, Ethiopia. 8. Aravind Eye Hospital and Postgraduate Institute of Ophthalmology, Madurai, India. kim@aravind.org.
Abstract
PURPOSE: To validate the fundus image grading results by a trained grader (Non-ophthalmologist) and an ophthalmologist grader for detecting diabetic retinopathy (DR) and diabetic macular oedema (DMO) against fundus examination by a retina specialist (gold standard). METHODS: A prospective diagnostic accuracy study was conducted using 2002 non-mydriatic colour fundus images from 1001 patients aged ≥40 years. Using the Aravind Diabetic Retinopathy Evaluation Software (ADRES) images were graded by both a trained non-ophthalmologist grader (grader-1) and an ophthalmologist (grader-2). Sensitivity, specificity, positive predictive value and negative predictive value were calculated for grader-1 and grader-2 against the grading results by an independent retina specialist who performed dilated fundus examination for every study participant. RESULTS: Out of 1001 patients included, 42% were women and the mean ± (SD) age was 55.8 (8.39) years. For moderate or worse DR, the sensitivity and specificity for grading by grader-1 with respect to the gold standard was 66.9% and 91.0% respectively and the same for the ophthalmologist was 83.6% and 80.3% respectively. For referable DMO, grader-1 and grader-2 had a sensitivity of 74.6% and 85.6% respectively and a specificity of 83.7% and 79.8% respectively. CONCLUSIONS: Our results demonstrate good level of accuracy for the fundus image grading performed by a trained non-ophthalmologist which was comparable with the grading by an ophthalmologist. Engaging trained non-ophthalmologists potentially can enhance the efficiency of DR diagnosis using fundus images. Further study with multiple non-ophthalmologist graders is needed to verify the results and strategies to improve agreement for DMO diagnosis are needed.
PURPOSE: To validate the fundus image grading results by a trained grader (Non-ophthalmologist) and an ophthalmologist grader for detecting diabetic retinopathy (DR) and diabetic macular oedema (DMO) against fundus examination by a retina specialist (gold standard). METHODS: A prospective diagnostic accuracy study was conducted using 2002 non-mydriatic colour fundus images from 1001 patients aged ≥40 years. Using the Aravind Diabetic Retinopathy Evaluation Software (ADRES) images were graded by both a trained non-ophthalmologist grader (grader-1) and an ophthalmologist (grader-2). Sensitivity, specificity, positive predictive value and negative predictive value were calculated for grader-1 and grader-2 against the grading results by an independent retina specialist who performed dilated fundus examination for every study participant. RESULTS: Out of 1001 patients included, 42% were women and the mean ± (SD) age was 55.8 (8.39) years. For moderate or worse DR, the sensitivity and specificity for grading by grader-1 with respect to the gold standard was 66.9% and 91.0% respectively and the same for the ophthalmologist was 83.6% and 80.3% respectively. For referable DMO, grader-1 and grader-2 had a sensitivity of 74.6% and 85.6% respectively and a specificity of 83.7% and 79.8% respectively. CONCLUSIONS: Our results demonstrate good level of accuracy for the fundus image grading performed by a trained non-ophthalmologist which was comparable with the grading by an ophthalmologist. Engaging trained non-ophthalmologists potentially can enhance the efficiency of DR diagnosis using fundus images. Further study with multiple non-ophthalmologist graders is needed to verify the results and strategies to improve agreement for DMO diagnosis are needed.
Authors: R M Anjana; R Pradeepa; M Deepa; M Datta; V Sudha; R Unnikrishnan; A Bhansali; S R Joshi; P P Joshi; C S Yajnik; V K Dhandhania; L M Nath; A K Das; P V Rao; S V Madhu; D K Shukla; T Kaur; M Priya; E Nirmal; S J Parvathi; S Subhashini; R Subashini; M K Ali; V Mohan Journal: Diabetologia Date: 2011-09-30 Impact factor: 10.122
Authors: P Namperumalsamy; R Kim; T P Vignesh; N Nithya; J Royes; T Gijo; R D Thulasiraj; V Vijayakumar Journal: Br J Ophthalmol Date: 2008-12-17 Impact factor: 4.638
Authors: Zack van Allen; Maman Joyce Dogba; Michael H Brent; Catherine Bach; Jeremy M Grimshaw; Noah M Ivers; Xiaoqin Wang; Nicola McCleary; Sarah Asad; Zahraa Chorghay; Hina Hakim; Olivera Sutakovic; Olivia Drescher; France Légaré; Holly O Witteman; Mary Zettl; Janet Squires; Marie-Claude Tremblay; Arshad Randhawa; Gladys Lopez; Afifa Ben Guiza; Justin Presseau Journal: Diabet Med Date: 2020-11-11 Impact factor: 4.359