Xiaoting Pei1, Xi Yao1, Yingrui Yang1, Hongmei Zhang2, Mengting Xia1, Ranran Huang1, Yuming Wang3, Zhijie Li4. 1. Henan Eye Institute, Henan Eye Hospital, and Henan Key Laboratory of Ophthalmology and Visual Science, Henan Provincial People's Hospital, People's Hospital of Zhengzhou University, People's Hospital of Henan University, Zhengzhou, China. 2. Nursing Department, Henan Provincial People's Hospital, People's Hospital of Zhengzhou University, People's Hospital of Henan University, Zhengzhou, China. 3. Departments of Science and Technology Administration, Henan Provincial People's Hospital, Henan University People's Hospital, Zhengzhou University People's Hospital, Zhengzhou, China. 4. Henan Eye Institute, Henan Eye Hospital, and Henan Key Laboratory of Ophthalmology and Visual Science, Henan Provincial People's Hospital, People's Hospital of Zhengzhou University, People's Hospital of Henan University, Zhengzhou, China. Electronic address: zhijielee@vip.163.com.
Abstract
AIM: To explore the efficacy of artificial intelligence (AI)-based screening for diabetic retinopathy (DR) in type 2 diabetes mellitus (T2DM) patients. METHODS: Data were obtained from 549 T2DM patients who visited the Fundus Disease Center at Henan Provincial People's Hospital from 2018/10-2020/09. DR identification and grading were conducted by two retina specialists, EyeWisdom®DSS and EyeWisdom®MCS, with ophthalmologist grading as reference standard, efficacy of EyeWisdom was evaluated according to sensitivity, specificity, positive predictive value, and negative predictive value. RESULTS: Ophthalmologists detected 324 DR cases. Among them, there were 43 of mild non-proliferative DR (NPDR), 79 of moderate NPDR, 61 of severe NPDR, and 141 of proliferative DR (PDR). EyeWisdom®DSS detected 337 DR and EyeWisdom®MCS detected 264 DR. Sensitivity and specificity of EyeWisdom®DSS were 91.0%(95 %CI: 87.3%-93.8%) and 81.3% (95 %CI: 75.5%-86.1%), while EyeWisdom®MCS correctly identified 76.2%(95 %CI: 71.1%-80.7%) of patients with DR and 92.4%(95 %CI: 87.9%-95.4%) of patients without DR. EyeWisdom®DSS showed 76.5%(95 %CI: 69.6%-82.3%) sensitivity and 78.4%(95 %CI: 73.7%-82.5%) specificity for detecting NPDR and 64.5%(95 %CI: 56.0%-72.3%) sensitivity and 93.1%(95 %CI: 90.1%-95.3%) specificity for diagnosing PDR. CONCLUSION: EyeWisdom®DSS is effective in screening for DR, and the accuracy of EyeWisdom®MCS was higher for identifying patients without DR. It is valuable to carry out AI-based DR screening in poorer regions.
AIM: To explore the efficacy of artificial intelligence (AI)-based screening for diabetic retinopathy (DR) in type 2 diabetes mellitus (T2DM) patients. METHODS: Data were obtained from 549 T2DM patients who visited the Fundus Disease Center at Henan Provincial People's Hospital from 2018/10-2020/09. DR identification and grading were conducted by two retina specialists, EyeWisdom®DSS and EyeWisdom®MCS, with ophthalmologist grading as reference standard, efficacy of EyeWisdom was evaluated according to sensitivity, specificity, positive predictive value, and negative predictive value. RESULTS: Ophthalmologists detected 324 DR cases. Among them, there were 43 of mild non-proliferative DR (NPDR), 79 of moderate NPDR, 61 of severe NPDR, and 141 of proliferative DR (PDR). EyeWisdom®DSS detected 337 DR and EyeWisdom®MCS detected 264 DR. Sensitivity and specificity of EyeWisdom®DSS were 91.0%(95 %CI: 87.3%-93.8%) and 81.3% (95 %CI: 75.5%-86.1%), while EyeWisdom®MCS correctly identified 76.2%(95 %CI: 71.1%-80.7%) of patients with DR and 92.4%(95 %CI: 87.9%-95.4%) of patients without DR. EyeWisdom®DSS showed 76.5%(95 %CI: 69.6%-82.3%) sensitivity and 78.4%(95 %CI: 73.7%-82.5%) specificity for detecting NPDR and 64.5%(95 %CI: 56.0%-72.3%) sensitivity and 93.1%(95 %CI: 90.1%-95.3%) specificity for diagnosing PDR. CONCLUSION: EyeWisdom®DSS is effective in screening for DR, and the accuracy of EyeWisdom®MCS was higher for identifying patients without DR. It is valuable to carry out AI-based DR screening in poorer regions.