Evaluation of retinopathy status in diabetic patients At national hospital of endocrinolory

Abstract

Objective: 1. Describe the clinical characteristics of diabetic retinopathy at National Hospital of Endocrinology. 2.Assess the stage of diabetic retinopathy and related factors. 3. Survey on artificial intelligence applications to evaluate the retina in diabetic patients. Materials and methods: The study was conducted on patients diagnosed with type 1 and type 2 diabetes at National Hospital of Endocrinology from September 2022 to September 2023. Cross-sectional descriptive study on 450 patients with 900 eyes. The results of fundus images were classified by an ophthalmologist and compared with the results of Cybersight AI software by the classification standards of the 2017 International Council of Ophthalmology (ICO). Results: The average age of the patients in the study was 58.76 ± 12.14 years old, the proportion of female patients was more dominant than male patients, accounting for 54.9%. Patients with type 2 diabetes account for the highest rate of 91.9%. The average duration of diabetes was 7.92 ± 6.94 years, and the group of diabetic patients who was detected for more than 15 years accounting for the majority at 34.9%. The prevalence of diabetic retinopathy was 27.3% with 246 eyes. The stage of DR at diagnosis with the highest rate is the moderate non-proliferative stage with more than 10.7%. There are 4.1% of eyes diagnosed with proliferative stage. There is a close relationship between HbA1C concentration, disease duration with p < 0.05. When analyzing retinal images through the AI image reading system of Cybersight AI software, the rate of diabetic retinopathy accounts for 24.4%. The moderate non- proliferative stage accounts for the highest rate at 11.0 %. Eyes without diabetic retinopathy lesions account for 72.7%. - The sensitivity of the AI system on Cybersight software compared with the image reading results of a clinical ophthalmologist is 76.7%, specificity 93.9%, positive predictive value 82.0%, negative predictive value 91.8%, accuracy 89.3%. Conclusion: The rate of diabetic retinopathy was 27.3% at National Hospital of Endocrinology. AI system on Cybersight software on 642 eyes of 321 patients. The sensitivity of the AI system on Cybersight software compared with the image reading results of a clinical ophthalmologist is 76.7%, specificity 93.9%, positive predictive value 82.0%, negative predictive value 91.8%, accuracy 89.3%.