ĐÁNH GIÁ TÌNH TRẠNG VÕNG MẠC TRÊN BỆNH NHÂN ĐÁI THÁO ĐƯỜNG TẠI BỆNH VIỆN ĐA KHOA ĐỨC GIANG

Abstract

Objectives: Describe the clinical characteristics of diabetic retinopathy at Duc Giang General Hospital; Assess the stage of diabetic retinopathy and its related factors; Conduct a survey on the applications of artificial intelligence in evaluating retinas of diabetic patients. Materials and methods: The study included patients diagnosed with diabetes who sought examination and treatment at the Eye Clinic of Duc Giang General Hospital. The research was conducted from August 2022 to July 2023, employing a cross-sectional descriptive study approach involving 150 patients. Participants were individuals diagnosed with diabetes who willingly participated and were randomly selected based on the medical examination list until the required sample size was reached. Color fundus images were examined by a vitreoretinal fluid specialist using the 2017 International Council of Ophthalmology (ICO) classification standards and were compared with the outcomes obtained from the Cybersight AI artificial intelligence application software. Results: The average age of patients in the study was 67.42 (±9.68) years old, with a predominant representation of women, and type 2 diabetes accounting for the majority at 96.7%. The primary duration of the disease was less than 5 years, constituting 65.3%. The prevalence of diabetic retinopathy was 44.66%. The most common retinal lesions observed were microaneurysms (44.67%), hard exudates (22%), retinal hemorrhages (20%), and macular edema at 15.78%. HbA1C concentration, disease duration, and retinal damage showed a significant association with p < 0.05. While dyslipidemia and blood pressure didn't exhibit a direct association with retinal damage in the study group, individuals with diabetic retinal damage in our study presented with dyslipidemia (60.67%) and hypertension (53.33%). The Cybersight AI software demonstrated a sensitivity of 95.61%, specificity of 89.62%, and an accuracy of 91.92% in diagnosing diabetic retinopathy. Conclusion: The rate of diabetic retinopathy is 44.66%. The study did not identify a significant relationship between hypertension, dyslipidemia, and diabetic retinopathy. However, it did reveal a close association between the HbA1c factor and the duration of diabetes with diabetic retinopathy. The application of artificial intelligence for screening diabetic retinopathy exhibits very high sensitivity and specificity.