“…Maniruzzaman et al developed a model with superior performance to detect DN using SVM-RBF (support vector machine-radial basis function) with 13 parameters (sex, age, BMI, DM duration, FBS, HbA1c, LDL, HDL, TGs, SBP, DBP, DM treatment, use of statins), and the accuracy and AUC were 88.7% and 0.9, respectively, when validated [ 22 ]. Satish Kumar David et al developed a detection model for DKD with an accuracy of 93.7% using IBK and random tree classification techniques through 18 parameters (age, sex, serum albumin, sodium, potassium, urea, glucose, creatinine, HbA1c, hemoglobin, white blood cell counts, red blood cell counts, hemoglobin (%), platelet counts, SBP, DBP, hypertension, and retinopathy) [ 19 ]. However, most biochemical parameters are not convenient enough, and retinal vascular parameters have not been used in formal models, although a large number of studies have indicated that retinal changes are related to DKD [ 1 , 9 ].…”