This study's primary objective was to develop and validate a novel graphical user interface based on a hierarchical fuzzy diabetic retinopathy detection tool titled as "An Accurate Hybrid Hierarchical Model for Diabetic Retinopathy Detection" for the rapid and accurate diagnosis of diabetic retinopathy. To diagnose diabetic retinopathy, three types of systems have been created, including intraocular pressure, vision field, visual acuity, blood glucose level, high-density lipoprotein (HDL), low-density lipoprotein (LDL), haemoglobin glycated sugar, blood pressure, and triglyceride. The hierarchical fuzzy expert system was constructed using IF-THEN rules based on the specialist's experiences, and these systems were evaluated using ophthalmoscopy. In addition, a fourth system has been created to detect anomalies in fundus pictures, such as microaneurysms, haemorrhages, exudates, and blood vessels, using a segmentation technique and classify them as belonging to a certain form of cancer using a random forest classifier. The hierarchical fuzzy expert system was determined to have 99% accuracy, 98% sensitivity, and 100% specificity after comparing fuzzy rules with health care professionals. The evaluation of the fundus image system revealed that it had an accuracy of 99.20%, AUC of 0.98, correctness of 0.97, Recall of 0.97, and F1 Score of 0.96

Diabetic Retinopathy, Hierarchical Fuzzy Expert System, Graphical User Interface, Adaptive Threshold Equalization .