S.Prasanth et al., International Journal of Advanced Trends in Computer Science and Engineering, 10(2), March - April 2021, 874 – 887 874 S.Prasanth 1 , M. Roshni Thanka 2 , E. Bijolin Edwin 3 1 Department of Computer Science and Engineering, Karunya Institute of Technology and Sciences, Coimbatore, Tamil Nadu, India. E-mail ids: sprasanth19@karunya.edu.in 2 Department of Computer Science and Engineering, Karunya Institute of Technology and Sciences, Coimbatore, Tamil Nadu, India. E-mail ids: roshni@karunya.edu 3 Department of Computer Science and Engineering, Karunya Institute of Technology and Sciences, Coimbatore, Tamil Nadu, India. E-mail ids: bijolin@karunya.edu ABSTRACT The aim of the study is to compare, assess the optimum tools as well as the techniques and advanced features focused on prediction of diabetes diagnosis based on machine learning tactics and diabetic retinopathy using Artificial Intelligence. The literature on data science, Artificial Intelligence (AI) contains important knowledge and understanding of AI entities such as Data science, machine learning, deep learning, Medical image processing, feature extraction, classification techniques, etc. Diabetes diagnosis is a phenomenon that impacts individuals around the globe. Now, with diabetes impacting people from children to the elderly, the out-dated approaches to diabetes diagnosis should be replaced with new, time-saving technologies. There's several studies carried out by researchers to recognise and predict diabetes. Here plenty of classifiers in machine learning can be used, such as KNN, Random Tree, etc.They can save time and get more precise outcome when using these techniques to predict diabetes. Diabetic retinopathy (DR) is a typical disorder of diabetic disease that induces vision-impacting lesions in the retina. It also can turn to visual impairment if it is not addressed early. DR therapy only helps vision. Deep learning has in recent times being one of the most widely used approaches that has accomplished higher outcomes in so many fields, especially in the analysing and identification of medical image classification. In medical image processing, convolutional neural networks (CNN) using transfer learning are commonly used as a deep learning approach and they are incredibly beneficial. Key words: Diabetic Retinopathy (DR), Artificial Intelligence , Machine Learning strategies, Deep learning , Transfer learning, Medical Image Processing ,Feature extraction, Classifiers. 1. INTRODUCTION Diabetes diagnosis is a group of chronic illnesses wherein glucose levels or sugar levels stay abnormally high for extended spans of time Frequent urination, elevated appetite, and increased hunger are signs of high blood sugar. Diabetes can cause multiple problems if left unchecked. Diabetic ketoacidosis, hyperosmolar hyper-glycaemic condition, or death may be acute complications. Cardiovascular disease, stroke, progressive kidney disease, foot ulcers, and eye injury are serious long- term risks. Diabetes mellitus, also known as diabetes, is another metabolic disorder that causes elevated blood sugar. The enzyme insulin transports sugar from the blood into the cells for absorption or use for eating. The body either doesn't have sufficient insulin for diabetes or doesn't use the insulin it produces effectively. But also untreated excessive blood sugar from diabetes can be affected in the liver, eye, lungs, kidneys, and other organs. One of the most severe and chronic conditions that cause blood sugar to increase is considered to be diabetes. Several risks occur as diabetes remains unchecked and unexplained. The exhausting identification process consists of a patient visiting and consulting a consultant at a medical centre. Yet this key issue is answered by the rise in approaches to machine learning. Classification approaches are widely used in the medical field to classify data subject to such constraints according to a single classifier in multiple classes. Diabetes is a disorder that inhibits the bodies natural capacity to regulate insulin receptors, which in turn induces unhealthy carbohydrate metabolism and increases blood glucose levels. High blood pressure is typically caused by diabetes. Intensifying hunger, intensifying appetite, and frequent urination are all the signs induced by increased blood sugar. Because diabetes is left uncontrolled, it causes a A detailed survey on Prognostication of diabetes diagnosis on the basis of machine learning techniques and the detection approaches to diabetic retinopathy using Artificial Intelligence ISSN 2278-3091 Volume 10, No.2, March - April 2021 International Journal of Advanced Trends in Computer Science and Engineering Available Online at http://www.warse.org/IJATCSE/static/pdf/file/ijatcse571022021.pdf https://doi.org/10.30534/ijatcse/2021/571022021