Machine Learning and Data Mining in Diabetes Diagnosis and Treatment

摘要

The remarkable progress of biotechnology and medical science has created the considerable amount of biomedical data. Diabetes mellitus (DM), a common chronic disease, has also been generated a large number of medical data in the process of diagnosis and treatment. So the exploration of medical data has become a hotpot. Nowadays, researchers are using machine learning to discover potentially valuable knowledge in medical data more than ever before. The purpose of this study is to systematically collate and review the application of machine learning, data mining method and supplement tools in the diabetes research field. Through sorting out, it was found that: a) the clinical data-sets were mainly used, b) about 82% of the articles based on diverse supervised machine learning method, c) deep learning method was widely used by researchers and the good experimental result have been achieved.