Diabetes Detection and Monitoring using Data Mining and Machine Learning

Abstract

Machine learning is a field of study of algorithms and statistical models that computer systems deploy to execute certain jobs without using explicit directions, depending on inference and patterns instead. Data mining is the process of extracting non-trivial or useful data from a large amount of data. Diabetes Mellitus is a collection of multiple metabolic disorders having a significant impact on the health of a human being. Substantial research on a vast number of patients has led to the collection of vital data. Several techniques are there in the medical field to detect if a person has diabetes. The aim of this paper is the early detection of diabetes in people. This will help to take the necessary precautions at the right time so that it could be monitored and controlled. A lot of parameters are considered as input, which could help in predicting the disease and detect whether the patient has a chance of acquiring diabetes or not shortly using data mining and machine learning techniques. K Nearest Neighbour and Boosting algorithm are used to identify the same, and a comparison between various algorithms is made.