The discovery of knowledge from medical databases is important in order to make effective medical diagnosis. The aim of data mining is to extract knowledge from information collected from various datastore and generate clear and understandable description of patterns. Applying machine learning and data mining methods in DM research is a key approach to utilizing large volumes of available diabetes-related data for extracting knowledge. The severe social impact of the specific disease renders DM one of the main priorities in medical science research, which inevitably generates huge amounts of data. The different machine learning algorithms namely SVM, SVM Kernel Linear, Logistic Regression, Decision tree, KNN, random forest algorithm and Bayesian classifier were used to make diabetes prediction. From the results obtained, it is very clear that random forest algorithm performs much better in terms of all the different performance measures when compared to all other machine learning algorithms.Thus, the results show that the machine learning algorithms can able to produce highly accurate diabetes predictive healthcare systems.
Volume 12 | 06-Special Issue
Pages: 263-272
DOI: 10.5373/JARDCS/V12SP6/SP20201031