Heart disease classification using data mining tools and machine learning techniques

Nowadays, in healthcare industry, data analysis can save lives by improving the medical diagnosis. And with the huge development in software engineering, different data mining tools are available for researchers, and used to conduct studies and experiments. For this, we have decided to compare six common data mining tools: Orange, Weka, RapidMiner, Knime, Matlab, and Scikit-Learn, using six machine learning techniques: Logistic Regression, Support Vector Machine, K Nearest Neighbors, Artificial Neural Network, Naïve Bayes, and Random Forest by classifying heart disease. The dataset used in this study has 13 features, one target variable, and 303 instances in which 139 suffers from cardiovascular disease and 164 are healthy subjects. Three performance measures were used to compare the performance of the techniques in each tool: the accuracy, the sensitivity, and the specificity. The results showed that Matlab was the best performing tool, and Matlab’s Artificial Neural Network model was the best performing technique. We concluded this research by plotting the Receiver operating characteristic curve of Matlab and by giving several recommendations on which tool to choose taking into account the users experience in the field of data mining.