<![CDATA[The number 1 diseases that take up to 17 million lives annually are Cardiovascular diseases (CVDs). CVDs mistreatment would increase the risk dramatically to the point that saving the patient deemed impossible. The dataset used in this research originated from RSUP DR. M Djamil Padang from January 2014, until July 2014 with 426 entries and seven columns, the data also digitized in CSV form from the log journal with a lot of wrong data input because the data has not been standardized yet. The proposed method analyses the pattern of patient diagnosis, age, insurance, origin, and gender using Support Vector Machine (SVM) and predicts the appropriate treatment for the patient. In the process, SVM drew a hyperplane for each target class in the transformed training set by the radial basis function (RBF), and classify the target data. Simulation results on CVDs treatment prediction show 50% accuracy, which then improved by Gaussian Process optimizer and the score increased to 66%.]]>
Copyrights © 2019
