Expert System for Early Diagnosis of Heart Disease Using the Random Forest Method

Abstract

In Indonesia, coronary heart disease continues to grow. However, the efforts to prevention it can still be done by diagnosing the initial symptoms caused by using an expert system. This study was designed to build an expert system application to diagnose early coronary disease by random forest methods. The application interface was built using the PHP programming language using framework bootstrap, and uses the python programming language to build a random forest. To make an early diagnosis of coronary heart disease, a decision tree was built by training data from the UCI Dataset Machine Learning Repository using the random forest method. Followed by patient classification data that has been collected through 13 questions to get the diagnosis. The diagnosis results were normal, stadium 1, stadium 2, stadium 3 and stadium 4. Based on the tests that had been carried out, the application was able to provide results in accordance with the sample data collected using a confusion matrix resulting in an accuracy of 92.25% +/- 0.62 with 70% precision, remember 46%, which obtained a score of f0,5 72%.