Heart Disease Classification Using Deep Neural Network with SMOTE Technique for Balancing Data

Abstract

Heart disease is the leading cause of premature death worldwide. According to the WHO, heart disease causes about 30% of the total 58 million deaths and mainly occurs in individuals who are in their productive age. Several studies have been conducted to anticipate this heart disease. Various algorithms, methods, and data balancing techniques have been applied, but still need to be done to get better accuracy results. Therefore, this research aims to classify heart disease using the Deep Neural Network algorithm and SMOTE technique to overcome data imbalance. This research resulted in a validation accuracy of 90% with a precision evaluation of 0.85, recall of 0.92, and f1-score of 0.88. Based on the results, the Deep Neural Network algorithm after SMOTE is superior to the model without SMOTE.