Prediction of Heart Disease Attack Risk using Deep Learning Algorithm

The heart is a muscular organ that acts as the main pump in the human circulatory system, pumping oxygen-rich blood throughout the body and returning blood containing carbon dioxide to be purified. Coronary heart disease, caused by arterial blockages due to plaque buildup (fat, cholesterol, and other substances), is often the leading cause of heart attacks as blood flow to the heart muscle is reduced. This condition is one of the leading causes of death worldwide, making it necessary to have an accurate method to detect this disease early. This study aims to help predict the risk of heart disease based on gender using data mining. Data mining facilitates heart disease diagnosis, particularly in helping doctors determine whether a patient suffers from heart disease based on early symptoms that appear. The author uses five data mining algorithms: Naïve Bayes, K-Nearest Neighbor (KNN), Decision Tree, Random Forest, and Deep Learning. The research results show that the Deep Learning model is the best algorithm for predicting heart disease symptoms. Additionally, using the right predictive model can help reduce the risk of delayed diagnosis. Therefore, the predictive model with this algorithm is recommended for implementation in hospitals to help detect heart disease symptoms in patients more accurately and efficiently. This way, early diagnosis can be made to improve patient recovery chances and reduce mortality rates due to heart disease.