Abstract
Coronary Heart disease is the global leading cause of death, accounting for 17.3 million deaths per year, and this number is expected to grow to more than 23.6 million by 2030 [20]. In healthcare, coronary artery diseases were found on the top of the healthcare problems, that many countries are facing nowadays. Data mining techniques have been widely used in many governmental sectors including healthcare to mine knowledgeable information from medical data. The current health care organizations use manual heart rate risk scoring models such as Framingham to calculate the early risk of coronary artery diseases. Due to the growing population and increase in the number of patients at health care, the manual process is becoming inefficient to treat the condition which may demand immediate treatment. In this research work, we are proposing an automated system for early risk classification of hard coronary heart diseases using Framingham scoring model. K-Nearest Neighbor and Random Forests algorithms were applied for heart rate risk prediction and the obtained results were compared to the results obtained through the manual process to measure the accuracy level. It was observed that, our proposed automated system for heart rate risk prediction using Framingham model was highly accurate when compared to the manual process. This work attempts to report the effectiveness of using K-Nearest Neighbor and Random Forests for Framingham heart and medical decision support in cardiology field.