UTILIZING MACHINE LEARNING TO PREDICT CARDIOVASCULAR DISEASE

Abstract

One of the diseases whose annual mortality toll is rising is heart disease. Heart illness early diagnosis enables the patient to receive therapy more quickly. For the purpose of early cardiac disease diagnosis , the machine learning classification algorithms Decision Tree, SVM, and KNN were employed. Data collection, pre-processing, model creation, model comparison, and evaluation are the steps involved in creating the manufacturing process model. The leading cause of death worldwide for a long time has been cardiovascular disease. The need for cardiovascular disease prediction is urgent due to the high mortality rate of the condition. As information technology develops, many studies have been conducted on a computer-assisted diagnosis for heart disease.Time and money can be saved by a computerised system that detects heart disease. Cardiovascular diseases (CVDs) are responsible for 17.9 million annual deaths worldwide, or 31% of all fatalities. Four out of every five CVD deaths result from heart attacks or strokes, with premature deaths accounting for a third of these deaths in people under the age of 70. Eleven features in this dataset can be used to anticipate a potential heart condition. Because cardiovascular disease has a high mortality rate, the issue of predicting it is becoming more and more urgent. In our paper, the algorithms' accuracy was highlighted by the following numbers: Decison Tree = 80.97%, SVM = 68.47% ,Naive Bayes =84.23%, and KNN = 65.21% which shows Naive Bayes is the highest.