International Journal of Engineering and Advanced Technology (IJEAT) ISSN: 2249 – 8958, Volume-9 Issue-3, February, 2020 2404 Published By: Blue Eyes Intelligence Engineering & Sciences Publication Retrieval Number: B3986129219/2020©BEIESP DOI: 10.35940/ijeat.B3986.029320 Prediction of Cardiovascular Disease using Machine Learning Algorithms Muktevi Srivenkatesh Abstract: Background/Aim: Healthcare is an unavoidable assignment to be done in human life. Cardiovascular sickness is a general class for a scope of infections that are influencing heart and veins. The early strategies for estimating the cardiovascular sicknesses helped in settling on choices about the progressions to have happened in high-chance patients which brought about the decrease of their dangers. Methods: In the proposed research, we have considered informational collection from kaggle and it doesn't require information pre-handling systems like the expulsion of noise data, evacuation of missing information, filling default esteems if applicable and classification of attributes for prediction and decision making at different levels. The performance of the diagnosis model is obtained by using methods like classification, accuracy, sensitivity and specificity analysis. This paper proposes a prediction model to predict whether a people have a cardiovascular disease or not and to provide an awareness or diagnosis on that. This is done by comparing the accuracies of applying rules to the individual results of Support Vector Machine, Random forest, Naive Bayes classifier and logistic regression on the dataset taken in a region to present an accurate model of predicting cardiovascular disease. Results: The machine learning algorithms under study were able to predict cardiovascular disease in patients with accuracy between 58.71% and 77.06%. Conclusions: It was shown that Logistic Regression has better Accuracy (77.06 %) when compared to different Machine-learning Algorithms. Keywords: Cardiovascular disease, Machine Learning Algorithms, Performance Evaluators, toxins I. INTRODUCTION Classification is significant component of data mining. Classification is the way toward finding a model (or capacity) that depicts and recognizes information classes or ideas. The model is inferred dependent on the investigation of a lot of preparing cardiovascular data (i.e., data objects for which the class marks are known). The model is utilized to foresee the class name of items for which the class name is having the cardiovascular malady or not having cardiovascular ailment that is obscure. Machine Learning examines how computers can learn (or improve their exhibition) in view of cardiovascular information. The primary research zone is for computer projects to consequently figure out how to perceive complex examples and settle on clever choices dependent on cardiovascular data. Supervised learning is fundamentally an equivalent word for arrangement. The supervision in the taking in originates from the named models in the cardiovascular preparing data collection. Revised Manuscript Received on January 22, 2020. Dr. M. Srivenkatesh, Associate Professor, Department of Computer Science, GITAM Deemed to be University, Visakhapatnam, Andhra Pradesh, India. Cardiovascular malady (CVD) is expanding day by day in this cutting edge world. As per the World Health Organization (WHO), an expected 17 million individuals die every year from cardiovascular ailment, especially respiratory failures and strokes [1]. It is, in this way, important to record the most significant side effects and wellbeing propensities that add to CVD. Different tests are performed before conclusion of CVD, including auscultation, ECG, circulatory strain, cholesterol and glucose. These tests are regularly long and long when a ient's condition might be basic and the indivpatidual in question must beginning taking prescription quickly, so it gets imperative to organize the tests [2]. A few wellbeing propensities add to CVD. In this way, it is likewise important to know which wellbeing propensities add to CVD. Machine Learning is currently a developing field because of the expanding measure of information. Machine Learning makes it conceivable to secure information from a huge measure of information, which is overwhelming for man and here and there inconceivable [3]. The remaining of the research discussion is organized as follows: Section II briefs Literature , Section III describes brief description of selected machine learning algorithms Section IV describes Patient Data Set and attributes, Section V discusses Proposed Technique ,Section VI Describes Performance measure of classification, Section VII briefs discussion and evaluated Results, and Section VIII determines the Conclusion of the research work and last Section describes References . A. Cardiovascular disease Cardiovascular infection, by and large, alludes to conditions that include limited or blocked veins that can prompt a coronary episode, chest torment (angina) or stroke. Other heart conditions, for example, those that influence your heart's muscle, valves or cadence, likewise are viewed as types of coronary illness. Cardiovascular malady incorporates conditions that influence the structures or capacity of your heart, for example, ฀ Coronary supply route infection (narrowing of the courses) ฀ Heart assault. ฀ Abnormal heart rhythms, or arrhythmias. ฀ Heart disappointment. ฀ Heart valve infection. ฀ Congenital coronary illness. ฀ Heart muscle sickness (cardiomyopathy)