Chakrabarty, AmitabhaAfrose, SadiaRubaiat, FarahTabassum, Homayra2021-10-182021-10-1820212021-06ID 17101546ID 17101540ID 17301068http://hdl.handle.net/10361/15348Cataloged from PDF version of thesis.Includes bibliographical references (pages 42-44).This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2021.In this thesis we have examined the accuracy of various classifiers to predict heart disease and heart vessel blockage. We have also analyzed the key features contribut ing to heart vessel blockage. We have used a dataset containing 14 attributes related to heart disease of 1025 patients. From our study we found that the Decision Tree, Random Forest and KNN algorithm gave the highest accuracy for detecting heart disease. For predicting heart vessel blockage, the Decision tree had the highest accuracy. While analyzing the features contributing to heart vessel blockage, we found that patients’ age and cholesterol level has the highest contribution. Hence, monitoring the patient’s cholesterol level may help prevent heart vessel blockage.44 pagesenBrac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission.Heart DiseaseCoronary Artery BlocksChest PainMachine LearningAnginaDisease PredictionCatBoostXGBoostAdaBoostDecision TreeSVMKNNNaive BayesLogistic RegressionLinear RegressionMachine LearningThesis