Abstract: In most cases, heart disease diagnosis depends on a complex combination of clinical and pathological data. Because of this complexity, there is a significant amount of interest among clinical professionals and researchers regarding efficient and accurate heart disease prediction. In this paper, we develop a heart disease prediction system that can assist medical professionals in predicting heart disease status based on the clinical data of patients. The system will consist of multiple features, including an input clinical data section, ROC curve display section, and prediction performance display section (execute time, accuracy, sensitivity, specificity, and predict result). The paper also discusses the pre-processing methods, classifier performances, and evaluation metrics. We have investigated the accuracy levels of various machine learning techniques such as Support Vector Machines (SVM), K-Nearest Neighbor (KNN), Naive Bayes, and Decision Trees (DT). In the result section, the visualized data shows that the prediction is accurate. The system developed in this study proves to be a novel approach that can be used in the classification of heart disease.
Keywords: Statistical Description and Dispersion, Correlation, Feature Analysis, Classification, K-Nearest Neighbor, Decision Tree, Support Vector Machines, Naive Bayes
|
DOI:
10.17148/IJARCCE.2024.134183
