A Hybrid Intelligent System Framework for Detecting and Predicting Risk of Cardiovascular Disease
Keywords:
Cardiovascukar disease, Decision tree, Heart disease, K-nearest neighbour, Logistic regression, Naive bayes, Random forest, Support vector machine, XG boostAbstract
Number of deaths is increasing everyday especially due to heart disease in the present-day world. The cardiovascular diseases can appear due to family history, obesity, smoking etc. Prevention of death due to heart failure and proper treatment requires on time and accurate diagnosis of the disease. In this study we predict heart disease using a system that is based on machine learning using heart disease dataset. In this paper we try analysing and predicting heart diseases occurring by applying algorithms such as K-Nearest Neighbour, Naive Bayes, Support Vector Machine, Decision Tree, Random Forest, Logistic Regression, XG Boost. We have taken the dataset from UCI Machine Learning Repository. The algorithms results based on different factors like cholesterol, age, gender etc. The resulting performance provides efficiency in diagnosing the disease.
