An Experiment on Various Classification Methods for Predicting Cardio Vascular Disease

EasyChair Preprint no. 10698

Abstract

The heart is regarded as one of the body's most significant and complex organs, as is generally accepted. Without it, most life forms will disappear. Because the heart's primary function is to pump blood to all of the body's organs and distribute it there, it plays a crucial role. Because of this, heart-related conditions are extremely delicate and require extreme caution. It is often said that prevention is better than cure. Most cardiac disorders tend to be identified after they have actually transpired. However, research has demonstrated that, with advance warning, approximately 90% of cardiovascular diseases can be prevented. We can determine the relationship between age, blood pressure, gender, and other variables from the findings of this study. Through their investigation, we will be able to gain a better understanding how these variables affect cardiovascular health. Along with other classification models, we simulate KNN, Gaussian Naive Bias, Decision Trees, Logistic Regression, SVM, Random Forests and others. Predicting whether a heart condition is present early on is critical. It provides medical foresight and aids in numerous potentially fatal situations. This paper provides an overview of the existing work as well as an insight into the existing algorithm.

Keyphrases: Cardio Vascular Disease (CVD), Decision Tree, K-Nearest Neighbor (KNN), logistic regression, Random Forest., Support Vector Machine (SVM)

@Booklet{EasyChair:10698,
  author = {Maya B Dhone and Swathi Voddi and Swarna Kamalam Vaddi},
  title = {An Experiment on Various Classification Methods for Predicting Cardio Vascular Disease},
  howpublished = {EasyChair Preprint no. 10698},

  year = {EasyChair, 2023}}