Cardiovascular Disease Prediction Using Machine Learing

EasyChair Preprint 12649

Abstract

Cardiovascular disease (CVD) remains a significant cause of mortality globally, with high prevalence rates in countries like India. Early detection and accurate prediction of CVD are crucial for timely intervention and treatment. In this study, we employ various machine learning techniques to analyze a dataset containing multiple factors associated with heart disease. Data preprocessing, exploratory data analysis, feature correlation analysis, and model building are performed to predict the occurrence of heart disease. Support Vector Machines (SVM), K-Nearest Neighbor (KNN), Decision Trees (DT), Logistic Regression (LR), and Random Forest (RF) algorithms are evaluated for their predictive performance. The results provide insights into the effectiveness of different machine learning approaches in detecting cardiovascular disease. This  paper investigates that which technique gives more accuracy in predicting heart disease based on health  parameters.  Experiment  show  that Naïve  Bayes  has  the  highest  accuracy  of 88%.

Keyphrases: K-Nearest Neighbor, Random Forest, Support Vector Machines, decision trees, logistic regression

@booklet{EasyChair:12649,
  author    = {Parthsarthi Bhatt and Agravat Smit and Priyanshu Anand and Vishal Kumar and Amar Chandra},
  title     = {Cardiovascular Disease Prediction Using Machine Learing},
  howpublished = {EasyChair Preprint 12649},
  year      = {EasyChair, 2024}}