Novel Implementation of Cardio Vascular Disease Using Machine Learning Techniques

EasyChair Preprint 8216

Abstract

The medical field is growing at a rapid pace with new diseases cropping up daily with the need for the invention of an appropriate course of treatment. The heart is a clenched human fist-sized muscular organ, which is responsible for the blood circulation. Though heart/cardiac disease is the name given to diseases affecting the heart in general, many diseases come under this name including coronary artery diseases (CAD), cardiomyopathy, Cardio Vascular Disease (CVD), and so on depending on the circulation of blood throughout the body. To support clinicians in the diagnosis of heart disease, heart disease data prediction has been so designed to analyze medical data with clinical expertise. Through improvement in these predicting systems, there can be an enhancement in the quality of medical diagnostic decisions for heart disease. Data mining plays a crucial part in the prediction of cardiac disease. In this work, the Naïve Bayes (NB) classifier, C4.5 classifier, and Artificial Neural Network (RNN)-Back Propagation (BP) methods are used. These traditional methods are utilized for predicting heart disease. When the dimensionality of the input is huge, the NB classifier method derived from the Bayesian theorem is used. Despite being simple, it performs better than other protocols. The C4.5 protocol builds decision trees from a training data set by utilizing data entropy perception. It is a well-known and used protocol and is also called the statistical classifier. For solving several decision modeling problems, RNN has been utilized as a tool in typical cases. The use of RNNs is evidenced in areas of modeling, pattern recognition, data processing, and sequence recognition systems.

Keyphrases: Data Leak Reduction, EHR, Security, Sub Carrier

@booklet{EasyChair:8216,
  author    = {R Ramkumar and M.O Ramkumar},
  title     = {Novel Implementation of Cardio Vascular Disease Using Machine Learning Techniques},
  howpublished = {EasyChair Preprint 8216},
  year      = {EasyChair, 2022}}