A Survey on Machine Learning Algorithms for Predicting Cardiovascular Disease

EasyChair Preprint 7969

Abstract

Cardiovascular disease(CVD) is a kind of disease that distress the heart or blood vessels (veins and arteries). It can be initiated by means of a mixture of socio-economic, behavioral, and ecological risk features, including high blood pressure, unhealthy diet, high cholesterol, diabetes, tobacco use, physical inactivity, harmful use of alcohol and stress. Family history, traditional background, sex, and age can also distress a person’s threat of cardiovascular disease. Machine learning algorithms can be used to predict the heart diseases more accurately and precisely. And the risk factors for heart disease can also be predicted effectively using Machine learning techniques and algorithms. This paper suggests a number of models built on algorithms and methods, to examine their performance. Best frequently used Supervised ML algorithms by the scholars are SVM, KNN, Decision Trees, Random Forest, Ensemble models.

Keyphrases: Feed-forward backpropagation, Machine Learning(ML), Random Forest, SMOTE, Waikato Environment for Knowledge Analysis(WEKA), neural network

@booklet{EasyChair:7969,
  author    = {R Sathya and J Shanthini and S Karthik},
  title     = {A Survey on Machine Learning Algorithms for Predicting Cardiovascular Disease},
  howpublished = {EasyChair Preprint 7969},
  year      = {EasyChair, 2022}}