Download PDFOpen PDF in browser

Recognize the Most Effective Exploratory Data Analysis and Machine Learning Methods for Predicting the Chances of Having a Heart Attack

EasyChair Preprint no. 6488

6 pagesDate: August 31, 2021

Abstract

Every year, around 17.9 million people die as a result of cardiovascular illnesses, the majority of which are heart attacks or strokes. As a result, it is critical to keep track of the most prevalent symptoms and health behaviors related to cardiovascular disease (CVD). These tests can take a long time, especially if a patient's health is urgent and they need to start taking medication right away, so they must be prioritized. A variety of hazardous behaviors contribute to the development of heart disease. As a result, determining which risk factors for CVD exist is essential. Exploratory Data Analysis and Machine Learning enable the extraction of information from enormous amounts of data that would be hard to process manually. This article will review diagnostic testing and go through a variety of cardiovascular risk factors. The essay is chock-full of cutting-edge data analysis and machine learning techniques. We demonstrate the use of exploratory data analysis (EDA) and other techniques such as logistic regression, KNN, decision trees, Random Forest, support vector machines, gradient boosting, XG Boost, MLP classifier, and AdaBoost classifier. The collection has 303 samples, each with 14 distinct features. The chance of contracting the disease increases significantly, and a number of diagnostic criteria are used to assess the disease's diagnostic accuracy. The XG boost classifier outperforms all other models in the data set, with an accuracy of 95.08 percent. It is capable of properly identifying 96.55 percent of those who are in danger. With a total accuracy of 93.44 percent, Adaboost and the MLP classifier performed admirably in our classification model. This study highlights the most promising machine learning approaches for predicting the likelihood of heart attacks. We demonstrated that adopting some approaches might be useful for implementing preventative measures for heart disease patients.

Keyphrases: Cardiovascular Disease (CVD), classification algorithms, exploratory data analysis, Healthcare, heart attack prediction, machine learning

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
@Booklet{EasyChair:6488,
  author = {Sm Mahamudul Hasan and Md Forhad Rabbi and Mohammad Rubbyat Akram},
  title = {Recognize the Most Effective Exploratory Data Analysis and Machine Learning Methods for Predicting the Chances of Having a Heart Attack},
  howpublished = {EasyChair Preprint no. 6488},

  year = {EasyChair, 2021}}
Download PDFOpen PDF in browser