Investigating myocardial infarction and its effects in patients with urgent medical problems using advanced data mining tools

TL;DR

This study compares various data mining algorithms to predict myocardial infarction in emergency patients, identifying key features and achieving a 76% accuracy with random decision forests.

Contribution

It introduces a comparative analysis of data analysis algorithms for myocardial infarction prediction using real patient data and identifies the most effective features and model.

Findings

Random decision forests achieved 76% accuracy.

Seven key features significantly influence myocardial infarction prediction.

The study highlights the importance of specific blood tests and emergency operation timing.

Abstract

In medical science, it is very important to gather multiple data on different diseases and one of the most important objectives of the data is to investigate the diseases. Myocardial infarction is a serious risk factor in mortality and in previous studies, the main emphasis has been on people with heart disease and measuring the likelihood of myocardial infarction in them through demographic features, echocardiography, and electrocardiogram. In contrast, the purpose of the present study is to utilize data analysis algorithms and compare their accuracy in patients with a heart attack in order to identify the heart muscle strength during myocardial infarction by taking into account emergency operations and consequently predict myocardial infarction. For this purpose, 105 medical records of myocardial infarction patients with fourteen features including age, the time of emergency operation, Creatine Phosphokinase (CPK) test, heart rate, blood sugar, and vein are gathered and investigated through classification techniques of data analysis including random decision forests, decision tree, support vector machine (SVM), k-nearest neighbor, and ordinal logistic regression. Finally, the model of random decision forests with an accuracy of 76% is selected as the best model in terms of the mean evaluation indicator. Also, seven features of the creatine Phosphokinase test, urea, white and red blood cell count, blood sugar, time, and hemoglobin are identified as the most effective features of the ejection fraction variable.