التنبأ بأمراض القلب باستخدام الانحدار اللوجستي

Abstract

Heart disease is one of the most common diseases in the world today and the most terrifying as it causes many deaths. We are now in the data age where huge amounts of data are collected and stored in the internet from different parts of the world (from companies, social networking sites, medical clinics, etc...). In this research work, we seek to build a model that predicts heart disease to improve early general diagnosis around it, that is, using logistic regression as a kind of classification without the help of a set of ready-made functions for machine learning, and that is based on a set of data consisting of 319,795 examples that help train the model and compare the results of Model with sklearn logistic regression algorithm and some other classification algorithms (SVM(SVC), NN, RF, KNN, DT, NBC). where the accuracy rate in our model was good (74%), which is very close to the rest of the sklearn classification algorithms, which were between 70% and 76% accuracy.