Intelligent Computational Model for Early Heart Disease Prediction using Logistic Regression and Stochastic Gradient Descent (A Preliminary Study)

Abstract

Heart disease, also known as cardiovascular disease (CVDs) caused major death worldwide. Heart disease couldcan be diagnosed using non-invasive and invasive methods. The main distinctions for invasive and non-invasive tests were invasive test use medical equipment entering the human body while non-invasive tests did not. This study was designed a model for non-invasive prediction with an intelligent computational and machine learning approach for predicting early heart disease. Logistic regression and stochastic gradient descent applied for this model. A clinical dataset of 303 patients was gathered from the UCI repository that was available at http://archive.ics.uci.edu/ml/datasets/Heart+Disease. Age, Sex, Cp, Trestbps, Chol, Fbs, Exang Continuous Maximum heart rate achieved, Thalach, Old peak ST, Slope, Ca and Thal variables were used to classify the patient into two class prediction namely No presence or Have heart disease. Classifier performance for logistic regression namely accuracy 91.67%, precision 93.93%, F Measure 92.53%, recall 91.18% and for gradient descent namely accuracy 80.00%, precision 76.47%, F Measure 81.25%, recall, 86.67%. The experiment result revealed logistic regression gained higher accuracy, precision, F -measure and recall value than stochastic gradient descent.