Comparison of Logistic Regression and Support Vector Machine in Predicting Stroke Risk

Abstract

The issue of health is the third goal of Indonesia's Sustainable Development Goals (SDGs) which is state to ensuring a healthy life and promoting prosperity for all people at all ages. One of the SDGs’s concerns is deaths caused by non-communicable diseases (NCDs) including strokes. One prevention that can be done is by making a prediction of stroke for early detection. There are various methods available which are statistical methods and machine learning methods. In this research work, we aim to compare the two methods based on statistical method and machine learning method on stroke risk prediction. The data used in this research is primary data from Universitas Airlangga Hospital (RSUA) from June until August 2023. In this research, we compare the statistical method that is Logistic Regression (LR), and the machine learning method which is Support Vector Machine(SVM). We use Phyton to analyze all methods in this research. The results show that SVM with Radial Basis Kernel is better than LR in predicting stroke risk based on three goodness criteria namely sensitivity, F-1 score and accuracy where these three goodness criteria values of SVM are greater than those of LR.