Detection of Stroke (Cerebrovascular Accident) Using Machine Learning Methods

Abstract

Stroke occurs when the blood flow to the brain is suddenly interrupted. This interruption can lead to the loss of function in the affected area of the brain and cause permanent damage to the corresponding part of the body. Stroke can develop due to various factors such as age, occupation, chronic diseases, and a family history of stroke. Assessing these factors and predicting stroke risk is often a costly and timeconsuming process, which can increase the risk of permanent damage for the individual. However, with today's technology, Artificial Intelligence (AI) and Machine Learning (ML) models can process millions of data points to determine stroke risk within seconds. In this study, the risk of stroke in individuals is predicted most reliably using ML methods such as Logistic Regression (LR), Decision Tree (DT), Support Vector Machines (SVM), and k-Nearest Neighbors (KNN), with the aim of saving time, protecting human health, and enabling early diagnosis of the disease. As a result of the study, the highest accuracy rate was achieved by the DT model with 91%. The accuracy rates of the other models were found to be 89% for SVM, 81% for KNN, and 75% for LR.