Analysis and Prediction of the Effect of Stroke Prediction with Improved Accuracy Using Medium Tree and Coarse Gaussian Svm Classifiers

Stroke is one of the leading causes of death and permanent disability, stroke is a serious global health concern. Early detection of stroke risk factors can significantly enhance treatment results and lessen the financial load on healthcare systems. Based on clinical and demographic characteristics, this study proposes a machine learning-based predictive model that evaluates stroke risk using Medium Tree and Coarse Gaussian Support Vector Machine (SVM) classifiers. Several factors are included within the dataset, The dataset consists of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{1 8 0 0}$</tex> patient records which includes features such as age, marital status, type of work, heart disease, hypertension, average blood sugar, Body mass index (BMI), type of habitation, and smoking status. Missing value management, categorical variable encoding, feature scaling, and class balancing with the Synthetic Minority Oversampling Technique (SMOTE) were all part of the data preprocessing process. The models were trained and validated using MATLAB's Classification Learner Toolbox. Using critical criteria for evaluation, such as <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{F 1}$</tex>-score, accuracy, and recall, both classifiers showed excellent prediction performance. According to the study's findings, these classifiers can be dependable parts of intelligent clinical decision support systems, which could help doctors diagnose and treat patients early. Future studies might use dynamic patient data for real-time deployment and testing in clinical settings.