Intensify Stroke Prediction Model Associated with Hypertensive State

Hypertension and stroke are significant worldwide health issues with high prevalence and complex health hazards. Hypertensive state implications include death or major complications such as myocardial infarction. This study leverages data from the Internet to foresee the prognosis for individuals with hypertensive strokes. There are two main components to the clinical outcome prediction in this study. The value of various variables is ranked by our model through the use of cross-validation techniques, recursive feature disposal, and classification algorithms such as Support Vector Machine (SVM), Random Forest (RF), and Logistic Regression (LR). Our empirical cross-validation results demonstrate the remarkable predictive reliability of both LR and RF once repetitive features are removed, even with a smaller set of features and classifiers. Particularly in terms of accuracy, F1 score, and area under the receiver operating characteristic curve (AUC), logistic regression performs better than the other two classifiers. Likewise, we conducted independent prediction analyses for hypertension, hypertensive stroke, and stroke. The highest result of 96.15% is obtained using logistic regression for stroke prediction. The random forest classifier has an accuracy of 91.25% for hypertension, and combining stroke with a hypertension support vector classifier gives 91.72% accuracy. This demonstrates how well it might provide patients with hypertensive strokes with precise and trustworthy projections. Finally, our study illuminates the potentially useful prediction powers of particular algorithms in determining the prognosis of patients with hypertensive strokes.