Elastic Net – MLP – SMOTE (EMS)-Based Model for Enhancing Stroke Prediction

Abstract

A stroke is a sudden disruption in the blood supply to the brain, affecting one or more blood vessels that nourish the brain. This results in a disturbance or deficiency in the brain's oxygen supply, causing damage or impairment to brain cells. In some cases, determining the timing and severity of a stroke can be challenging. This study proposes an EMS (Elastic Net - MLP - SMOTE) model built on artificial intelligence, specifically utilizing two machine learning algorithms, Elastic Net and Multilayer Perceptron (MLP) with using Synthetic Minority Over-sampling Technique (SMOTE). The Elastic Net algorithm was employed for feature selection to identify crucial features, followed by prediction using the Multilayer Perceptron algorithm. The Elastic Net algorithm was used due to its incorporation of both L2 and L1 regularization, providing good results in discerning influential features in model performance. The Multilayer Perceptron algorithm was employed for its reliance on deep learning techniques, which yield promising results in such cases. This algorithm classified data from a comprehensive dataset containing essential features related to stroke. SMOTE is used to increase the performance of the model. Notably, no previous research study has integrated these three techniques together (Elastic Net - MLP – SMOTE). EMS achieved a prediction accuracy of 95% and MSE = 0.05. This model facilitates predicting the occurrence of stroke by relying on the patient's historical data, mitigating the sudden onset of this serious disease.