NEUROPREDICT: AN INTELLIGENT MACHINE LEARNING MODEL FOR EARLY STROKE DETECTION

Abstract

Brain stroke remains one of the leading causes of mortality and long-term disability worldwide, with early detection playing a crucial role in reducing patient risk and improving treatment outcomes. Traditional diagnostic methods often face limitations in speed, scalability, and accuracy, emphasizing the need for computationally intelligent solutions. This study presents NeuroPredict, a machine learning–driven framework designed for the early prediction of brain stroke risk. By leveraging diverse patient health records, including demographic, clinical, and lifestyle-related attributes, NeuroPredict applies supervised learning algorithms such as logistic regression, decision trees, random forests, support vector machines, and deep neural networks to classify individuals based on stroke likelihood. The proposed framework incorporates feature engineering and optimization techniques to enhance model interpretability and predictive accuracy. Experimental evaluation demonstrates that NeuroPredict achieves high performance in terms of precision, recall, and overall accuracy compared to conventional approaches. The findings suggest that machine learning offers a reliable, scalable, and cost-effective means of identifying at-risk patients, thereby enabling proactive medical interventions and supporting healthcare providers in stroke prevention strategies.