Integrated support vector machine with improved PSO optimization for early risk screening and prevention of stroke in patients with hypertension

Abstract

Hypertension is a significant global health threat, and stroke is the leading cause of death and disability worldwide. Therefore, early risk identification is crucial for stroke prevention in patients with hypertension. This study proposes an integrated approach using a support vector machine optimized by a two-stage adaptive particle swarm optimization algorithm for the early risk screening of stroke in patients with hypertension. We collected medical data from Shanghai First People’s Hospital and used machine learning to construct a predictive model. The support vector machine served as the base model, and the two-stage adaptive particle swarm optimization algorithm performed parameter optimization, enhancing the model’s classification accuracy and computational efficiency. This improved algorithm achieved an accuracy of 0.8905, outperforming standard support vector machines, genetic algorithm support vector machines, and grid search-support vector machine algorithms. Compared with other methods, our model demonstrated superior prediction accuracy and generalization ability, which are essential for the early screening and prevention of stroke in patients with hypertension. This study contributes to the advancement of medical services for stroke prevention in patients with hypertension and provides a model for effective health management.