Big Data-Based Analysis and Prediction Model for Disease Risk Factors

Hypertension is a core disease of metabolic syndrome, with its prevalence continuously rising in China, particularly showing significantly higher rates among males compared to females. Based on large-scale healthcare data, this study focuses on male hypertension as a case study, utilizing multivariate statistical theory and big data analytics to identify key risk factors and construct a risk prediction model. The study incorporates 18 risk factors, including age, BMI, family history, and smoking habits, employs correlation analysis for key feature selection, and addresses high-dimensional data collinearity through principal component analysis. Subsequently, a risk prediction mathematical model is developed using logistic regression, followed by ranking the significance and importance of influential factors. The results indicate that family history, age, waist circumference, BMI, and triglycerides are the top five critical factors affecting male hypertension. This study provides a data-driven solution for hypertension risk assessment, applicable to personalized health management and insurance risk control, while offering a scalable data analysis methodology for chronic disease prevention and control.