A novel predicted model for hypertension based on a large cross-sectional study.

Area of Science:

• Cardiology
• Public Health
• Epidemiology

Background:

• Hypertension is a significant global health concern and a primary risk factor for mortality and morbidity.
• There is a critical need for innovative methods to predict hypertension accurately.

Purpose of the Study:

• To develop and validate a predictive model for hypertension using clinical parameters in a Central China population.
• To identify significant risk factors associated with hypertension in the study cohort.

Main Methods:

• Utilized data from 73,158 physical examination participants in Central China (2008-2018).
• Included 33,570 hypertension cases and 35,410 healthy controls after exclusion criteria.
• Employed a logistic regression model with 70% training and 30% testing data split.

Main Results:

• Identified nine optimal markers for hypertension prediction.
• The logistic regression model achieved an Area Under the Curve (AUC) of 76.52% in the training set and 75.81% in the test set.
• Significant differences in clinical parameters like BMI, lipids, and kidney function markers were observed between hypertensive and control groups.

Conclusions:

• This study presents the first logistic regression-based predictive model for hypertension in Central China.
• The model provides valuable insights into hypertension risk factors and offers a novel prediction strategy.
• The findings support enhanced hypertension prediction and prevention efforts in the region.