RISK FACTORS FOR HIGH SYSTOLIC BLOOD PRESSURE: A PREDICTIVE ANALYSIS USING MACHINE LEARNING IN A NIGERIAN SETTING

Abstract

High blood pressure (hypertension) remains a significant health challenge, especially in developing countries where early detection is limited. This study applies advanced machine learning techniques regression trees and artificial neural networks (ANNs) to predict and analyze high blood pressure patterns in the Iyekhei community. The dataset includes systolic blood pressure (SBP), age, body mass index (BMI), and other risk factors collected from a cross-sectional survey of residents. Correlation analysis revealed age and BMI as significant predictors of SBP. The regression tree provided an interpretable rule-based classification, while the neural network achieved a classification accuracy of 91%, outperforming traditional methods. These findings highlight the potential of combining machine learning models with community-based health data to improve early detection and management of hypertension.