A Predictive Model Using Deep Learning Techniques for Hypertension Risk Analysis

Abstract

Hypertension remains a leading risk factor for cardiovascular diseases and early mortality worldwide, necessitating the development of effective predictive tools for early intervention. This study presents the design and implementation of a predictive model for hypertension risk analysis using a deep learning approach. Specifically, a Multilayer Perceptron (MLP) neural network architecture was employed to analyse key risk indicators, including demographic, lifestyle, and clinical variables. The dataset, sourced from a publicly available health database, comprised 5,000 patient records and was pre-processed to ensure quality and relevance. A training-testing split of 80:20 was used to evaluate the model’s performance. The model achieved high predictive performance, with an accuracy of 91.3%, precision of 89.5%, recall of 92.7%, and F1-score of 91.0%. These results demonstrate the model’s effectiveness in identifying individuals at risk of hypertension. The study contributes to the growing body of intelligent health risk prediction systems and offers potential for integration into clinical decision support tools to enhance preventive care.