Hypertension, a universal health concern worldwide, significantly contributes to cardiovascular disease and premature mortality. This study explores the classification of hypertension risk through machine learning techniques, aiming to enhance diagnosis support and preventive measures. Notable studies in this field have highlighted demographic trends, risk patterns, and prediction models using various algorithms. This study leverage on a Framework-Based Method, Where the data collection in this study involved observation and expert consultation, resulting in a dataset comprising 298 hypertensive patients' records. Data preprocessing was conducted using principal component analysis for feature selection, ensuring the relevance of variables like age, blood pressure, and lifestyle factors. Furthermore, the Classification processes employed Support Vector Machine (SVM), Decision Tree, and General Linear Model algorithms. Where SVM gave 90%, DT gave 83% and GLM gave 64% on accuracy. Performance evaluation metrics, including accuracy, sensitivity, and precision, were used to assess model efficacy. SVM emerged as the best-performing model and was deployed in a web-based interface for real-time hypertension risk classification. This study underscores the significance of machine learning in hypertension management, offering valuable insights into risk assessment and preventive strategies. The integration of SVM into a user-friendly interface enhances accessibility and empowers healthcare professionals and individuals to make informed decisions, ultimately mitigating the burden of hypertension-related complications.

Hypertension Machine Learning Classification Risk