Patient Hypertension Modeling Using Decision Tree: Analysis of Age, Symptoms, Fatty Food Intake, Salt Intake, Medication Count, and Blood Pressure Using RapidMiner

Abstract

Hypertension is a chronic disease characterized by persistently elevated blood pressure and remains a major global health problem. Various interacting factors, including age, salt and fatty food intake, medication use, and blood pressure, influence the risk and symptoms of hypertension. This study aims to identify patterns and characteristics of hypertension patients and determine the most influential factors using data mining techniques. A quantitative approach with the Decision Tree algorithm was applied using RapidMiner Studio. The analysis involved data preprocessing, model training and validation, and identification of influential variables. The Decision Tree analysis revealed that medication use is the main determinant of symptom patterns in hypertension. In patients not taking medication, symptoms were mainly influenced by salt intake and blood pressure, where low salt intake was associated with nausea and moderate salt intake with varied symptoms, especially headaches. In patients taking medication, symptom patterns were affected by the combination of salt and fatty food intake. High salt and fat consumption were associated with dizziness, while moderate intake was related to fatigue. Hypertension symptoms are determined not only by blood pressure but also by lifestyle factors and medication use. The Decision Tree model effectively identifies hierarchical relationships among these factors, providing valuable insights for healthcare professionals to design more targeted hypertension management and prevention strategies.