Data-Driven Lifestyle Therapy Model for Hypertension Management: A Comparative Analysis of Algorithms

Abstract

Primary hypertension in young adults in Nigeria is a significant health concern, with many having risk indicators well in advance of the disease's negative consequences. Preventive care is essential for mitigating the early start of the disease, rather than relying on pharmacological therapy. Lifestyle therapy, a preventative intervention, addresses related risk factors to treat, reverse, and avert chronic conditions like hypertension. This research examined risk factors, developed a predictive model for hypertension classification, and provided lifestyle advice based on these characteristics. The model was developed using three machine learning algorithms: extreme gradient (XG) boost, random forest, and support vector machine learning. Data from 303 individuals at the General Out-patient Department of General Hospital, Kubwa, FCT-Abuja was used to train and evaluate the model's performance. The results showed an accuracy of 93.4%, 92.6%, and 91.8% for the random forest, XG boost, and SVM models, respectively. The performance of the developed system showed that 294 participants (93.7%) out of the 303 participant data tested were accurately classified and given appropriate lifestyle therapy recommendations. The model performance indicates that a thorough analysis of risk variables associated with hypertension can yield effective lifestyle therapy suggestions for illness prevention and early management.