A Scalability-Equipped Machine Learning Approach for Predicting Hypertension

This research study intends to identify hypertension by using machine learning techniques. When blood vessel pressure rises, it results in hypertension (high blood pressure), this condition can cause heart disease and possibly renal failure. Therefore, the early diagnosis can eliminate high-risk and be treated in the early stages, which is made feasible by Machine Learning (ML) algorithms. In this work, machine learning algorithms such as random forests, decision trees, multinomial naive bayes, and logistic regression are applied. The model performance is then determined by their accuracy, F1 score, recall, etc. It has been found through a comparison of algorithms that the accuracy of both Logistic Regression (LR) and Decision Tree (DT) are higher.