Predicting Hypertension using Machine Learning: A Case Study at Petra University

Abstract

Hypertension is a key cardiovascular disease risk factor (CVD). Identifying these high-risk individuals is crucial since it would save time and money before using any sophisticated, invasive, or costly diagnostic technique. This endeavour may be accomplished in part with the use of modern machine learning techniques. Specifically, a prediction model may be created based on several easily-obtained, non-invasive, and inexpensive indicator characteristics of high-risk individuals. This research is an effort to forecast hypertension risks based on Petra University's population. This case study was done between 2019 and 2020 at Petra University. Using hospital-visited patients' medical records, the gathered data was used to develop a model. The research comprised a comprehensive dataset of 31500 patients, comprising 12658 hypertension cases and 18842 non-hypertensive cases. SMOTE was used as a dataset for the categorization of hypertension. The SMOTE-k-nearest neighbour prediction model performs exceptionally well, as evidenced by its excellent performance (83.9% classification accuracy, 85.1% specificity, 83.3% sensitivity, and 89.6% AUC) when compared to other classifiers using 10-fold cross-validation with full features and no oversampling on the hypertension dataset. The data extracted from Petra University Health Center is considered to be very helpful for ML and is availed to produce a decision tree to identify the data related to hypertension.