Mahalanobis Distance Based Multivariate Outlier Detection to Improve Performance of Hypertension Prediction

In recent years, the incidence of hypertension diseases has increased dramatically, not only among the elderly but also among young people. In this regard, the use of machine learning methods to diagnose the causes of hypertension diseases has increased in recent years. In this article, we have improved the prediction of hypertension detection using Mahalanobis distance-based multivariate outlier removing of Korean national health data named by the KNHANES database. The study identified a variety of risk factors associated with chronic hypertension. Chronic disease is often caused by many factors, not just one. Therefore, it is necessary to study the detection of the disease taking into account complex factors. The paper is divided into two modules. Initially, the data preprocessing step that uses a tree classifier-based feature selection, and to remove multivariate outlier using Mahalanobis distance from KNHANES data. The next module applies the predictive analysis step to detect and prediction of hypertension. In this study, we compare the accuracy, mean standard error (MSE), F1-score, and area under the ROC curve (AUC) for each classification model. The test results show that the proposed RF-MAH algorithm has an accuracy, F1-score, MSE and AUC outcomes of 99.48%, 99.62%, 0.0025 and 99.61%, respectively. Following these, the second-best outcomes of an accuracy rate of 99.51%, MSE of 0.0028, F1-score of 99.58%, and AUC of 99.65% were achieved by XGBoost with the MAH model. The proposed method can be used not only for hypertension but also for the detection of various diseases, such as stroke and cardiovascular disease. It is planned to support the identification and decision-making of high-risk patients with various diseases.