Feature Selection for Hypertension Risk Prediction Using XGBoost on Single Nucleotide Polymorphism Data

Abstract

Objectives: Hypertension, commonly known as high blood pressure, is a prevalent and serious condition affecting a significantportion of the adult population globally. It is a chronic medical issue that, if left unaddressed, can lead to severe healthcomplications, including kidney problems, heart disease, and stroke. This study aims to develop a feature selection modelusing the XGBoost algorithm to identify specific single nucleotide polymorphisms (SNPs) as biomarkers for detecting hypertensionrisk. Methods: We propose using the high dimensionality of genetic variations (i.e., SNPs) to build a classifiermodel for prediction. In this study, SNPs were used as markers for hypertension in patients. We utilized the OpenSNP dataset,which includes 19,697 SNPs from 2,052 samples. Extreme gradient boosting (XGBoost) is an ensemble machine learningmethod employed here for feature selection, which incrementally adjusts weights in a series of steps. Results: The experimentalresults identified 292 SNPs that exhibited high performance, with an F1-score of 98.55%, precision of 98.73%, recallof 98.38%, and overall accuracy of 98%. This study provides compelling evidence that the XGBoost feature selection methodoutperforms other representative feature selection methods, such as genetic algorithms, analysis of variance, chi-square, andprincipal component analysis, in predicting hypertension risk, demonstrating its effectiveness. Conclusions: We developeda model for predicting hypertension using the SNPs dataset. The high dimensionality of SNP data was effectively managedto identify significant features as biomarkers using the XGBoost feature selection method. The results indicate high performancein predicting the risk of hypertension.