A New Hybrid XGBSVM Model: Application for Hypertensive Heart Disease

The changes in people's life rhythm and improvement in material levels that happened in recent years increased the number of people suffering from high blood pressure in the world. Therefore, as a cardiac complication of hypertension, the prevalence of hypertensive heart disease has increased a...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2019, Vol.7, p.175248-175258
Main Authors: Chang, Wenbing, Liu, Yinglai, Wu, Xueyi, Xiao, Yiyong, Zhou, Shenghan, Cao, Wen
Format: Article
Language:English
Subjects:
Biomedical materials
biomedicine
Cardiovascular disease
Cardiovascular diseases
Classification algorithms
Heart
Heart diseases
Hypertension
hypertensive heart disease
Machine learning
Radio frequency
Support vector machines
SVM
XGBoost
XGBSVM
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The changes in people's life rhythm and improvement in material levels that happened in recent years increased the number of people suffering from high blood pressure in the world. Therefore, as a cardiac complication of hypertension, the prevalence of hypertensive heart disease has increased annually, it has seriously endangered the safety of human life, and the effective prediction of hypertensive heart disease has become a worldwide problem. This paper uses the newly proposed XGBSVM hybrid model to predict whether hypertensive patients will develop hypertensive heart disease within three years. The final experiment proves that through this model, hypertensive patients can learn their risk of hypertensive heart disease within 3 years and then undergo targeted preventive treatment, thereby reducing the psychological, physiological and economic burden. This paper confirms that the machine learning can be successfully applied in the biomedical field, with strong real-world significance and research value.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2019.2957367