Welcome to the InfoSci Platform
Reference Hub2
Hypertension Prediction Using Machine Learning Technique

Hypertension Prediction Using Machine Learning Technique

Youngkeun Choi, Jae Choi
Copyright: © 2020 |Volume: 11 |Issue: 3 |Pages: 11
ISSN: 1947-8569|EISSN: 1947-8577|EISBN13: 9781799806271|DOI: 10.4018/IJSDS.2020070103
Cite Article Cite Article

MLA

Choi, Youngkeun, and Jae Choi. "Hypertension Prediction Using Machine Learning Technique." IJSDS vol.11, no.3 2020: pp.52-62. http://doi.org/10.4018/IJSDS.2020070103

APA

Choi, Y. & Choi, J. (2020). Hypertension Prediction Using Machine Learning Technique. International Journal of Strategic Decision Sciences (IJSDS), 11(3), 52-62. http://doi.org/10.4018/IJSDS.2020070103

Chicago

Choi, Youngkeun, and Jae Choi. "Hypertension Prediction Using Machine Learning Technique," International Journal of Strategic Decision Sciences (IJSDS) 11, no.3: 52-62. http://doi.org/10.4018/IJSDS.2020070103

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Machine learning technology is used in advanced data analysis and optimization approaches for different kinds of medical problems. Hypertension is complicated, and every year it causes a lot of many severe illnesses such as stroke and heart disease. This study essentially had two primary goals. Firstly, this paper intends to understand the role of variables in hypertension modeling better. Secondly, the study seeks to evaluate the predictive performance of the decision trees. Based on these results, first, age, BMI, and average glucose level influence hypertension significantly, while other variables have an influence. Second, for the full model, the accuracy rate is 0.905, which implies that the error rate is 0.095. Among the patients who were predicted not to have hypertension, the accuracy that would not have hypertension was 90.51%, and the accuracy that had strike was 30.77% among the patients who were predicted to have hypertension.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.