Analyzing Cardiovascular Disease Risk Factors Using Generalized Logistic Logic Regression: A Retrospective Study

Habibollah  Esmaily; Mahbubeh  Jahani; Mohammad Ali  Kianfard; Majid  Ghayour-Mobarhan

doi:10.18502/jbe.v11i3.21373

Habibollah Esmaily Student Research Committee, Mashhad University of Medical Sciences, Mashhad, Iran.
Mahbubeh Jahani Faculty of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran.
Mohammad Ali Kianfard Student Research Committee, Mashhad University of Medical Sciences, Mashhad, Iran.
Majid Ghayour-Mobarhan International UNESCO Center for Health-Related Basic Sciences and Human Nutrition, Mashhad University of Medical Sciences, Mashhad, Iran

DOI: https://doi.org/10.18502/jbe.v11i3.21373

Keywords: Generalized logistic logic regression; Cardiovascular disease; Machine learning; Interaction effects; Risk factors

Abstract

Introduction: Cardiovascular disease (CVD) is a general term that refers to diseases of the heart or blood vessels. Logic regression is a machine learning method that is commonly used when the number of predictor variables is high, and it can account for interaction effects between predictor variables. As CVD can be influenced by multiple factors, this study was conducted to identify variables related to CVD and predict the occurrence of CVD using generalized logistic logic regression.

Methods: The present study is a retrospective study utilizing data from phase one of the MASHAD study. The analysis was performed on the information of 7,385 individuals. Generalized logistic logic regression analysis was performed using the “LogicReg” package in R software.

Results: Out of the 7385 individuals included in this study, 235 (3.2%) were diagnosed with CVD, while 7150 (96.8%) did not have CVD. Of the variables examined, age, anxiety, depression, metabolic syndrome, and family history were significant as main effects, and an interaction between smoking status and education had a significant effect.

Conclusion: Based on the findings of this study, it can be tentatively concluded that for CVD, the existence of interaction effects among the mentioned risk factors may not be a significant concern. In other words, the primary effects of each variable may be more important, as these variables appear to play a role in CVD independently of each other.