Logo-aim
Arch Iran Med. 2024;27(5): 239-247.
doi: 10.34172/aim.2024.35
  Abstract View: 198
  PDF Download: 108

Original Article

Identifying Risk Indicators of Cardiovascular Disease in Fasa Cohort Study (FACS): An Application of Generalized Linear Mixed-Model Tree

Fariba Asadi 1 ORCID logo, Reza Homayounfar 2, Mojtaba Farjam 3, Yaser Mehrali 4, Fatemeh Masaebi 1, Farid Zayeri 5* ORCID logo

1 Department of Biostatistics, School of Allied Medical Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran
2 National Nutrition and Food Technology Research Institute, Faculty of Nutrition Sciences and Food Technology, Shahid Beheshti University of Medical Sciences, Tehran, Iran
3 Noncommunicable diseases research center, Fasa University of Medical Sciences, Fasa, Iran
4 Statistical Center of Iran, Tehran, Iran
5 Proteomics Research Center and Department of Biostatistics, School of Allied Medical Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran
*Corresponding Author: Farid Zayeri, Email: fzayeri@gmail.com

Abstract

Background: Today, cardiovascular disease (CVD) is the most important cause of death around the world. In this study, our main aim was to predict CVD using some of the most important indicators of this disease and present a tree-based statistical framework for detecting CVD patients according to these indicators.

Methods: We used data from the baseline phase of the Fasa Cohort Study (FACS). The outcome variable was the presence of CVD. The ordinary Tree and generalized linear mixed models (GLMM) were fitted to the data and their predictive power for detecting CVD was compared with the obtained results from the GLMM tree. Statistical analysis was performed using the RStudio software.

Results: Data of 9499 participants aged 35‒70 years were analyzed. The results of the multivariable mixed-effects logistic regression model revealed that participants’ age, total cholesterol, marital status, smoking status, glucose, history of cardiac disease or myocardial infarction (MI) in first- and second-degree relatives, and presence of other diseases (like hypertension, depression, chronic headaches, and thyroid disease) were significantly related to the presence of CVD (P<0.05). Fitting the ordinary tree, GLMM, and GLMM tree resulted in area under the curve (AUC) values of 0.58 (0.56, 0.61), 0.81 (0.77, 0.84), and 0.80 (0.76, 0.83), respectively, among the study population. In addition, the tree model had the best specificity at 81% but the lowest sensitivity at 65% compared to the other models.

Conclusion: Given the superior performance of the GLMM tree compared with the standard tree and the lack of significant difference with the GLMM, using this model is suggested due to its simpler interpretation and fewer assumptions. Using updated statistical models for more accurate CVD prediction can result in more precise frameworks to aid in proactive patient detection planning.


Cite this article as: Asadi F, Homayounfar R, Farjam M, Mehrali Y, Masaebi F, Zayeri F. Identifying risk indicators of cardiovascular disease in Fasa Cohort Study (FACS): an application of generalized linear mixed-model tree. Arch Iran Med. 2024;27(5):239-247. doi: 10.34172/aim.2024.35
First Name
 
Last Name
 
Email Address
 
Comments
 
Security code


Abstract View: 199

Your browser does not support the canvas element.


PDF Download: 108

Your browser does not support the canvas element.

Submitted: 03 Dec 2023
Accepted: 11 Mar 2024
ePublished: 01 May 2024
EndNote EndNote

(Enw Format - Win & Mac)

BibTeX BibTeX

(Bib Format - Win & Mac)

Bookends Bookends

(Ris Format - Mac only)

EasyBib EasyBib

(Ris Format - Win & Mac)

Medlars Medlars

(Txt Format - Win & Mac)

Mendeley Web Mendeley Web
Mendeley Mendeley

(Ris Format - Win & Mac)

Papers Papers

(Ris Format - Win & Mac)

ProCite ProCite

(Ris Format - Win & Mac)

Reference Manager Reference Manager

(Ris Format - Win only)

Refworks Refworks

(Refworks Format - Win & Mac)

Zotero Zotero

(Ris Format - Firefox Plugin)