Correlation of visceral adiposity index and dietary profile with cardiovascular disease based on decision tree modeling: a cross-sectional study of NHANES

Abstract Background Visceral adiposity index (VAI) and diets are associated with the risk of cardiovascular disease (CVD). It is unclear how well VAI and diet predict CVD. Methods Data were obtained from the National Health and Nutrition Examination Survey (NHANES 2017–2018). Demographic data, diets...

Full description

Saved in:
Bibliographic Details
Main Authors: Shiyong Xu, Yirou Cai, Haizhen Hu, Changlin Zhai
Format: Article
Language:English
Published: BMC 2025-02-01
Series:European Journal of Medical Research
Subjects:
Online Access:https://doi.org/10.1186/s40001-025-02340-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849715642644561920
author Shiyong Xu
Yirou Cai
Haizhen Hu
Changlin Zhai
author_facet Shiyong Xu
Yirou Cai
Haizhen Hu
Changlin Zhai
author_sort Shiyong Xu
collection DOAJ
description Abstract Background Visceral adiposity index (VAI) and diets are associated with the risk of cardiovascular disease (CVD). It is unclear how well VAI and diet predict CVD. Methods Data were obtained from the National Health and Nutrition Examination Survey (NHANES 2017–2018). Demographic data, diets, biochemical examination, and questionnaire information were collected. VAI was calculated using body mass index, waist circumference, triglycerides, and high-density lipoprotein cholesterol. Binary logistic regression was adopted to examine the correlation of VAI and diets with CVD. A decision tree model was developed to predict CVD risk according to different factors. Results 2104 participants (mean age: 50.87 ± 17.35 years, 48.38% males) were included. Participants with high levels of VAI (≥ 2.18) had an elevated risk of CVD compared to those with low levels of VAI (≤ 0.76) (OR = 1.654, 95% CI: 1.025–2.669, P = 0.039). Compared with the low protein intake level (≤ 50.34 g), the upper intermediate (72.10–99.92 g) (OR = 0.445, 95% CI: 0.257–0.770, P = 0.004) and high (≥ 99.93 g) levels of protein intake (OR = 0.450, 95% CI: 0.236–0.858, P = 0.015) reduced CVD risk. The decision tree model unveiled that VAI, protein intake, and dietary fiber intake were predictors for CVD. Conclusion VAI and protein intake levels are independently associated with CVD risk and have predictive power for CVD. These findings can provide insights into the development of appropriate lifestyle and treatment strategies for patients to reduce the incidence of CVD.
format Article
id doaj-art-dcd76122d00a4e6fb0f0373ba42055ba
institution DOAJ
issn 2047-783X
language English
publishDate 2025-02-01
publisher BMC
record_format Article
series European Journal of Medical Research
spelling doaj-art-dcd76122d00a4e6fb0f0373ba42055ba2025-08-20T03:13:17ZengBMCEuropean Journal of Medical Research2047-783X2025-02-0130111010.1186/s40001-025-02340-wCorrelation of visceral adiposity index and dietary profile with cardiovascular disease based on decision tree modeling: a cross-sectional study of NHANESShiyong Xu0Yirou Cai1Haizhen Hu2Changlin Zhai3Department of Cardiology, Affiliated Hospital of Jiaxing UniversityHospital of the Chinese People’s Armed Police Force Maritime Safety BureauDepartment of Cardiology, Affiliated Hospital of Jiaxing UniversityDepartment of Cardiology, Affiliated Hospital of Jiaxing UniversityAbstract Background Visceral adiposity index (VAI) and diets are associated with the risk of cardiovascular disease (CVD). It is unclear how well VAI and diet predict CVD. Methods Data were obtained from the National Health and Nutrition Examination Survey (NHANES 2017–2018). Demographic data, diets, biochemical examination, and questionnaire information were collected. VAI was calculated using body mass index, waist circumference, triglycerides, and high-density lipoprotein cholesterol. Binary logistic regression was adopted to examine the correlation of VAI and diets with CVD. A decision tree model was developed to predict CVD risk according to different factors. Results 2104 participants (mean age: 50.87 ± 17.35 years, 48.38% males) were included. Participants with high levels of VAI (≥ 2.18) had an elevated risk of CVD compared to those with low levels of VAI (≤ 0.76) (OR = 1.654, 95% CI: 1.025–2.669, P = 0.039). Compared with the low protein intake level (≤ 50.34 g), the upper intermediate (72.10–99.92 g) (OR = 0.445, 95% CI: 0.257–0.770, P = 0.004) and high (≥ 99.93 g) levels of protein intake (OR = 0.450, 95% CI: 0.236–0.858, P = 0.015) reduced CVD risk. The decision tree model unveiled that VAI, protein intake, and dietary fiber intake were predictors for CVD. Conclusion VAI and protein intake levels are independently associated with CVD risk and have predictive power for CVD. These findings can provide insights into the development of appropriate lifestyle and treatment strategies for patients to reduce the incidence of CVD.https://doi.org/10.1186/s40001-025-02340-wNHANESDecision treeVisceral adiposity indexCardiovascular disease
spellingShingle Shiyong Xu
Yirou Cai
Haizhen Hu
Changlin Zhai
Correlation of visceral adiposity index and dietary profile with cardiovascular disease based on decision tree modeling: a cross-sectional study of NHANES
European Journal of Medical Research
NHANES
Decision tree
Visceral adiposity index
Cardiovascular disease
title Correlation of visceral adiposity index and dietary profile with cardiovascular disease based on decision tree modeling: a cross-sectional study of NHANES
title_full Correlation of visceral adiposity index and dietary profile with cardiovascular disease based on decision tree modeling: a cross-sectional study of NHANES
title_fullStr Correlation of visceral adiposity index and dietary profile with cardiovascular disease based on decision tree modeling: a cross-sectional study of NHANES
title_full_unstemmed Correlation of visceral adiposity index and dietary profile with cardiovascular disease based on decision tree modeling: a cross-sectional study of NHANES
title_short Correlation of visceral adiposity index and dietary profile with cardiovascular disease based on decision tree modeling: a cross-sectional study of NHANES
title_sort correlation of visceral adiposity index and dietary profile with cardiovascular disease based on decision tree modeling a cross sectional study of nhanes
topic NHANES
Decision tree
Visceral adiposity index
Cardiovascular disease
url https://doi.org/10.1186/s40001-025-02340-w
work_keys_str_mv AT shiyongxu correlationofvisceraladiposityindexanddietaryprofilewithcardiovasculardiseasebasedondecisiontreemodelingacrosssectionalstudyofnhanes
AT yiroucai correlationofvisceraladiposityindexanddietaryprofilewithcardiovasculardiseasebasedondecisiontreemodelingacrosssectionalstudyofnhanes
AT haizhenhu correlationofvisceraladiposityindexanddietaryprofilewithcardiovasculardiseasebasedondecisiontreemodelingacrosssectionalstudyofnhanes
AT changlinzhai correlationofvisceraladiposityindexanddietaryprofilewithcardiovasculardiseasebasedondecisiontreemodelingacrosssectionalstudyofnhanes