ORIGINAL RESEARCH article
Front. Nutr.
Sec. Nutritional Epidemiology
Volume 12 - 2025 | doi: 10.3389/fnut.2025.1618610
Exploring the Association Between Vitamin D Levels and Dyslipidemia Risk: Insights from Machine Learning and Generalized Additive Models
Provisionally accepted
- 1Southeast University, Nanjing, China
- 2Zhongda Hospital, Southeast University, Nanjing, Jiangsu Province, China
- 3Jiangsu Provincial Center for Disease Control And Prevention, Nanjing, Jiangsu Province, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Vitamin D is a necessary nutrient that is important for calcium homeostasis and bone health.Dyslipidemia is thought to be a risk factor for the development of atherosclerotic illnesses. Recent research suggests that vitamin D may influence lipid metabolism, specifically the levels of circulating lipids in the blood.However, the relationship between vitamin D and dyslipidemia remains controversial, indicating a need for further research to clarify this association. Objectives: Data from 780 participants in the "Early Identification, Early Diagnosis Techniques, and Points of Risk for Diabetes in Major Chronic Noncommunicable Disease Prevention and Control Studies" were analyzed. Methods: We employed machine learning with the XGboost algorithm, Least Absolute Shrinkage Selection Operator (LASSO) regression, and univariate logistic regression to screen variables. Subsequently, multiple logistic regression and a generalized additive model (GAM) were utilized to construct models analyzing the association between vitamin D levels and dyslipidemia. Results: In our study, the XGboost machine learning algorithm explored the relative importance of all included variables, confirming a robust association between vitamin D levels and dyslipidemia. After adjusting for all the important covariates, the results showed that the risk of dyslipidemia in Vitamin D insufficiency group and Vitamin D deficiency group was 2.11 times and 2.77 times of that in Vitamin D sufficiency group, respectively. A smooth curve was constructed based on GAM and a significant negative association was found between 25(OH)D and the risk of dyslipidemia. Conclusions: There may be a negative association between 25(OH)D and the risk of dyslipidemia. Nonetheless, additional well-designed studies are necessary to substantiate this relationship.
Keywords: Dyslipidemia, 25(OH)D, XGBoost, GAM, machine learning
Received: 26 Apr 2025; Accepted: 28 Jul 2025.
Copyright: © 2025 Yin, Zhang, Liu, Zhu, Hu, Guo and Wang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Bei Wang, Southeast University, Nanjing, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.