Tianxiu Yin, Chen Zhang, Yuxiang Liu, Xiaoyue Zhu, Jingyao Hu, Haijian Guo, Bei Wang
Department of Epidemiology and Health Statistics, School of Public Health, Southeast University, Nanjing, China.
Zhongda Hospital Affiliated to Southeast University, Nanjing, China.
Front Nutr. 2025 Aug 11;12:1618610. doi: 10.3389/fnut.2025.1618610. eCollection 2025.
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.
Data from 780 participants in the "Early Identification, Early Diagnosis Techniques, and Points of Risk for Diabetes in Major Chronic Non-communicable Disease Prevention and Control Studies" were analyzed.
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.
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.
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.
维生素D是一种必需营养素，对钙稳态和骨骼健康至关重要。血脂异常被认为是动脉粥样硬化疾病发生的危险因素。最近的研究表明，维生素D可能影响脂质代谢，特别是血液中循环脂质的水平。然而，维生素D与血脂异常之间的关系仍存在争议，这表明需要进一步研究以阐明这种关联。
分析了“重大慢性非传染性疾病预防与控制研究中糖尿病的早期识别、早期诊断技术及风险点”中780名参与者的数据。
我们采用了基于XGboost算法的机器学习、最小绝对收缩选择算子（LASSO）回归和单变量逻辑回归来筛选变量。随后，利用多变量逻辑回归和广义相加模型（GAM）构建模型，分析维生素D水平与血脂异常之间的关联。
在我们的研究中，XGboost机器学习算法探讨了所有纳入变量的相对重要性，证实了维生素D水平与血脂异常之间存在密切关联。在对所有重要协变量进行调整后，结果显示维生素D不足组和维生素D缺乏组血脂异常的风险分别是维生素D充足组的2.11倍和2.77倍。基于GAM构建了一条平滑曲线，发现25(OH)D与血脂异常风险之间存在显著的负相关。
25(OH)D与血脂异常风险之间可能存在负相关。尽管如此，仍需要更多精心设计的研究来证实这种关系。
