ORIGINAL RESEARCH article
Front. Endocrinol.
Sec. Bone Research
Volume 16 - 2025 | doi: 10.3389/fendo.2025.1589002
The Relationship Between Number of Pregnancies and Serum 25-Hydroxyvitamin D Levels in Women with a Prior Pregnancy: A Cross - Sectional Analysis, Machine Learning - Based Prediction Model, and SHAP - Assisted Feature Importance Evaluation
Provisionally accepted
- 1Harbin Medical University, Harbin, China
- 2Chengdu Medical College, Chengdu, 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
Background: The primary aim of this study is to explore the association between gravidity and serum 25-hydroxyvitamin D [25(OH)D] levels in women, as existing research rarely addresses gravidity's cumulative impact on maternal vitamin D status. Secondarily, it seeks to develop and evaluate a machine learning model for predicting vitamin D insufficiency (serum 25(OH)D < 50 nmol/L) using reproductive data (including gravidity) and biochemical indicators, with model contribution analysis further validating this relationship to translate findings into a clinically useful tool.Methods: The study included 8,003 parous women from the 2011–2018 NHANES, excluding those with missing vitamin D or gravidity data. For the primary objective, covariate-adjusted linear regression was used, with three hierarchical models: Model 1 (unadjusted); Model 2 (adjusted for age and race/ethnicity); Model 3 (adjusted for all potential confounders like body mass index, blood urea nitrogen, glycated hemoglobin). For model development, multiple regression and six machine learning algorithms (including XGBoost, Random Forest) were employed (suited for mixed-type biomedical data). The dataset was split into training/validation sets at 70:30.Results: Each additional pregnancy was associated with a 0.6 nmol/L decrease in 25(OH)D (P<0.001). XGBoost outperformed other methods in predicting vitamin D levels (AUC=0.73) and identifying low levels; key features were age, BMI, and blood urea nitrogen.Conclusion: In women with a prior pregnancy, an independent inverse association exists between gravidity and vitamin D status. The XGBoost algorithm, using common blood tests, shows superior performance in clinically predicting vitamin D levels, facilitating timely detection and intervention for low serum vitamin D.
Keywords: Gravidity, serum 25 (OH) D, Vitamin D insufficiency, machine learning algorithms, predictive model
Received: 06 Mar 2025; Accepted: 05 Sep 2025.
Copyright: © 2025 Wu, Wei and Zhang. 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: Li Wei, Harbin Medical University, Harbin, 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.