ORIGINAL RESEARCH article
Front. Cardiovasc. Med.
Sec. Hypertension
Volume 12 - 2025 | doi: 10.3389/fcvm.2025.1627811
Analysis of Risk Factors and Early Prediction Model Construction for Gestational Hypertension
Provisionally accepted
- Civil Aviation General Hospital, Beijing, 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: This study evaluates the impact of traditional and placental function factors on gestational hypertension and compares the predictive performance of multivariable logistic regression, random forest, and support vector machine models. Methods: We first compared baseline characteristics and pregnancy-related features between women with normal pregnancies and those with gestational hypertension. Subsequently, we constructed prediction models for gestational hypertension based on traditional and placental function factors using multivariable logistic regression, random forest, and support vector machines with SHAP value interpretation.The predictive performance of each model was evaluated using ROC curves. Results: Among the models compared, the multivariable logistic regression model based on traditional factors achieved the highest AUC (0.831), indicating the best predictive performance. The AUCs for random forest and support vector machine using traditional factors were 0.730 and 0.732, respectively. However, both models showed reduced performance when using placental function factors, with random forest yielding the lowest AUC (0.612). Feature importance analysis revealed that baseline systolic blood pressure, diastolic blood pressure, high-risk pregnancy, and family history were key predictors among traditional factors, while fasting plasma glucose, triglycerides, and C-reactive protein were common features ranked among the top five most important variables 2 in both the random forest and support vector machine models. Conclusion: Traditional factors appear to be more effective in predicting gestational hypertension, with multivariable logistic regression based on these factors demonstrating the strongest performance. These findings suggest that prioritizing logistic regression models using traditional predictors may be optimal, while the integration of additional variables and machine learning approaches could further enhance predictive accuracy through a more comprehensive evaluation.
Keywords: Gestational hypertension, risk prediction, multivariable logistic regression, random forest, Support vector machine
Received: 22 May 2025; Accepted: 24 Jul 2025.
Copyright: © 2025 Sun, Wang, Huang, Li and Yang. 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: Yue Yang, Civil Aviation General Hospital, Beijing, 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.