PDF icon Download PDF
Am J Perinatol 2025; 42(10): 1354-1361
DOI: 10.1055/a-2495-3600
Original Article

Derivation and Validation of Prediction of Preterm Preeclampsia Using Machine Learning Algorithms

Tetsuya Kawakita
1   Department of Obstetrics and Gynecology, Macon and Joan Brock Virginia Health Sciences at Old Dominion University (ODU), Norfolk, Virginia
,
Juliana G. Martins
1   Department of Obstetrics and Gynecology, Macon and Joan Brock Virginia Health Sciences at Old Dominion University (ODU), Norfolk, Virginia
,
Yara H. Diab
1   Department of Obstetrics and Gynecology, Macon and Joan Brock Virginia Health Sciences at Old Dominion University (ODU), Norfolk, Virginia
,
Lea Nehme
1   Department of Obstetrics and Gynecology, Macon and Joan Brock Virginia Health Sciences at Old Dominion University (ODU), Norfolk, Virginia
,
George Saade
1   Department of Obstetrics and Gynecology, Macon and Joan Brock Virginia Health Sciences at Old Dominion University (ODU), Norfolk, Virginia
› Author Affiliations
Funding nuMoM2b specimen and data collection were supported by grant funding from the Eunice Kennedy Shriver National Institute of Child Health and Human Development (NICHD): U10 HD063036; U10 HD063072; U10 HD063047; U10 HD063037; U10 HD063041; U10 HD063020; U10 HD063046; U10 HD063048; and U10 HD063053. In addition, support was provided by Clinical and Translational Science Institutes: UL1TR001108 and UL1TR000153.
› Further Information
Also available ateRefHebammen
   Permissions and Reprints
Preview

Abstract

Objective

This study aimed to develop machine learning (ML) models for predicting preterm preeclampsia using the information available before 23 weeks gestation.

Study Design

This was a secondary analysis of the Nulliparous Pregnancy Outcomes Study: Monitoring Mothers-to-Be (nuMoM2b) cohort. We considered 131 features available before 23 weeks including maternal demographics, obstetrics and family history, social determinants of health, physical activity, nutrition, and early second-trimester ultrasound. Our primary outcome was preterm preeclampsia before 37 weeks. The dataset was randomly split into a training set (70%) and a validation set (30%). ML models using glmnet, multilayer perceptron, random forest, XGBoost (extreme gradient boosting), and LightGBM models were developed. Using the ML approach that achieved the best area under the curve (AUC), we developed the final model. Further feature selection was conducted from the top 25 important features based on SHapley Additive exPlanations (SHAP) values. The performance of the final model was assessed using the validation dataset.

Results

Of 9,467 individuals, 219 (2.3%) had preterm preeclampsia. The AUC of the XGBoost model was the highest (AUC = 0.749 [95% confidence interval (95% CI), 0.736–0.762]) compared with other models. Therefore, XGBoost was used to develop models using fewer variables. The XGBoost model with the eight features (in order of importance: mean uterine artery pulsatility index in the early second trimester, chronic hypertension, pregestational diabetes, uterine artery notch, systolic and diastolic blood pressure in the first trimester, body mass index, and maternal age) was chosen as the final model as it had an AUC of 0.741 (95% CI, 0.730–0.752) which was not inferior to the original model (p = 0.58). The final model in the validation dataset had an AUC of 0.779 (95% CI, 0.722–0.831). An online application of the final model was developed ( https://kawakita.shinyapps.io/Preterm_preeclampsia/ ).

Conclusion

ML algorithms using information available before 23 weeks can accurately predict preterm preeclampsia before 37 weeks.

Key Points

  • Prediction models using uterine artery Doppler have not been adopted in the US.

  • We developed a model using an ML algorithm.

  • An online application of the final model was developed.

  • ML algorithms using information available before 23 weeks can accurately predict preterm preeclampsia before 37 weeks.

Keywords

nulliparous - online application - uterine artery doppler - XGBoost

Note

The content of this article is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.


Supplementary Material



Publication History

Received: 20 October 2024

Accepted: 03 December 2024

Accepted Manuscript online:
04 December 2024

Article published online:
24 December 2024

© 2024. Thieme. All rights reserved.

Thieme Medical Publishers, Inc.
333 Seventh Avenue, 18th Floor, New York, NY 10001, USA