Clinical And Laboratory Determinants Of Preeclampsia Onset Using Ensemble Machine Learning Prediction And Comparison Among Stacking Ensemble, Neural Network With And Without Stacking Ensemble Approach
DOI:
https://doi.org/10.29284/f3g2mk55Keywords:
Machine Learning Ensemble Models; Neural Network-Based Stacking Ensemble; Neural Networks; Clinical and Laboratory Risk Factors and Onset Preeclampsia prediction.Abstract
Preeclampsia is a pregnancy-related hypertensive illness that bears increased maternal and fetal morbidity and mortality. For early risk stratification of preeclampsia, the development of models that can forecast its onset is crucial. This work analyzes maternal clinical and laboratory features using bagging- and boosting-based ensemble models in comparison with a neural network stacking framework that incorporates these models. Experimental results show that Random Forest yields the highest performance of 81% for late-onset preeclampsia and maintains robust performance for early-onset preeclampsia. In contrast, the boosting models XGBoost and CatBoost yield competitive performance with an accuracy of 77% and 71%, respectively. However, their performance is still inferior to that from Random Forest. Hematological parameters, especially total leukocyte count and platelet count, are major predictors influencing model performance and misclassification patterns across all the ensemble models. On the other hand, neural network-based stacking ensemble models yielded more balanced and reliable predictions, with great value for clinical risk assessment. The developed models can enhance the early risk stratification of preeclampsia and support decisions for obstetric care.
References
1. American College of Obstetricians and Gynecologists. (2002). ACOG practice bulletin No. 33: Diagnosis and management of preeclampsia and eclampsia. Obstetrics & Gynecology, 99(1), 159–167.
2. American College of Obstetricians and Gynecologists, & Task Force on Hypertension in Pregnancy. (2013). Hypertension in pregnancy: Report of the American College of Obstetricians and Gynecologists’ Task Force on Hypertension in Pregnancy. Obstetrics & Gynecology, 122(5), 1122–1131.
3. Aksornphusitaphong, A., & Phupong, V. (2013). Risk factors of early and late onset pre-eclampsia. Journal of Obstetrics and Gynaecology Research, 39(3), 627–631.
4. Bozdag, H., Ogutcuoglu, F. B., Guzin, K., Kilic, S. R., Duran, E. A., & Aydin, I. T. (2015). The frequency and fetomaternal outcomes of early- and late-onset preeclampsia: Experience of a single tertiary health center in Istanbul. Medeniyet Medical Journal, 30(4), 163–169.
5. F. Pettit, Mangos, G., Davis, G., Henry, A., & Brown, M. A. (2015). Pre-eclampsia causes adverse maternal outcomes across the gestational spectrum. Pregnancy Hypertension, 5(2), 198–204.
6. Gohar, S., & Syed, W. (2021). Comparison of adverse fetomaternal outcome in early and late onset pre-eclampsia. Journal of Postgraduate Medical Institute, 35(1), 15–18.
7. Hellman, L. M., & Pritchard, J. A. (2014). Williams obstetrics (14th ed.). World Health Organization.
8. Jhee, J. H., et al. (2019). Prediction of pregnancy outcomes using machine learning: A retrospective cohort study. PLOS ONE.
9. Khan, S., Aleem, N. T., Hasna, A. U., Husein, S., Khatun, K., & Ara, R. (2013). A clinical study on risk factors and fetomaternal outcome of pre-eclampsia in Bangladesh. Journal of the Bangladesh Society of Anaesthesiologists, 26(1), 39–44.
10. Kolluru, V., Harika, R. Y., & Kaul, R. (2016). Maternal and perinatal outcomes associated with pregnancy-induced hypertension. International Journal of Reproduction, Contraception, Obstetrics and Gynecology, 5(10), 3367–3372.
11. Kooffreh, M. E., Ekott, M., & Ekpoudom, D. O. (2010). The prevalence of preeclampsia among pregnant women in the University of Calabar Teaching Hospital, Calabar. Saudi Journal of Health Sciences, 3(3), 133–136.
12. Liu, L., et al. (2022). Machine learning models for early prediction of preeclampsia: A systematic review. Frontiers in Public Health.
13. Madazli, R., Yuksel, M. A., Imamoglu, M., Tuten, A., Oncul, M., et al. (2014). Comparison of clinical and perinatal outcomes in early- and late-onset preeclampsia. Archives of Gynecology and Obstetrics, 290(1), 53–57.
14. Madhuri, C., & Varalakshmi, Y. (2019). Retrospective study on fetomaternal outcome in gestational hypertension, pre-eclampsia and eclampsia in a tertiary care centre. Indian Journal of Basic and Applied Medical Research, 8(4), 246–255.
15. Magee, L. A., Pels, A., Helewa, M., Rey, E., & von Dadelszen, P. (2014). Diagnosis, evaluation, and management of the hypertensive disorders of pregnancy. Pregnancy Hypertension, 4(2), 105–145.
16. Paruk, F., & Moodley, J. (2000). Maternal and neonatal outcome in early- and late-onset pre-eclampsia. Seminars in Neonatology, 5(3), 197–207.
17. Poon, L. C., & Nicolaides, K. H. (2014). Early prediction of preeclampsia. Obstetrics and Gynecology International, Article ID 297397.
18. Publications Committee, Society for Maternal-Fetal Medicine, & Sibai, B. M. (2011). Evaluation and management of severe preeclampsia before 34 weeks’ gestation. American Journal of Obstetrics and Gynecology, 205(3), 191–198.
19. Sibai, B. M. (1999). Hypertension in pregnancy. Clinical Obstetrics and Gynecology, 421–436.
20. Sovio, U., et al. (2020). Prediction of preeclampsia using first-trimester biomarkers and machine learning models. Hypertension.
21. Stergiotou, I., Crispi, F., Valenzuela-Alcaraz, B., Bijnens, B., & Gratacos, E. (2013). Patterns of maternal vascular remodeling and responsiveness in early- versus late-onset preeclampsia. American Journal of Obstetrics and Gynecology, 209(6), 558.e1–558.e14.
22. Thangaratinam, S., et al. (2011). Prediction models for pre-eclampsia: A systematic review. BMJ.
23. Tranquilli, A. L., Brown, M. A., Zeeman, G. G., Dekker, G., & Sibai, B. M. (2013). The definition of severe and early-onset preeclampsia: Statements from the International Society for the Study of Hypertension in Pregnancy (ISSHP). Pregnancy Hypertension, 3(1), 44–47.
24. Tranquilli, A. L., Dekker, G., Magee, L., et al. (2014). The classification, diagnosis and management of the hypertensive disorders of pregnancy: A revised statement from the ISSHP. Pregnancy Hypertension, 4(2), 97–104.
25. World Health Organization. (2018). Maternal mortality. Retrieved March 24, 2018, from http://www.who.int/mediacentre/factsheets/fs348/en
26. Ye, C., et al. (2020). Prediction of pregnancy-related hypertensive disorders using machine learning. BMC Medical Informatics and Decision Making.
27. You, S.-H., Cheng, P.-J., Chung, T.-T., Kuo, C.-F., Wu, H.-M., & Chu, P.-H. (2014). Population-based trends and risk factors of early- and late-onset preeclampsia in Taiwan.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
