Abstract:
General Background: Preeclampsia is a leading cause of maternal and perinatal morbidity and mortality worldwide, with early prediction remaining a critical challenge in obstetric care. Specific Background: Conventional diagnostic approaches based on clinical and isolated biochemical markers often identify the disorder at advanced stages and fail to capture its multifactorial pathophysiology. Knowledge Gap: There is limited integration of multidimensional clinical, biochemical, and Doppler data into robust predictive models capable of early and individualized risk assessment. Aims: This study aimed to develop and evaluate a machine learning–based model for early prediction of preeclampsia using comprehensive antenatal data. Results: In a retrospective cohort of 1,200 pregnant women, the Extreme Gradient Boosting (XGBoost) model demonstrated superior performance, achieving an AUC of 0.94, sensitivity of 91%, specificity of 89%, and overall accuracy of 90%, outperforming random forest, support vector machine, and logistic regression models. Key predictors included mean arterial pressure, maternal age, uterine artery pulsatility index, placental growth factor, and soluble fms-like tyrosine kinase-1. Novelty: The study integrates 35 heterogeneous parameters into an AI-driven framework, highlighting the strength of ensemble learning in capturing nonlinear risk patterns. Implications: AI-based predictive tools offer significant potential for early identification of high-risk pregnancies, enabling targeted preventive interventions and advancing precision obstetrics to reduce preeclampsia-related adverse outcomes.
Highlight :
XGBoost showed high accuracy for early preeclampsia risk prediction.
Combined clinical, biochemical, and Doppler data enabled early risk identification.
Early prediction supports timely preventive obstetric interventions.
Keywords : Preeclampsia, Pregnancy, Prediction, Artificial Intelligence, Machine Learning
Downloads
References
Ayusheva, S. E., M. S. Zhdanova, and E. A. Ponomareva, “Modern Approaches to Prediction and Prevention of Preeclampsia,” Akusherstvo i Ginekologiya, no. 5, pp. 45–52, 2022. Available: [https://www.mediasphera.ru/issues/akusherstvo-i-ginekologiya](https://www.mediasphera.ru/issues/akusherstvo-i-ginekologiya)
Brown, M. A., L. A. Magee, L. C. Kenny, et al., “The Hypertensive Disorders of Pregnancy: ISSHP Classification, Diagnosis and Management Recommendations for International Practice,” Pregnancy Hypertension, vol. 13, pp. 291–310, 2018, doi: 10.1016/j.preghy.2018.05.004
Savel’eva, G. M., M. A. Kurtser, and R. I. Shalina, Preeclampsia: Modern Aspects of Pathogenesis, Diagnosis and Therapy. Moscow, Russia: GEOTAR-Media, 2021.
Rana, S., E. Lemoine, J. P. Granger, and S. A. Karumanchi, “Preeclampsia: Pathophysiology, Challenges, and Perspectives,” Circulation Research, vol. 124, no. 7, pp. 1094–1112, 2019, doi: 10.1161/CIRCRESAHA.118.313276
Kasymova, N. A., G. R. Khalilova, and D. Sh. Ibragimova, “Role of Fetal Risk Factors in the Development of Pregnancy Complications,” Vestnik Reproduktivnogo Zdorovya, no. 2, pp. 25–30, 2023. Available: [https://www.reprohealthjournal.uz](https://www.reprohealthjournal.uz)
Liu, X., M. Chen, J. Zhao, et al., “Machine Learning-Based Prediction of Preeclampsia Using Maternal and Fetal Parameters,” Frontiers in Medicine, vol. 8, Article 625133, 2021, doi: 10.3389/fmed.2021.625133
Mukhamedova, Z. Sh., G. B. Tursunova, and N. M. Khamraeva, “Use of Artificial Intelligence Technologies in Perinatal Diagnostics,” Journal of Clinical Medicine of Uzbekistan, no. 4, pp. 57–63, 2023. Available: [https://www.tma.uz/journals](https://www.tma.uz/journals)
Chappell, L. C., C. A. Cluver, J. Kingdom, and S. Tong, “Pre-Eclampsia,” The Lancet, vol. 398, no. 10297, pp. 341–354, 2021, doi: 10.1016/S0140-6736(20)32335-7
Abdullaeva, M. R. and D. A. Yusupova, “Prospects for the Implementation of Intelligent Systems in the Prediction of Obstetric Complications,” Medical Bulletin of Bukhara, no. 1, pp. 18–24, 2024. Available: [https://www.bukhmi.uz/vestnik](https://www.bukhmi.uz/vestnik)
Zhang, Y., H. Wang, Q. Li, et al., “Artificial Intelligence-Assisted Prediction of Preeclampsia Based on Fetal Ultrasound and Maternal Biomarkers,” BMC Pregnancy and Childbirth, vol. 22, Article 154, 2022, doi: 10.1186/s12884-022-04488-6
Bahado-Singh, R. O., A. Syngelaki, R. Akolekar, et al., “Machine Learning Approach for Prediction of Preeclampsia Using Maternal Serum Biomarkers at 11 to 13 Weeks’ Gestation,” American Journal of Obstetrics and Gynecology, vol. 212, no. 1, pp. 103.e1–103.e10, 2015, doi: 10.1016/j.ajog.2014.07.028
Ye, C., J. Li, Y. Li, et al., “Real-Time Prediction of Preeclampsia Using Machine Learning Models With Electronic Health Record Data,” Journal of Biomedical Informatics, vol. 112, Article 103606, 2020, doi: 10.1016/j.jbi.2020.103606
AlRahmani, L., M. Qassem, M. AlShehhi, et al., “Application of Artificial Intelligence in Early Screening of Preeclampsia: A Systematic Review,” Pregnancy Hypertension, vol. 29, pp. 56–64, 2022, doi: 10.1016/j.preghy.2022.05.003
Reddy, A., S. Suresh, and R. Krishnan, “Deep Learning-Based Risk Stratification for Preeclampsia Using Maternal Clinical Parameters,” IEEE Access, vol. 9, pp. 145732–145741, 2021, doi: 10.1109/ACCESS.2021.3121954
Duhig, K., J. Myers, P. T. Seed, et al., “Placental Growth Factor–Based Algorithm Improves Preeclampsia Prediction and Diagnosis: A Prospective Multicenter Study,” BJOG: An International Journal of Obstetrics and Gynaecology, vol. 129, no. 4, pp. 593–602, 2022, doi: 10.1111/1471-0528.16919