Autors: Derimanov V., Stoilov B., Shopov, M. P.
Title: Impact of SMOTE Oversampling on Machine Learning Classifiers for Preeclampsia Prediction Under Severe Class Imbalance: Evidence from a Bulgarian Screening Cohort †
Keywords: artificial intelligence, Bulgarian population, clinical decision support, first-trimester screening, logistic regression, machine learning, preeclampsia, SMOTE

Abstract: This paper evaluates machine learning (ML) classifiers for predicting preeclampsia (PE) and pregnancy-induced hypertension (PIH) using first-trimester screening data from 1383 pregnant women in Plovdiv, Bulgaria (2018–2020). Three classifiers—Logistic Regression (LR), Extra Trees Classifier (ETC), and Voting Classifier (VC)—are compared across multiple prediction targets and feature configurations. The impact of SMOTE oversampling strategies on model performance in the context of a severe class imbalance (2.46% PE prevalence) is assessed. Logistic Regression achieves the highest AUC of 0.853 for preterm PE prediction without oversampling, while SMOTE significantly improves tree-based models (ETC: +0.058 AUC). A non-screened control cohort of 533 patients is evaluated separately using maternal characteristics alone (AUC 0.751). The ML model showed promising discrimination for preterm PE in this local cohort and warrants direct comparison with FMF-based risk stratification in future studies. These results support further validation of ML-based tools as potential components of future clinical decision support systems to extend systematic PE screening in resource-constrained settings.

References

  1. Say L. Chou D. Gemmill A. Tunçalp Ö. Moller A.-B. Daniels J. Gülmezoglu A.M. Temmerman M. Alkema L. Global causes of maternal death: A WHO systematic analysis Lancet Glob. Health 2014 2 E323 E333 10.1016/s2214-109x(14)70227-x
  2. Duley L. The Global Impact of Pre-eclampsia and Eclampsia Semin. Perinatol. 2009 33 130 137 19464502 10.1053/j.semperi.2009.02.010
  3. Magee L.A. Nicolaides K.H. von Dadelszen P. Preeclampsia N. Engl. J. Med. 2022 386 1817 1832 10.1056/nejmra2109523 35544388
  4. Wang W. Xie X. Yuan T. Wang Y. Zhao F. Zhou Z. Zhang H. Epidemiological trends of maternal hypertensive disorders of pregnancy at the global, regional, and national levels: A population-based study BMC Pregnancy Childbirth 2021 21 364 10.1186/s12884-021-03809-2 33964896
  5. European Commission State of Health in the EU: Bulgaria Country Health Profile 2023 OECD Publishing Paris, France 2023
  6. Rolnik D.L. Wright D. Poon L.C. O’Gorman N. Syngelaki A. de Paco Matallana C. Akolekar R. Cicero S. Janga D. Singh M. et al. Aspirin versus Placebo in Pregnancies at High Risk for Preterm Preeclampsia N. Engl. J. Med. 2017 377 613 622 10.1056/nejmoa1704559 28657417
  7. Chaemsaithong P. Sahota D.S. Poon L.C. First trimester preeclampsia screening and prediction Am. J. Obstet. Gynecol. 2022 226 S1071 S1097.e2 10.1016/j.ajog.2020.07.020 32682859
  8. O’ Gorman N. Wright D. Poon L.C. Rolnik D.L. Syngelaki A. De Alvarado M. Carbone I.F. Dutemeyer V. Fiolna M. Frick A. et al. Multicenter screening for pre-eclampsia by maternal factors and biomarkers at 11-13 weeks’ gestation: Comparison with NICE guidelines and ACOG recommendations Ultrasound Obstet. Gynecol. 2017 49 756 760 10.1002/uog.17455 28295782
  9. Dkeen N.O.M. Radwan M.E.D. Zumam I.A.A. Mohamed N.A.A.E. Abdelmahmoud E.M.A. Magboul N.M.E. Artificial Intelligence Applications in Obstetric Risk Prediction: A Systematic Review of Machine Learning Models for Preeclampsia Cureus 2025 17 e83961 10.7759/cureus.83961 40510095
  10. Schmidt L.J. Rieger O. Neznansky M. Hackelöer M. Dröge L.A. Henrich W. Higgins D. Verlohren S. A machine-learning–based algorithm improves prediction of preeclampsia-associated adverse outcomes Am. J. Obstet. Gynecol. 2022 227 77.e1 77.e30 10.1016/j.ajog.2022.01.026 35114187
  11. Gil M.M. Cuenca-Gómez D. Rolle V. Pertegal M. Díaz C. Revello R. Adiego B. Mendoza M. Molina F.S. Santacruz B. et al. Validation of machine-learning model for first-trimester prediction of pre-eclampsia using cohort from PREVAL study Ultrasound Obstet. Gynecol. 2024 63 68 74 10.1002/uog.27478 37698356
  12. Ansbacher-Feldman Z. Syngelaki A. Meiri H. Cirkin R. Nicolaides K.H. Louzoun Y. Machine-learning-based prediction of pre-eclampsia using first-trimester maternal characteristics and biomarkers Ultrasound Obstet. Gynecol. 2022 60 739 745 10.1002/uog.26105 36454636
  13. European Parliament and Council Regulation (EU) 2024/1689 laying down harmonised rules on artificial intelligence (Artificial Intelligence Act) Available online: http://data.europa.eu/eli/reg/2024/1689/oj (accessed on 9 April 2026)
  14. Butler L. Gunturkun F. Chinthala L. Karabayir I. Tootooni M.S. Bakir-Batu B. Celik T. Akbilgic O. Davis R.L. AI-based preeclampsia detection and prediction with electrocardiogram data Front. Cardiovasc. Med. 2024 11 1360238 10.3389/fcvm.2024.1360238 38500752
  15. Ryu D. Kim D.H. Price J.T. Lee J.Y. Chung H.U. Allen E. Walter J.R. Jeong H. Cao J. Kulikova E. et al. Comprehensive pregnancy monitoring with a network of wireless, soft, and flexible sensors in high- and low-resource health settings Proc. Natl. Acad. Sci. USA 2021 118 e2100466118 10.1073/pnas.2100466118 33972445
  16. Zhou S. Park G. Longardner K. Lin M. Qi B. Yang X. Gao X. Huang H. Chen X. Bian Y. et al. Clinical validation of a wearable ultrasound sensor of blood pressure Nat. Biomed. Eng. 2025 9 865 881 10.1038/s41551-024-01279-3 39567702
  17. Munyao M.M. Maina E.M. Mambo S.M. Wanyoro A. Real-time pre-eclampsia prediction model based on IoT and machine learning Discov. Internet Things 2024 4 10 10.1007/s43926-024-00063-8
  18. Marques J.A.L. Han T. Wu W. Madeiro J.P.D.V. Neto A.V.L. Gravina R. Fortino G. de Albuquerque V.H.C. IoT-Based Smart Health System for Ambulatory Maternal and Fetal Monitoring IEEE Internet Things J. 2021 8 16814 16824 10.1109/jiot.2020.3037759
  19. Stoilov B.T. Assessment of Preeclampsia Screening and Prevention with Acetylsalicylic Acid in a High-Risk Group of Women in the Bulgarian Population Ph.D. Thesis Medical University of Plovdiv Plovdiv, Bulgaria 2023
  20. Tiruneh S.A. Rolnik D.L. Teede H. Enticott J. Temporal validation of machine learning models for pre-eclampsia prediction using routinely collected maternal characteristics: A validation study Comput. Biol. Med. 2025 191 110183 10.1016/j.compbiomed.2025.110183 40228443

Issue

Engineering Proceedings, vol. 150, 2026, Switzerland, https://doi.org/10.3390/engproc2026150084

Вид: статия в списание, публикация в издание с импакт фактор, публикация в реферирано издание, индексирана в Scopus