Pep-Ensem-2n: A Robust Deep Ensemble Framework for Trimester-Wise Prediction of Preeclampsia Using Clinical Data
International Journal of Medical Toxicology and Forensic Medicine,
Vol. 16 (2026),
1 January 2026
,
Page 1-14
https://doi.org/10.22037/ijmtfm.v16.53285
Abstract
Background: There is significant maternal and perinatal morbidity associated with Preeclampsia. Maternal variability in physical and biochemical parameters during gestation makes accurate, timely risk assessment difficult. In this study, we propose a deep ensemble model, PEP-Ensem-2N, to predict preeclampsia at various pregnancy visits.
Methods: It incorporates missing-value imputation, standardization, random-forest feature selection, and class-balancing using the Synthetic Minority Oversampling Technique. We weight and soft-vote the prediction probabilities from five learning architectures (long short-term memory, gated recurrent unit, simple recurrent neural network, temporal convolutional network, and deep convolutional network). We used three datasets to evaluate the framework: PEP-T1, PEP-T2, and PEP-T3. We compared various model structures and activation functions and assessed the relative importance of the model inputs by comparing random forest feature rankings.
Results: The reported experiments showed that the rectified linear unit (ReLU)-based model PEP-Ensem-2N achieved an accuracy of 0.9946 on the PEP-T1 dataset, 0.9992 on PEP-T2, and 0.9990 on PEP-T3.
Conclusion: PEP-Ensem-2N is a feature-selection, class-imbalance, and probability-fusion approach within a unified prediction framework. The reported performance should be confirmed through counts and evaluation procedures. It needs independent validation with observed clinical data before it can be applied in clinical settings.
- Preeclampsia (PE); Machine Learning (ML); Deep Learning (DL); Ensemble Learning (EL); Clinical Decision Support System (CDSS); Random Forest (RF); Temporal Convolutional Network (TCN); Synthetic Minority Oversampling Technique (SMOTE); Medical Prediction.
How to Cite
References
[1] Edvinsson C, Björnsson O, Erlandsson L, Hansson SR. Predicting intensive care need in women with preeclampsia using machine learning – a pilot study. Hypertens Pregnancy. 2024;43(1):2312165. [DOI: 10.1080/10641955.2024.2312165]
[2] Torres-Torres J, Villafan-Bernal JR, Martinez-Portilla RJ, Hidalgo-Carrera JA, Estrada-Gutierrez G, Adalid-Martinez-Cisneros R, et al. Performance of machine-learning approach for prediction of pre-eclampsia in a middle-income country. Ultrasound Obstet Gynecol. 2024;63(4):506-13. [DOI: 10.1002/uog.27510]
[3] Li T, Xu M, Wang Y, Wang Y, Tang H, Duan H, et al. Prediction model of preeclampsia using machine learning based methods: a population-based cohort study in China. Front Endocrinol (Lausanne). 2024;15:1345573. [DOI: 10.3389/fendo.2024.1345573]
[4] Butler L, Gunturkun F, Chinthala L, Karabayir I, Tootooni MS, Bakir-Batu B, et al. AI-based preeclampsia detection and prediction with electrocardiogram data. Front Cardiovasc Med. 2024;11:1360238. [DOI: 10.3389/fcvm.2024.1360238]
[5] Scripcariu IS, Vasilache IA, Pavaleanu I, Doroftei B, Cărăuleanu A, Socolov D, et al. Machine Learning-Based Prediction of Intrauterine Growth Restriction and Preeclampsia: A Prospective Study. Med Sci (Basel). 2024;12(1):8. [DOI: 10.3390/medsci12010008]
[6] Villalaín C, Herraiz I, Domínguez-Del Olmo P, Angulo P, Ayala JL, Galindo A. Prediction of Delivery Within 7 Days After Diagnosis of Early Onset Preeclampsia Using Machine-Learning Models. Front Cardiovasc Med. 2022;9:910701. [DOI: 10.3389/fcvm.2022.910701]
[7] Gomez-Jerez L, Oprescu AM, Chimenea-Toscano Á, Garcia-Diaz L, Romero-Ternero MDC. Machine Learning to Predict Pre-Eclampsia and Intrauterine Growth Restriction in Pregnant Women. Electronics. 2022;11(19):3240. [DOI: 10.3390/electronics11193240]
[8] Chen X, Lan Y, Du J, Lin W, Ke J, Lin F, et al. Development and validation of the prediction models for preeclampsia: a retrospective, single-centre, case-control study. Ann Transl Med. 2022;10(18):987. [DOI: 10.21037/atm-22-4192]
[9] Zhang X, Chen Y, Salerno S, Li Y, Zhou L, Zeng X, et al. Prediction of severe preeclampsia in machine learning. Med Novel Technol Devices. 2022;14:100158. [DOI: 10.1016/j.medntd.2022.100158]
[10] McLaughlin K, Hobson SR, Ravi Chandran A, Agrawal BS, Windrim RC, Parks WT, et al. Circulating maternal placental growth factor responses to low-molecular-weight heparin in pregnant patients at risk of placental dysfunction. Am J Obstet Gynecol. 2022;226(2):248.e1-248.e12. [DOI: 10.1016/j.ajog.2021.08.027]
[11] Bennett R, Mulla ZD, Parikh P, Hauspurg A, Razzaghi T. An imbalance-aware deep neural network for early prediction of preeclampsia. PLoS One. 2022;17(3):e0266042. [DOI: 10.1371/journal.pone.0266042]
[12] Gupta K, Balyan K, Lamba B, Puri M, Sengupta D, Kumar M. Ultrasound placental image texture analysis using artificial intelligence to predict hypertension in pregnancy. J Matern Fetal Neonatal Med. 2022;35(25):5281-7. [DOI: 10.1080/14767058.2021.1887847]
[13] Wang G, Zhang Y, Li S, Zhang J, Jiang D, Li X, et al. A Machine Learning-Based Prediction Model for Cardiovascular Risk in Women with Preeclampsia. Front Cardiovasc Med. 2021;8:736491. [DOI: 10.3389/fcvm.2021.736491]
[14] Zhang Y, Wang X, Han N, Zhao R. Ensemble Learning Based Postpartum Hemorrhage Diagnosis for 5G Remote Healthcare. IEEE Access. 2021;9:20546-20556. [DOI: 10.1109/ACCESS.2021.3051215]
[15] Li YX, Shen XP, Yang C, Cao ZZ, Du R, Yu MD, et al. Novel electronic health records applied for prediction of pre-eclampsia: Machine-learning algorithms. Pregnancy Hypertens. 2021;26:104-110. [DOI: 10.1016/j.preghy.2021.10.006]
[16] Huang Q, Hao S, You J, Yao X, Li Z, Schilling J, et al. Early-pregnancy prediction of risk for pre-eclampsia using maternal blood leptin/ceramide ratio: discovery and confirmation. BMJ Open. 2021;11(9):e050963. [DOI: 10.1136/bmjopen-2021-050963]
[17] Dathan-Stumpf A, Czarnowsky V, Hein V, Andraczek T, Stepan H. Real-world data on the clinical use of angiogenic factors in pregnancies with placental dysfunction. Am J Obstet Gynecol. 2021;224(4):393.e1-393.e11. [DOI: 10.1016/j.ajog.2020.10.028]
[18] Sufriyana H, Wu YW, Su EC. Prediction of Preeclampsia and Intrauterine Growth Restriction: Development of Machine Learning Models on a Prospective Cohort. JMIR Med Inform. 2020;8(5):e15411. [DOI: 10.2196/15411]
[19] Marić I, Tsur A, Aghaeepour N, Montanari A, Stevenson DK, Shaw GM, et al. Early prediction of preeclampsia via machine learning. Am J Obstet Gynecol MFM. 2020;2(2):100100. [DOI: 10.1016/j.ajogmf.2020.100100]
[20] Jhee JH, Lee S, Park Y, Lee SE, Kim YA, Kang SW, et al. Prediction model development of late-onset preeclampsia using machine learning-based methods. PLoS One. 2019;14(8):e0221202. [DOI: 10.1371/journal.pone.0221202]
[21] PRAISE Lab. PEPrML: Machine Learning for Preeclampsia Prediction [Software/Repository]. GitHub; 2023 [cited 2024]. [Link]
- Abstract Viewed: 29 times
- 53285 Downloaded: 11 times