Vol. 29 No. 3 (2026) Cover Image
Vol. 29 No. 3 (2026)

Published: September 20, 2026

Pages: 542-551

Articles

Comparing Operative Delivery Risk Using Explainable Artificial Intelligence (XAI) and Maternal and Fetal Clinical Information

C Ramani Vijay Chelvi 1 B. Shunmugapriya 1
1 Department of Computer Science and Engineering, National Engineering College, Kovilpatti, India.
History
  • Received: March 21, 2026
  • Revised: May 15, 2026
  • Accepted: May 23, 2026
  • Available Online: September 20, 2026
DOI

https://doi.org/10.29194/NJES.29030542

Abstract

Predicting the risk of operative delivery, especially Cesarean section, is important for improving outcomes for both mothers and newborns. In this study, a machine-learning-based framework is developed using explainable artificial intelligence techniques across three clinical datasets: fetal cardiotocography, maternal health parameters, and pregnancy outcome data.Three classification models—Logistic Regression, Decision Tree, and Random Forest—were evaluated to identify the most effective approach. Among these, the Random Forest model achieved the best performance, with an F1 Score of 0.88 and an Area Under the Curve of 0.99 on the fetal health dataset.To enhance interpretability in a clinical context, a dual-layer explanation strategy was adopted. SHapley Additive exPlanations was used to analyze global feature importance, while Local Interpretable Model-agnostic Explanations was applied to explain individual predictions. The results indicate that abnormal short-term variability is a key factor influencing operative delivery risk. The explanations generated by both methods were consistent with established clinical understanding, making the model both accurate and interpretable.

Keywords

References

  1. A. de R. Fernández, D. R. Fernández, and M. T. P. Sánchez, "Prediction of the mode of delivery using artificial intelligence algorithms," Comput. Methods Programs Biomed., vol. 219, p. 106740, 2022. https://doi.org/10.1016/j.cmpb.2022.106740
  2. K. W. Schulz, K. Gmther, C. Zigler, T. Urban, J. Drake, and R. Bukowski, "Optimal mode of delivery in pregnancy: individualized predictions using national vital statistics data," PLOS Digit. Health, vol. 1, no. 12, p. e0000166, 2022. https://doi.org/10.1371/journal.pdig.0000166
  3. I. Ferreira, J. Simões, B. Pereira, J. Correia, and A. L. Areia, "Ensemble learning for fetal ultrasound and maternal-fetal data to predict mode of delivery after labor induction," Sci. Rep., vol. 14, no. 1, p. 15275, 2024. https://doi.org/10.1038/s41598-024-65394-6
  4. J. E. Jung and Y. J. Lee, "Intrapartum transperineal ultrasound: angle of progression to evaluate and predict the mode of delivery and labor progression," Obstet. Gynecol. Sci., vol. 67, no. 1, pp. 1-16, 2024. https://doi.org/10.5468/ogs.23141
  5. J. Chen, H. Shen, Y. T. Chen, C.-H. Chen, K.-H. Lee, and P.-L. Torng, "Experience in different modes of delivery in twin pregnancy," PLOS ONE, vol. 17, no. 3, p. e0265180, 2022. https://doi.org/10.1371/journal.pone.0265180
  6. Y. Liu, Q. Gong, Y. Yuan, and Q. Shi, "Prediction model for labour dystocia occurring in the active phase," J. Obstet. Gynaecol., vol. 43, no. 1, p. 2174837, 2023. https://doi.org/10.1080/01443615.2023.2174837
  7. L. Ihan, E. Nowak, F. Anouilh, C. Tremouilhac, P. Merviel, C. Tromeur, S. Robin, G. Drugmanne, L. Le Roux, and F. Couturaud, "Development and validation of a predictive tool for postpartum hemorrhage after vaginal delivery: a prospective cohort study," Biology, vol. 12, p. 54, 2023. https://doi.org/10.3390/biology12010054
  8. S. Balke, P. Weid, L. Fangmann, P. Rostin, W. Henrich, and J. T. Koenigbauer, "Glucose levels of the oral glucose tolerance test (oGTT) can predict adverse pregnancy outcomes in women with gestational diabetes (GDM)," J. Clin. Med., vol. 12, p. 3709, 2023. https://doi.org/10.3390/jcm12113709
  9. H. Khosravi, Z. Mehrbakhsh, S. Moghasemi, and G. Samiei, "Preferred mode of delivery association with the body image and genital image in pregnant women: cross-sectional study," BMC Pregnancy Childbirth, vol. 23, no. 1, p. 490, 2023. https://doi.org/10.1186/s12884-023-05589-3
  10. T. Hu, S. Du, X. Li, F. Yang, S. Zhang, J. Yi, and L. He, "Establishment of a model for predicting the outcome of induced labor in full-term pregnancy based on a machine learning algorithm," Sci. Rep., vol. 12, no. 1, p. 19063, 2022. https://doi.org/10.1038/s41598-022-21954-2
  11. M. L. Meng, J. J. Federspiel, M. Fuller, A. McNeil, A. S. Habib, J. Quist-Nelson, and V. Krishnamoorthy, "Severe maternal morbidity according to mode of delivery among pregnant patients with cardiomyopathies," Heart Failure, vol. 11, no. 12, pp. 1678-1689, 2023. https://doi.org/10.1016/j.jchf.2023.09.012
  12. K. Robertson, M. Vieira, and L. Impey, "Perinatal outcome of fetuses predicted to be large-for-gestational age on universal third-trimester ultrasound in non-diabetic pregnancy," Ultrasound Obstet. Gynecol., vol. 63, no. 1, pp. 98-104, 2024. https://doi.org/10.1002/uog.26305
  13. D. G. Iliescu, S. Belciug, R. C. Ivanescu, and others, "Prediction of labor outcome pilot study: evaluation of primiparous women at term," Am. J. Obstet. Gynecol. MFM, vol. 4, p. 100711, 2022. https://doi.org/10.1016/j.ajogmf.2022.100711
  14. E. Nouri-Khasheh-Heiran, A. Montazeri, F. Conversano, M. Kashanian, M. Rasuli, M. Rahimi, and N. Akbari, "The success of vaginal birth by use of trans-labial ultrasound plus vaginal examination and vaginal examination only in pregnant women with labor induction: a comparative study," BMC Pregnancy Childbirth, vol. 23, no. 1, p. 3, 2023. https://doi.org/10.1186/s12884-022-05324-4
  15. M. H. Tun, R. Chari, P. Kaul, F. V. Mamede, M. Paulden, D. L. Lefebvre, and P. J. Mandhane, "Prediction of odds for emergency cesarean section: a secondary analysis of the CHILD term birth cohort study," PLOS ONE, vol. 17, no. 10, p. e0268229, 2022. https://doi.org/10.1371/journal.pone.0268229
  16. S. Płotka, M. K. Grzeszczyk, R. Brawura-Biskupski-Samaha, P. Gutaj, M. Lipa, T. Trzciński, and A. Sitek, "BabyNet++: fetal birth weight prediction using biometric multimodal data acquired less than 24 hours before delivery," Comput. Biol. Med., vol. 167, p. 107602, 2023. https://doi.org/10.1016/j.compbiomed.2023.107602
  17. A. Shorten, A. Fagerlin, J. Illuzzi, and others, "Developing an internet-based decision aid for women choosing between vaginal birth after cesarean and planned repeat cesarean," J. Midwifery Women's Health, 2015. https://doi.org/10.1111/jmwh.12298
  18. T. Bloomfield, "Cesarean section, NICE guidelines and management of labour," J. Obstet. Gynaecol., 2004. https://doi.org/10.1080/0144361042331271052
  19. J. Mas-Cabo, G. Prats-Boluda, J. Garcia-Casado, and others, "Electrohysterogram for ANN-based prediction of imminent labor in women with threatened preterm labor undergoing tocolytic therapy," Sensors, vol. 20, 2020. https://doi.org/10.3390/s20092681
  20. C. Benalcazar-Parra, Y. Ye-Lin, J. Garcia-Casado, and others, "Prediction of labor induction success from the uterine electrohysterogram," J. Sens., 2019. https://doi.org/10.1155/2019/6916251
  21. E. Rohith, V. Sowmya, and K. P. Soman, "Convolutional neural networks for placenta cell classification," in Proc. 2nd Int. Conf. Intell. Comput., Instrum. Control Technol. (ICICICT), 2019, pp. 1273-1277. https://doi.org/10.1109/ICICICT46008.2019.8993145
  22. D. S. A. Maylawati, M. A. Ramdhani, W. B. Zulfikar, and others, "Expert system for predicting the early pregnancy with disorders using an artificial neural network," in Proc. 5th Int. Conf. Cyber IT Service Manage. (CITSM), 2017. https://doi.org/10.1109/CITSM.2017.8089243
  23. A. Al Housseini, T. Newman, A. Cox, and others, "Prediction of risk for cesarean delivery in term nulliparas: a comparison of neural network and multiple logistic regression models," Am. J. Obstet. Gynecol., 2009. https://doi.org/10.1016/j.ajog.2009.05.001
  24. H. Ocak, "A medical decision support system based on support vector machines and the genetic algorithm for the evaluation of fetal well-being," J. Med. Syst., 2013. https://doi.org/10.1007/s10916-012-9913-4
  25. J. Spilka, J. Frecon, R. Leonarduzzi, and others, "Sparse support vector machine for intrapartum fetal heart rate classification," IEEE J. Biomed. Health Inform., 2017. https://doi.org/10.1109/JBHI.2016.2546312
  26. J. Alberola-Rubio, J. Garcia-Casado, G. Prats-Boluda, and others, "Prediction of labor onset type: spontaneous vs induced; role of electrohysterography," Comput. Methods Programs Biomed., 2017. https://doi.org/10.1016/j.cmpb.2017.03.018
  27. Kaggle, "Fetal Health Classification Dataset," Kaggle Repository, accessed 2026. [Online]. Available: https://www.kaggle.com/datasets/andrewmvd/fetal-health-classification
  28. Kaggle, "Maternal Health Risk Dataset," Kaggle Repository, accessed 2026. [Online]. Available: https://www.kaggle.com/datasets/csafrit2/maternal-health-risk-data
  29. Local ANCC Register Dataset, "Pregnancy Outcome Clinical Register Data (Babies Dataset)," Collected dataset, 2026.