Hostname: page-component-745bb68f8f-cphqk Total loading time: 0 Render date: 2025-01-26T21:44:15.224Z Has data issue: false hasContentIssue false
  • English
  • Français

Artificial Intelligence in Predicting Postpartum Hemorrhage in Twin Pregnancies Undergoing Cesarean Section

Published online by Cambridge University Press:  15 January 2025

Sukran Dogru ,
Huriye Ezveci Open the ORCID record for Huriye Ezveci [Opens in a new window] ,
Fatih Akkus ,
Pelin Bahçeci ,
Fikriye Karanfil Yaman  and
Ali Acar
Sukran Dogru
Affiliation:
Necmettin Erbakan University Medical School of Meram, Department of Obstetrics and Gynecology, Division of Fetal and Maternal Medicine, Konya, Turkey
Huriye Ezveci*
Affiliation:
Necmettin Erbakan University Medical School of Meram, Department of Obstetrics and Gynecology, Division of Fetal and Maternal Medicine, Konya, Turkey
Fatih Akkus
Affiliation:
Necmettin Erbakan University Medical School of Meram, Department of Obstetrics and Gynecology, Division of Fetal and Maternal Medicine, Konya, Turkey
Pelin Bahçeci
Affiliation:
Necmettin Erbakan University Medical School of Meram, Department of Obstetrics and Gynecology, Konya/Turkey
Fikriye Karanfil Yaman
Affiliation:
Necmettin Erbakan University Medical School of Meram, Department of Obstetrics and Gynecology, Division of Fetal and Maternal Medicine, Konya, Turkey
Ali Acar
Affiliation:
Necmettin Erbakan University Medical School of Meram, Department of Obstetrics and Gynecology, Division of Fetal and Maternal Medicine, Konya, Turkey
*
Corresponding author: Huriye Ezveci; Email: huriyeezveci00@gmail.com
Get access

Abstract

This study aimed to create a risk prediction model with artificial intelligence (AI) to identify patients at higher risk of postpartum hemorrhage using perinatal characteristics that may be associated with later postpartum hemorrhage (PPH) in twin pregnancies that underwent cesarean section. The study was planned as a retrospective cohort study at University Hospital. All twin cesarean deliveries were categorized into two groups: those with and without PPH. Using the perinatal characteristics of the cases, four different machine learning classifiers were created: Logistic regression (LR), support vector machine (SVM), random forest (RF), and multilayer perceptron (MLP). LR, RF, and SVM models were created a second time by including class weights to manage the underlying imbalances in the data. A total of 615 twin pregnancies were included in the study. There were 150 twin pregnancies with PPH and 465 without PPH. Dichorionity, PAS, and placenta previa were significantly higher in the PPH-positive group (p = .045, p = .004, p = .001 respectively). In our model, LR with class weight was the best model with the highest negative predictive value. The AUC in our LR with class weight model was %75.12 with an accuracy of 70.73%, a PPV of 47.92%, and an NPV of 85.33% in our data. Although the application of machine learning to create predictive models using clinical risk factors and our model’s 70% accuracy rate are encouraging, it is not sufficient. Machine learning modeling needs further study and validation before being incorporated into clinical use.

Keywords

artificial intelligencepostpartum hemorrhagetwin pregnancyprediction
Type
Article
Information
Twin Research and Human Genetics , First View , pp. 1 - 7
Check for updates
Copyright
© The Author(s), 2025. Published by Cambridge University Press on behalf of International Society for Twin Studies

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

American College of Obstetricians and Gynecologists. (2006). ACOG Practice Bulletin: Clinical Management Guidelines for Obstetrician-Gynecologists Number 76, October 2006: postpartum hemorrhage. Obstetrics & Gynecology, 108, 1039–1047. https://doi.org/10.1097/00006250-200610000-00046 Google Scholar
Betts, K. S., Kisely, S., & Alati, R. (2019). Predicting common maternal postpartum complications: Leveraging health administrative data and machine learning. BJOG, 126, 702–709. https://doi.org/10.1111/1471-0528.15607 CrossRefGoogle ScholarPubMed
Blitz, M. J., Yukhayev, A., Pachtman, S. L., Reisner, J., Moses, D., Sison, C. P., Greenberg, M., & Rochelson, B. (2020). Twin pregnancy and risk of postpartum hemorrhage. Journal of Maternal-Fetal and Neonatal Medicine, 33, 3740–3745. https://doi.org/10.1080/14767058.2019.1583736 CrossRefGoogle ScholarPubMed
Cao, X., Luo, Y., Zhou, S., Zhao, Q., Qin, X., Liu, Z., & Xu, Z. (2022). Twin growth discordance and risk of postpartum hemorrhage: A retrospective cohort study. Frontiers in Medicine, 9, 876411. https://doi.org/10.3389/fmed.2022.876411 CrossRefGoogle ScholarPubMed
Committee on Practice Bulletins—Obstetrics. (2017). Practice Bulletin No. 183: Postpartum hemorrhage. Obstetrics & Gynecology, 130, e168–e186. https://doi.org/10.1097/aog.0000000000002351 CrossRefGoogle Scholar
DeStephano, C. C., Bakkum-Gamez, J. N., Kaunitz, A. M., Ridgeway, J. L., & Sherman, M. E. (2020). Intercepting endometrial cancer: Opportunities to expand access using new technology. Cancer Prevention Research, 13, 563–568. https://doi.org/10.1158/1940-6207.Capr-19-0556 CrossRefGoogle ScholarPubMed
di Marco, G., Bevilacqua, E., Passananti, E., Neri, C., Airoldi, C., Maccarrone, A., Ciavarro, V., Lanzone, A., & Familiari, A. (2023). Multiple pregnancy and the risk of postpartum hemorrhage: Retrospective analysis in a tertiary level center of care. Diagnostics, 13. https://doi.org/10.3390/diagnostics13030446 CrossRefGoogle Scholar
Dilla, A. J., Waters, J. H., & Yazer, M. H. (2013). Clinical validation of risk stratification criteria for peripartum hemorrhage. Obstetrics & Gynecology, 122, 120–126. https://doi.org/10.1097/AOG.0b013e3182941c78 CrossRefGoogle ScholarPubMed
Easter, S. R., Robinson, J. N., Lieberman, E., & Carusi, D. (2017). Association of intended route of delivery and maternal morbidity in twin pregnancy. Obstetrics & Gynecology, l, 129, 305–310. https://doi.org/10.1097/aog.0000000000001844 CrossRefGoogle ScholarPubMed
Ekin, A., Gezer, C., Solmaz, U., Taner, C. E., Dogan, A., & Ozeren, M. (2015). Predictors of severity in primary postpartum hemorrhage. Arch Gynecol Obstet, 292, 1247–1254. https://doi.org/10.1007/s00404-015-3771-5 CrossRefGoogle ScholarPubMed
Ende, H. B., Lozada, M. J., Chestnut, D. H., Osmundson, S. S., Walden, R. L., Shotwell, M. S., & Bauchat, J. R. (2021). Risk factors for atonic postpartum hemorrhage: A systematic review and meta-analysis. Obstetrics & Gynecology, 137, 305–323. https://doi.org/10.1097/aog.0000000000004228 CrossRefGoogle ScholarPubMed
Feng, B., Zhai, J., & Cai, Y. (2018). Effect of twin pregnancy chorionic properties on maternal and fetal outcomes. Taiwanese Journal of Obstetrics and Gynecology, 57, 351–354. https://doi.org/10.1016/j.tjog.2018.03.002 CrossRefGoogle ScholarPubMed
Jiang, F., Gao, J., He, J., Tang, Y., Cao, Y., Wang, X., Liu, X., Wang, T., Liu, X., Sun, J., Zhong, M., Liu, X., Liao, S., Liu, C., & Yang, J. (2021). Obstetric outcomes for twins from different conception methods ¾ A multicenter cross-sectional study from China. Acta Obstetricia et Gynecologica Scandinavica, 100, 1061–1067. https://doi.org/10.1111/aogs.14116 CrossRefGoogle ScholarPubMed
Kong, C. W., & To, W. W. K. (2023). Risk factors for postpartum haemorrhage in twin pregnancies and haemorrhage severity. Hong Kong Medical Journal, 29, 295–300. https://doi.org/10.12809/hkmj219830 Google ScholarPubMed
Koopmans, C. M., van der Tuuk, K., Groen, H., Doornbos, J. P., de Graaf, I. M., van der Salm, P. C., Porath, M. M., Kuppens, S. M., Wijnen, E. J., Aardenburg, R., van Loon, A. J., Akerboom, B. M., van der Lans, P. J., Mol, B. W., & van Pampus, M. G. (2014). Prediction of postpartum hemorrhage in women with gestational hypertension or mild preeclampsia at term. Acta Obstetricia et Gynecologica Scandinavica, 93, 399–407. https://doi.org/10.1111/aogs.12352 CrossRefGoogle ScholarPubMed
Kramer, M. S., Berg, C., Abenhaim, H., Dahhou, M., Rouleau, J., Mehrabadi, A., & Joseph, K. S. (2013). Incidence, risk factors, and temporal trends in severe postpartum hemorrhage. American Journal of Obstetrics & Gynecology, 209, 449.e441–447. https://doi.org/10.1016/j.ajog.2013.07.007 CrossRefGoogle ScholarPubMed
Krishnamoorthy, S., Liu, Y., & Liu, K. (2022). A novel oppositional binary crow search algorithm with optimal machine learning based postpartum hemorrhage prediction model. BMC Pregnancy Childbirth, 22, 560. https://doi.org/10.1186/s12884-022-04775-z CrossRefGoogle ScholarPubMed
Liu, J., Wang, C., Yan, R., Lu, Y., Bai, J., Wang, H., & Li, R. (2022). Machine learning-based prediction of postpartum hemorrhage after vaginal delivery: Combining bleeding high risk factors and uterine contraction curve. Archives of Gynecology and Obstetrics, 306, 1015–1025. https://doi.org/10.1007/s00404-021-06377-0 CrossRefGoogle ScholarPubMed
Liu, Z., Chen, R., Huang, H., Yan, J., & Jiang, C. (2023). Predicting risk of postpartum hemorrhage associated with vaginal delivery of twins: A retrospective study. Medicine (Baltimore), 102, e36307. https://doi.org/10.1097/md.0000000000036307 CrossRefGoogle ScholarPubMed
McLintock, C. (2020). Prevention and treatment of postpartum hemorrhage: focus on hematological aspects of management. Hematology ASH Education Program, 2020, 542–546. https://doi.org/10.1182/hematology.2020000139 CrossRefGoogle ScholarPubMed
Miller, H. E., Leonard, S. A., Fox, K. A., Carusi, D. A., & Lyell, D. J. (2021). Placenta accreta spectrum among women with twin gestations. Obstetrics & Gynecology, 137, 132–138. https://doi.org/10.1097/aog.0000000000004204 CrossRefGoogle ScholarPubMed
Monden, C., Pison, G., & Smits, J. (2021). Twin Peaks: more twinning in humans than ever before. Human Reproduction, 36, 1666–1673. https://doi.org/10.1093/humrep/deab029 CrossRefGoogle Scholar
Qi, F., Tian, D., Wang, Y., & Jiao, L. (2018, October 19–21). Prediction of postpartum hemorrhage by adaptive K-nearest neighbor based on influence factors [Paper presentation]. 9th International Conference on Information Technology in Medicine and Education (ITME), Hangzhou, China.CrossRefGoogle Scholar
Qi, Y. (2012). Random forest for bioinformatics. In Zhang, C. & Ma, Yunquin (Eds.), Ensemble machine learning: Methods and applications (pp. 307–323) Springer.CrossRefGoogle Scholar
Rubio-Álvarez, A., Molina-Alarcón, M., Arias-Arias, Á., & Hernández-Martínez, A. (2018). Development and validation of a predictive model for excessive postpartum blood loss: A retrospective, cohort study. International Journal of Nursing Studies, 79, 114–121. https://doi.org/10.1016/j.ijnurstu.2017.11.009 CrossRefGoogle ScholarPubMed
Say, L., Chou, D., Gemmill, A., Tunçalp, Ö., Moller, A. B., Daniels, J., Gülmezoglu, A. M., Temmerman, M., & Alkema, L. (2014). Global causes of maternal death: a WHO systematic analysis. Lancet Global Health, 2, e323–333. https://doi.org/10.1016/s2214-109x(14)70227-x CrossRefGoogle ScholarPubMed
Seo, G. H., Kim, J. Y., Lee, D. Y., Lee, C., & Lee, J. (2023). Risk factors for severe postpartum hemorrhage requiring blood transfusion after cesarean delivery for twin pregnancy: A nationwide cohort study. Anesthesia and Pain Medicine, 18, 367–375. https://doi.org/10.17085/apm.23019 CrossRefGoogle ScholarPubMed
Suthaharan, S. (2016). Machine learning models and algorithms for big data classification. Springer.CrossRefGoogle Scholar
Tang, J., Deng, C., & Huang, G.-B. (2015). Extreme learning machine for multilayer perceptron. IEEE Transactions on Neural Networks and Learning Systems, 27, 809–821.CrossRefGoogle ScholarPubMed
Venkatesh, K. K., Strauss, R. A., Grotegut, C. A., Heine, R. P., Chescheir, N. C., Stringer, J. S. A., Stamilio, D. M., Menard, K. M., & Jelovsek, J. E. (2020). Machine learning and statistical models to predict postpartum hemorrhage. Obstetrics & Gynecology, 135, 935–944. https://doi.org/10.1097/aog.0000000000003759 CrossRefGoogle ScholarPubMed
Wang, R., Pan, W., Jin, L., Li, Y., Geng, Y., Gao, C., Chen, G., Wang, H., Ma, D., & Liao, S. (2019). Artificial intelligence in reproductive medicine. Reproduction, 158, 139–154. https://doi.org/10.1530/rep-18-0523 CrossRefGoogle ScholarPubMed
Westcott, J. M., Hughes, F., Liu, W., Grivainis, M., Hoskins, I., & Fenyo, D. (2022). Prediction of maternal hemorrhage using machine learning: Retrospective cohort study. Journal of Medical Internet Research, 24, e34108. https://doi.org/10.2196/34108 CrossRefGoogle ScholarPubMed
Zhang, H., Song, Y., Xu, S., He, Y., Li, Z., Yu, X., Liang, Y., Wu, W., & Wang, Y. (2022). Combining a class-weighted algorithm and machine learning models in landslide susceptibility mapping: A case study of Wanzhou section of the Three Gorges Reservoir, China. Computers & Geosciences, 158, 104966. https://doi.org/10.1016/j.cageo.2021.104966 CrossRefGoogle Scholar