Machine learning-based prediction of postpartum hemorrhage after vaginal delivery: combining bleeding high risk factors and uterine contraction curve
- PMID: 35171347
- DOI: 10.1007/s00404-021-06377-0
Machine learning-based prediction of postpartum hemorrhage after vaginal delivery: combining bleeding high risk factors and uterine contraction curve
Abstract
Purpose: This work used a machine learning model to improve the accuracy of predicting postpartum hemorrhage in vaginal delivery.
Methods: Among the 25,098 deliveries in the obstetrics department of the First Hospital of Jinan University recorded from 2016 to 2020, 10,520 were vaginal deliveries with complete study data. Further review selected 850 cases of postpartum hemorrhage (amount of bleeding > 500 mL) and 54 cases of severe postpartum hemorrhage (amount of bleeding > 1000 mL). Indicators of clinical risk factors for postpartum hemorrhage were retrieved from electronic medical records. Features of the uterine contraction curve were extracted 2 h prior to vaginal delivery and modeled using a 49-variable machine learning with 90% of study cases used in the training set and 10% of study cases used in the test set. Accuracy was compared among the assessment table, classical statistical models, and machine learning models used to predict postpartum hemorrhage to assess their clinical use. The assessment table contained 16 high-risk factor scores to predict postpartum hemorrhage. The classical statistical model used was Logistic Regression (LR). The machine learning models were Random Forest (RF), K Nearest Neighbor (KNN), and the one integrated with Lightgbm (LGB) and LR. The effect of model prediction was evaluated by area under the receiver operating characteristic curve (AUC), namely, C-static, calibration curve Brier score, decision curve, F-measure, sensitivity (SE), and specificity (SP).
Results: 1: Among the tested tools, the machine learning model LGB + LR has the best performance in predicting postpartum hemorrhage. Its Brier, AUC, and F-measure scores are better than those of other models in each group, and its SE and SP reach 0.694 and 0.800, respectively. The predictive performance of the classical statistical model LR is AUC: 0.729, 95%CI [0.702-0.756]). 2: Verification on the testing set reveals that the features of uterine contraction contribute to the improved accuracy of the model prediction. 3: LGB + LR model suggested that among the 49 indicators for predicting severe postpartum hemorrhage, the importance of the first 10 characteristics in descending order is as follows: hematocrit (%), shock index, frequency of contractions (min-1), white blood cell count, gestational hypertension, neonatal weight (kg), time of second labor (min), mean area of contractions (mmHg s), total amniotic fluid (mL), and body mass index (BMI). The prediction effect is close to that of the model after training with all 49 features. The predictive effect was close to that of the model after training using all 49 features. 4: Contraction frequency and intensity Mean_Area (representing effective contractions) have a high predictive value for severe postpartum hemorrhage. 5: Blood loss amount within 2 h has a high warning effect on postpartum hemorrhage, and the increase in AUC to 0.95 indicates that postpartum bleeding mostly occurs within 2 h after delivery.
Conclusion: Machine learning models incorporated with uterine contraction features can further improve the accuracy of postpartum hemorrhage prediction in vaginal delivery and provide a reference for clinicians to intervene early and reduce adverse pregnancy outcomes.
Keywords: Machine learning; Postpartum hemorrhage; Prediction model; Vaginal delivery.
© 2022. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.
Similar articles
-
Machine Learning Algorithms Versus Classical Regression Models in Pre-Eclampsia Prediction: A Systematic Review.Curr Hypertens Rep. 2024 Jul;26(7):309-323. doi: 10.1007/s11906-024-01297-1. Epub 2024 May 28. Curr Hypertens Rep. 2024. PMID: 38806766 Free PMC article. Review.
-
Prediction of Maternal Hemorrhage Using Machine Learning: Retrospective Cohort Study.J Med Internet Res. 2022 Jul 18;24(7):e34108. doi: 10.2196/34108. J Med Internet Res. 2022. PMID: 35849436 Free PMC article.
-
Prediction and Evaluation of Machine Learning Algorithm for Prediction of Blood Transfusion during Cesarean Section and Analysis of Risk Factors of Hypothermia during Anesthesia Recovery.Comput Math Methods Med. 2022 Apr 13;2022:8661324. doi: 10.1155/2022/8661324. eCollection 2022. Comput Math Methods Med. 2022. Retraction in: Comput Math Methods Med. 2023 Jun 28;2023:9863486. doi: 10.1155/2023/9863486. PMID: 35465016 Free PMC article. Retracted.
-
Machine learning approach for the prediction of postpartum hemorrhage in vaginal birth.Sci Rep. 2021 Nov 19;11(1):22620. doi: 10.1038/s41598-021-02198-y. Sci Rep. 2021. PMID: 34799687 Free PMC article.
-
Comparison of Multivariable Logistic Regression and Other Machine Learning Algorithms for Prognostic Prediction Studies in Pregnancy Care: Systematic Review and Meta-Analysis.JMIR Med Inform. 2020 Nov 17;8(11):e16503. doi: 10.2196/16503. JMIR Med Inform. 2020. PMID: 33200995 Free PMC article. Review.
Cited by
-
An Explainable Artificial Intelligence Model Proposed for the Prediction of Myalgic Encephalomyelitis/Chronic Fatigue Syndrome and the Identification of Distinctive Metabolites.Diagnostics (Basel). 2023 Nov 21;13(23):3495. doi: 10.3390/diagnostics13233495. Diagnostics (Basel). 2023. PMID: 38066735 Free PMC article.
-
Prediction of postpartum hemorrhage using traditional statistical analysis and a machine learning approach.AJOG Glob Rep. 2023 Feb 17;3(2):100185. doi: 10.1016/j.xagr.2023.100185. eCollection 2023 May. AJOG Glob Rep. 2023. PMID: 36935935 Free PMC article.
-
Development and validation of a machine learning-based predictive model for secondary post-tonsillectomy hemorrhage.Front Surg. 2023 Feb 7;10:1114922. doi: 10.3389/fsurg.2023.1114922. eCollection 2023. Front Surg. 2023. PMID: 36824494 Free PMC article.
References
-
- Bais J, Eskes M, Pel M, Bonsel G, Bleker O (2004) Postpartum haemorrhage in nulliparous women: incidence and risk factors in low and high risk womena dutch population-based cohort study on standard (≥500 ml) and severe (≥1000 ml) postpartum haemorrhage. Eur J Obstetr Gynecol Reprod Biol 115(2):166–172
-
- Briley A, Seed PT, Tydeman G, Ballard H, Waterstone M, Sandall J, Poston L, Tribe RM, Bewley S (2014) Reporting errors, incidence and risk factors for postpartum haemorrhage and progression to severe pph: a prospective observational study. BJOG Int J Obstetr Gynaecol 121(7):876–888 - DOI
-
- Khan KS, Wojdyla D, Say L, Gülmezoglu AM, Van Look PF (2006) Who analysis of causes of maternal death: a systematic review. The Lancet 367(9516):1066–1074 - DOI
-
- Knight M, Callaghan WM, Berg C, Alexander S, Bouvier-Colle MH, Ford JB et al (2010) Trends in postpartum hemorrhage in high resource countries: a review and recommendations from the international postpartum hemorrhage collaborative group. Obstetr Gynecol Survey 65(4):211–212 - DOI
-
- American College of Obstetricians and Gynecologists (2017) Postpartum hemorrhage. Practice bulletin No. 183. Obstet Gynecol 130:e168–e186 - DOI
Publication types
MeSH terms
LinkOut - more resources
Full Text Sources
Miscellaneous