Abstract: The procedure of external cephalic version (ECV) is an important option in the management of breech presentation. However, there is still a lack of effective methods to accurately predict the likelihood of ECV success on the basis of individual conditions. With the aim of better predicting the outcomes of ECV and subsequent delivery modes, this study developed neural network-based models. We conducted a retrospective cohort study of women with singleton pregnancies who underwent an ECV for breech presentation at a single, tertiary, university-affiliated hospital between January 2016 and September 2023. Data on the demographic characteristics, comprehensive preoperative ultrasound assessment, and conditions during the ECV procedure were extracted from the hospital’s electronic record system. A neural network algorithm was implemented to establish prediction models for the success or failure of ECV, as well as subsequent delivery modes. The performance of the models was improved by increasing the number of iterations. A total of 378 patients were retrospectively included, including 279 successful and 99 failed cases, showing an overall success rate of 73.8%. Univariate analysis revealed that gravidity, parity, systolic blood pressure, presence of uterine fibroids, and amniotic fluid index (AFI) indicated by preoperative and intra-operative ultrasound were positively associated with ECV success, while thicker maternal abdominal walls and the use of anesthesia were correlated with failure. Multivariate analysis determined that parity, uterine fibroids, AFI, and the use of anesthesia were independent determinants of ECV outcomes. The samples were then divided into training and testing sets in a 1׃1 ratio. By increasing the number of iterations, the true positive rates for the successful and failed versions both reached 100%. The overall accuracy was 82.5% for predicting ECV outcomes. A total of 291 samples with delivery records were included for the prediction of delivery modes. The neural network-based model achieved a predictive accuracy of 78.8% after 2000 iterations, with the true positive rates for vaginal delivery and cesarean section both reaching 100%. These algorithms output exact predicted probabilities instead of providing the outcomes alone. An external validation set was also employed to further confirm the algorithm’s performance. Collectively, prediction models formulated on the basis of neural network algorithms were developed to assess the ECV outcomes and subsequent delivery modes, with both models demonstrating favorable results and great performance. For women eligible for ECV, the application of these models can potentially assist in the crucial clinical decision-making process.

神经网络预测臀位外倒转术的临床结局：一项回顾性队列研究

[1]American College of Obstetricians and Gynecologists, 2020. External cephalic version: ACOG practice bulletin, Number 221. Obstet Gynecol, 135(5):e203-e212.

[2]Boujenah J, Fleury C, Bonneau C, et al., 2017. Successful external cephalic version is an independent factor for caesarean section during trial of labor‒a matched controlled study. J Gynecol Obstet Hum Reprod, 46(10):737-742.

[3]Bresson J, Christie K, Walker S, 2023. Not too fast, not too slow: a review of historical trends in vaginal breech time management. Eur J Obstet Gynecol Reprod Biol, 287:216-220.

[4]Dahl CM, Zhang Y, Ong JX, et al., 2021. A multivariable predictive model for success of external cephalic version. Obstet Gynecol, 138(3):426-433.

[5]de Castro H, Ciobanu A, Formuso C, et al., 2020. Value of routine ultrasound examination at 35‒37 weeks’ gestation in diagnosis of non-cephalic presentation. Ultrasound Obstet Gynecol, 55(2):248-256.

[6]Hakem E, Lindow SW, O'Connell MP, et al., 2021. External cephalic version ‒ a 10-year review of practice. Eur J Obstet Gynecol Reprod Biol, 258:414-417.

[7]Impey LWM, Murphy DJ, Griffiths M, et al., 2017. External cephalic version and reducing the incidence of term breech presentation. BJOG, 124(7):e178-e192.

[8]Isakov O, Reicher L, Lavie A, et al., 2019. Prediction of success in external cephalic version for breech presentation at term. Obstet Gynecol, 133(5):857-866.

[9]Issaiy M, Zarei D, Saghazadeh A, 2023. Artificial intelligence and acute appendicitis: a systematic review of diagnostic and prognostic models. World J Emerg Surg, 18:59.

[10]Kasera B, Shinar S, Edke P, et al., 2024. Deep-learning computer vision can identify increased nuchal translucency in the first trimester of pregnancy. Prenat Diagn, 44(5):535-543.

[11]Kishkovich TP, Naert MN, Warsame F, et al., 2023. External validation of a prediction model for external cephalic version success. Obstet Gynecol, 141(5):964-966.

[12]Kuppens SM, Smailbegovic I, Houterman S, et al., 2017. Fetal heart rate abnormalities during and after external cephalic version: which fetuses are at risk and how are they delivered? BMC Pregnancy Childbirth, 17:363.

[13]Levin G, Rottenstreich A, Weill Y, et al., 2019. External cephalic version at term: a 6-year single-operator experience. Birth, 46(4):616-622.

[14]Levin G, Rottenstreich A, Meyer R, et al., 2020. Management of labor after external cephalic version. J Perinat Med, 49(1):30-35.

[15]Londero AP, Xholli A, Massarotti C, et al., 2023. Factors influencing the effect of external cephalic version: a retrospective nationwide cohort analysis. Arch Gynecol Obstet, 308(4):1127-1137.

[16]Long Q, Zhang YG, Zhang J, et al., 2022. Changes in caesarean section rates in China during the period of transition from the one-child to two-child policy era: cross-sectional National Household Health Services Surveys. BMJ Open, 12(4):e059208.

[17]López-Pérez R, Lorente-Fernández M, Velasco-Martínez M, et al., 2020. Prediction model of success for external cephalic version. Complications and perinatal outcomes after a successful version. J Obstet Gynaecol Res, 46(10):2002-2009.

[18]Magro-Malosso ER, Saccone G, di Tommaso M, et al., 2016. Neuraxial analgesia to increase the success rate of external cephalic version: a systematic review and meta-analysis of randomized controlled trials. Am J Obstet Gynecol, 215(3):276-286.

[19]Olson Koutrouvelis G, 2019. Role of external cephalic version in reducing the cesarean delivery rate. Obstet Gynecol, 133(5):855-856.

[20]Płotka SS, Grzeszczyk MK, Szenejko PI, et al., 2023. Deep learning for estimation of fetal weight throughout the pregnancy from fetal abdominal ultrasound. Am J Obstet Gynecol MFM, 5(12):101182.

[21]Renganathan V, 2019. Overview of artificial neural network models in the biomedical domain. Bratisl Lek Listy, 120(7):536-540.

[22]Rodgers R, Beik N, Nassar N, et al., 2017. Complications of external cephalic version: a retrospective analysis of 1121 patients at a tertiary hospital in Sydney. BJOG, 124(5):767-772.

[23]Schreiber H, Daykan Y, Arbib N, et al., 2019. Adverse pregnancy outcomes and multiple nuchal cord loops. Arch Gynecol Obstet, 300(2):279-283.

[24]Sium AF, Gudu W, Urgie T, et al., 2023. External cephalic version success rate and associated factors: experience from a tertiary center in Sub-Saharan Africa: a cross-sectional study. PLoS ONE, 18(1):e0280404.

[25]Sun BR, Fang YW, Yang H, et al., 2024. The combination of deep learning and pseudo-MS image improves the applicability of metabolomics to congenital heart defect prenatal screening. Talanta, 275:126109.

[26]Svensson E, Axelsson D, Nelson M, et al., 2021. Success rate of external cephalic version in relation to the woman’s body mass index and other factors—a population-based cohort study. Acta Obstet Gynecol Scand, 100(12):2260-2267.

[27]Velzel J, de Hundt M, Mulder FM, et al., 2015. Prediction models for successful external cephalic version: a systematic review. Eur J Obstet Gynecol Reprod Biol, 195:160-167.

[28]Vogel JP, Pujar Y, Vernekar SS, et al., 2024. Effects of the WHO Labour Care Guide on cesarean section in India: a pragmatic, stepped-wedge, cluster-randomized pilot trial. Nat Med, 30(2):463-469.

[29]Xiang YT, Lin HX, Zhou QJ, et al., 2026. The influence of advanced maternal age on the success rate, delivery mode and maternal and fetal outcomes of pregnant women undergoing external cephalic version: a retrospective cohort study. BMC Pregnancy Childbirth, 26:87.

Similar articles