Title: A prediction model for successful vaginal birth after caesarean delivery in Chinese mothers by using machine learning

Authors: Lin Rao; Wei Gao; Kaixin Fu; Yingying Zhang; Yu Huang; Xuan Zhou; Hong Li

Addresses: Department of Nursing, International Peace Maternity and Child Health Hospital, Shanghai Jiao Tong University, 910 Hengshan Road, Xuhui District, Shanghai, 200000, China ' Department of Nursing, International Peace Maternity and Child Health Hospital, Shanghai Jiao Tong University, 910 Hengshan Road, Xuhui District, Shanghai, 200000, China ' Department of Automation, Key Laboratory of System Control and Information Processing, Ministry of Education, Shanghai Jiao Tong University, Minhang District, Shanghai, 200000, China ' Department of Nursing, The Children's Hospital of Fudan University, Fudan University, Minhang District, Shanghai, 200000, China ' International Peace Maternity and Child Health Hospital, 910 Hengshan Road, Xuhui District, Shanghai, 200000, China ' International Peace Maternity and Child Health Hospital, 910 Hengshan Road, Xuhui District, Shanghai, 200000, China ' International Peace Maternity and Child Health Hospital, 910 Hengshan Road, Xuhui District, Shanghai, 200000, China

Abstract: Background: This study aimed to build a personalised prediction algorithm for successful vaginal birth after caesarean delivery in Chinese mothers. Methods: This study used data from the electronic medical records of 406 admitted pregnant women between January 2010 and October 2020. Descriptive analyses, chi-square tests, and multivariate logistic regression were undertaken. By using the Spearman correlation coefficient, a prediction model for successful vaginal birth after caesarean delivery was derived. Results: The identified predictors included degree of cervical dilatation, fetal exposure, cervical canal regression, uterine orifice location, height, the thickness of the lower uterine segment, gestational age, BMI before delivery, and estimated birth weight. The prediction model performed well with an area under the receiver operating characteristics curve of 0.954 (95% CI, 0.87-0.94). Conclusion: The results show that the prediction model can better predict VBAC. The new prediction model may be used in clinical consultations to decide the preferred delivery mode.

Keywords: prediction model; caesarean delivery; obstetrics; trial of labour; vaginal delivery.

DOI: 10.1504/IJSCIP.2024.138667

International Journal of System Control and Information Processing, 2024 Vol.4 No.2, pp.123 - 137

Received: 16 May 2023
Accepted: 25 May 2023
Published online: 23 May 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article