Continued Versus Discontinued Oxytocin Stimulation in the Active Phase of Labour (CONDISOX): Individual Management Based on Artificial Intelligence - a Secondary Analysis

Overview

Journal BMC Pregnancy Childbirth

Publisher Biomed Central

Specialty Gynecology & Obstetrics

Date 2024 Apr 19

PMID 38641779

Authors

Sidsel Boie

Julie Glavind

Pinar Bor

Philip Steer

Anders Hammerich Riis

Bo Thiesson

Niels Uldbjerg

Affiliations

Soon will be listed here.

Abstract

Background: Current guidelines regarding oxytocin stimulation are not tailored to individuals as they are based on randomised controlled trials. The objective of the study was to develop an artificial intelligence (AI) model for individual prediction of the risk of caesarean delivery (CD) in women with a cervical dilatation of 6 cm after oxytocin stimulation for induced labour. The model included not only variables known when labour induction was initiated but also variables describing the course of the labour induction.

Methods: Secondary analysis of data from the CONDISOX randomised controlled trial of discontinued vs. continued oxytocin infusion in the active phase of induced labour. Extreme gradient boosting (XGBoost) software was used to build the prediction model. To explain the impact of the predictors, we calculated Shapley additive explanation (SHAP) values and present a summary SHAP plot. A force plot was used to explain specifics about an individual's predictors that result in a change of the individual's risk output value from the population-based risk.

Results: Among 1060 included women, 160 (15.1%) were delivered by CD. The XGBoost model found women who delivered vaginally were more likely to be parous, taller, to have a lower estimated birth weight, and to be stimulated with a lower amount of oxytocin. In 108 women (10% of 1060) the model favoured either continuation or discontinuation of oxytocin. For the remaining 90% of the women, the model found that continuation or discontinuation of oxytocin stimulation affected the risk difference of CD by less than 5% points.

Conclusion: In women undergoing labour induction, this AI model based on a secondary analysis of data from the CONDISOX trial may help predict the risk of CD and assist the mother and clinician in individual tailored management of oxytocin stimulation after reaching 6 cm of cervical dilation.

References

Danilack V, Hutcheon J, Triche E, Dore D, Muri J, Phipps M . Development and Validation of a Risk Prediction Model for Cesarean Delivery After Labor Induction. J Womens Health (Larchmt). 2019; 29(5):656-669. PMC: 8935479. DOI: 10.1089/jwh.2019.7822. View

Boie S, Glavind J, Velu A, Mol B, Uldbjerg N, de Graaf I . Discontinuation of intravenous oxytocin in the active phase of induced labour. Cochrane Database Syst Rev. 2018; 8:CD012274. PMC: 6513418. DOI: 10.1002/14651858.CD012274.pub2. View

Boie S, Glavind J, Uldbjerg N, Steer P, Bor P . Continued versus discontinued oxytocin stimulation in the active phase of labour (CONDISOX): double blind randomised controlled trial. BMJ. 2021; 373:n716. PMC: 8044921. DOI: 10.1136/bmj.n716. View

Lundberg S, Erion G, Chen H, DeGrave A, Prutkin J, Nair B . From Local Explanations to Global Understanding with Explainable AI for Trees. Nat Mach Intell. 2020; 2(1):56-67. PMC: 7326367. DOI: 10.1038/s42256-019-0138-9. View

Bzdok D, Altman N, Krzywinski M . Statistics versus machine learning. Nat Methods. 2018; 15(4):233-234. PMC: 6082636. DOI: 10.1038/nmeth.4642. View

Ozenne B, Subtil F, Maucort-Boulch D . The precision--recall curve overcame the optimism of the receiver operating characteristic curve in rare diseases. J Clin Epidemiol. 2015; 68(8):855-9. DOI: 10.1016/j.jclinepi.2015.02.010. View

Kamel R, Negm S, Youssef A, Bianchini L, Brunelli E, Pilu G . Predicting cesarean delivery for failure to progress as an outcome of labor induction in term singleton pregnancy. Am J Obstet Gynecol. 2021; 224(6):609.e1-609.e11. DOI: 10.1016/j.ajog.2020.12.1212. View

Wie J, Lee S, Choi S, Jo Y, Hwang H, Park M . Prediction of Emergency Cesarean Section Using Machine Learning Methods: Development and External Validation of a Nationwide Multicenter Dataset in Republic of Korea. Life (Basel). 2022; 12(4). PMC: 9033083. DOI: 10.3390/life12040604. View

Levine L, Downes K, Parry S, Elovitz M, Sammel M, Srinivas S . A validated calculator to estimate risk of cesarean after an induction of labor with an unfavorable cervix. Am J Obstet Gynecol. 2017; 218(2):254.e1-254.e7. PMC: 5807156. DOI: 10.1016/j.ajog.2017.11.603. View

10.

Steer P, Glavind J, Uldbjerg N, Bor P, Boie S . Continued versus discontinued oxytocin stimulation in the active phase of induced labour: Factors associated with unexpectedly high rates of conversion to open label oxytocin in the CONDISOX trial. BJOG. 2023; 130(6):636-642. DOI: 10.1111/1471-0528.17376. View

11.

Dhombres F, Bonnard J, Bailly K, Maurice P, Papageorghiou A, Jouannic J . Contributions of Artificial Intelligence Reported in Obstetrics and Gynecology Journals: Systematic Review. J Med Internet Res. 2022; 24(4):e35465. PMC: 9069308. DOI: 10.2196/35465. View

12.

Boie S, Glavind J, Uldbjerg N, Bakker J, van der Post J, Steer P . CONDISOX- continued versus discontinued oxytocin stimulation of induced labour in a double-blind randomised controlled trial. BMC Pregnancy Childbirth. 2019; 19(1):320. PMC: 6720847. DOI: 10.1186/s12884-019-2461-x. View

13.

Marsal K, Persson P, Larsen T, Lilja H, Selbing A, Sultan B . Intrauterine growth curves based on ultrasonically estimated foetal weights. Acta Paediatr. 1996; 85(7):843-8. DOI: 10.1111/j.1651-2227.1996.tb14164.x. View

14.

Meyer R, Hendin N, Zamir M, Mor N, Levin G, Sivan E . Implementation of machine learning models for the prediction of vaginal birth after cesarean delivery. J Matern Fetal Neonatal Med. 2020; 35(19):3677-3683. DOI: 10.1080/14767058.2020.1837769. View

15.

Lauritsen S, Thiesson B, Johansson Jorgensen M, Riis A, Espelund U, Weile J . The Framing of machine learning risk prediction models illustrated by evaluation of sepsis in general wards. NPJ Digit Med. 2021; 4(1):158. PMC: 8593052. DOI: 10.1038/s41746-021-00529-x. View

16.

DAscenzo F, De Filippo O, Gallone G, Mittone G, Deriu M, Iannaccone M . Machine learning-based prediction of adverse events following an acute coronary syndrome (PRAISE): a modelling study of pooled datasets. Lancet. 2021; 397(10270):199-207. DOI: 10.1016/S0140-6736(20)32519-8. View

17.

de Carvalho L, Gioppato S, Fernandez M, Trindade B, Silva J, Miranda R . Machine Learning Improves the Identification of Individuals With Higher Morbidity and Avoidable Health Costs After Acute Coronary Syndromes. Value Health. 2020; 23(12):1570-1579. DOI: 10.1016/j.jval.2020.08.2091. View