Prediction of severe adverse neonatal outcomes at the second stage of labour using machine learning: a retrospective cohort study.

OBJECTIVE: To create a personalised machine learning model for prediction of severe adverse neonatal outcomes (SANO) during the second stage of labour. DESIGN: Retrospective Electronic-Medical-Record (EMR) -based study. POPULATION: A cohort of 73 868 singleton, term deliveries that reached the second stage of labour, including 1346 (1.8%) deliveries with SANO. METHODS: A gradient boosting model was created, analysing 21 million data points from antepartum features (e.g. gravidity and parity) gathered at admission to the delivery unit, and intrapartum data (e.g. cervical dilatation and effacement) gathered during the first stage of labour. Deliveries were allocated to high-risk and low-risk groups based on the Youden index to maximise sensitivity and specificity. MAIN OUTCOME MEASURES: SANO was defined as either umbilical cord pH levels ≤7.1 or 1-minute or 5-minute Apgar score ≤7. RESULTS: The model for prediction of SANO yielded an area under the receiver operating curve (AUC) of 0.761 (95% CI 0.748-0.774). A third of the cohort (33.5%, n = 24 721) were allocated to a high-risk group for SANO, which captured up to 72.1% of these cases (odds ratio 5.3, 95% CI 4.7-6.0; high-risk versus low-risk groups). CONCLUSIONS: Data acquired throughout the first stage of labour can be used to predict SANO during the second stage of labour using a machine learning model. Stratifying parturients at the beginning of the second stage of labour in a 'time out' session, can direct a personalised approach to management of this challenging aspect of labour, as well as improve allocation of staff and resources. TWEETABLE ABSTRACT: Personalised prediction score for severe adverse neonatal outcomes in labour using machine learning model.

Planned induction versus spontaneous delivery among women using prophylactic anticoagulation therapy: a retrospective study.

OBJECTIVES: To examine the outcomes of planned induction of labour versus spontaneous onset of labour among women using prophylactic-dose low-molecular weight heparin (LMWH) therapy. DESIGN: Retrospective cohort study. SETTING: University hospital. POPULATION: Women receiving antepartum prophylactic LMWH therapy undergoing a trial of vaginal delivery. METHODS: Charts from 2018-2019 were reviewed. MAIN OUTCOME MEASURES: Duration of anticoagulation interruption and eligibility to receive neuraxial anaesthesia. RESULTS: Data from 199 women were analysed; 78 (39.2%) were admitted following spontaneous onset of labour and 121 (60.8%) underwent planned induction of labour. Compared to women who underwent planned induction of labour, women who presented with spontaneous onset of labour had a shorter median admission-to-delivery interval (4.7 versus 29.3 hours, P < 0.001). Similarly, intervals from the last LMWH injection to delivery (25.8 versus 48.2 hours, P < 0.001) and to the first postpartum LMWH injection (41.2 versus 63.7 hours, P < 0.001) were shorter. Among those with spontaneous onset of labour, 69 (88.5%) were eligible to receive neuraxial anaesthesia. Rates of postpartum haemorrhage and blood transfusion were similar between the groups. No thrombotic events were encountered in those with spontaneous onset of labour, but four (3.3%) women who delivered following induction of labour developed a postpartum thrombotic event. CONCLUSION: Planned induction of labour was associated with a higher risk of postpartum thrombotic events than was spontaneous onset of labour (4 of 121 [3.3%] versus 0 of 78 [0%]), presumably due to prolonged duration of anticoagulation interruption, although the difference was not statistically significant. Allowing spontaneous onset of labour was associated with comparable rates of bleeding complications, and only a low proportion (9 of 78, 11.5%) were not eligible to receive neuraxial anaesthesia. TWEETABLE ABSTRACT: Planned induction among women using prophylactic LMWH therapy might increase the risk of thromboembolic complications.