Validating machine learning models for the prediction of labour induction intervention using routine data: a registry-based retrospective cohort study at a tertiary hospital in northern Tanzania. | LitMetric
Objectives: We aimed at identifying the important variables for labour induction intervention and assessing the predictive performance of machine learning algorithms.
Setting: We analysed the birth registry data from a referral hospital in northern Tanzania. Since July 2000, every birth at this facility has been recorded in a specific database.
Participants: 21 578 deliveries between 2000 and 2015 were included. Deliveries that lacked information regarding the labour induction status were excluded.
Primary Outcome: Deliveries involving labour induction intervention.
Results: Parity, maternal age, body mass index, gestational age and birth weight were all found to be important predictors of labour induction. Boosting method demonstrated the best discriminative performance (area under curve, AUC=0.75: 95% CI (0.73 to 0.76)) while logistic regression presented the least (AUC=0.71: 95% CI (0.70 to 0.73)). Random forest and boosting algorithms showed the highest net-benefits as per the decision curve analysis.
Conclusion: All of the machine learning algorithms performed well in predicting the likelihood of labour induction intervention. Further optimisation of these classifiers through hyperparameter tuning may result in an improved performance. Extensive research into the performance of other classifier algorithms is warranted.
Uterine rupture is a well-known, life-threatening complication of misoprostol use; the incidence is remarkably low. Herein, we report what seems to be the first documented case of uterine rupture following induction of labour for intrauterine foetal death in the second trimester without a uterine scar. A 40-year-old woman with no history of caesarean section or uterine surgery presented with mild lower abdominal pain and mild genital bleeding.
Department of Anesthesiology, West China Second University Hospital, Sichuan University, No. 20, Section 3, South of Renmin Road, Chengdu, 610041, Sichuan, China.
Background: Preterm birth, a leading cause of perinatal mortality and morbidity, is often associated with inflammation and aberrant myometrial contractions. This study investigates the role of Piezo1, a mechanosensitive ion channel, in myometrium contraction and inflammation-associated preterm birth.
Methods: We employed Western blotting, Immunofluorescence, and Quantitative real-time PCR techniques to examine Piezo1 expression in uterine tissues.
Introduction: Recurrent pregnancy loss (RPL), defined as two or more pregnancy losses, might be associated with elevated obstetrical and perinatal risks in the following pregnancies. RPL and pregnancy problems related to placental development may have similar etiological features. This study explores the incidences of pregnancy and perinatal outcomes in women with RPL.
The aim of this study was to explore women's preferences and experiences of degree of control in decision making when planning an induction of labor (IOL). This multi-method study was conducted using semi-structured individual interviews and the completion of two Control Preferences Scales by eight postnatal women from a metropolitan health service in Melbourne, Australia. Four themes were generated from the interview data: "shared decision making"; "changing expectations"; "IOL experience"; and "informed consent.
