Association between time of day and performance, indications, and outcomes of obstetric interventions among nulliparous women delivering at term

Time of Birth and the Risk of Adverse Maternal and Neonatal Outcomes-A Retrospective Cohort Study

Objectives: To determine whether in a labor floor housed continuously by senior physicians the risk of adverse maternal and neonatal outcome is affected by time of delivery. Methods: This retrospective cohort study, conducted at a tertiary medical center, assessed singleton term deliveries from 1 January 2011 to 30 January 2020. Participants were categorized based on delivery timing, correlating with nursing shifts, to evaluate perinatal outcomes. The primary endpoint included adverse maternal outcomes such as emergency Cesarean section, anal sphincter injuries, blood product transfusions, and postpartum surgeries (laparotomy/laparoscopy). Secondary outcomes focused on neonatal health indicators, including low Apgar scores, ICU admissions, respiratory issues, extended hospital stays, and neurological complications. Results: 87,863 deliveries were available for analysis with equal distribution during the day. The risk of adverse composite maternal outcome was highest during the evening (aOR 1.25, 95% CI 1.18-1.32) and lowest during the night (aOR 0.94, 95% CI 0.88-0.99) compared to daytime deliveries. This difference was primarily driven by the highest rate of emergency CD in the evening. Neonatal outcomes were comparable, except for length of stay > 5 days, which was more frequent among newborns delivered during the evening and night shifts compared to the morning shift (aOR 1.19, 95% CI 1.07-1.33 and aOR 1.17, 95% CI 1.05-1.31, respectively). Conclusions: In term pregnancies, the evening shift is associated with the highest risk of adverse maternal and neonatal outcomes despite physician seniority.

Busy day effect on the use of obstetrical interventions and epidural analgesia during labour: a cross-sectional register study of 601 247 deliveries

Background

Daily delivery volume might affect the quality of obstetric care. We explored the busy day effect on selected obstetrical interventions and epidural analgesia performed during labour in different sized delivery hospitals and on the Finnish obstetric ecosystem.

Methods

We conducted a cross-sectional study on Finnish Medical Birth Register data of singleton pregnancies (N = 601,247) from 26 delivery hospitals from 2006 to 2016. Delivery hospitals were stratified by annual delivery volume: C (category) 1: < 1000, C2: 1000–1999, C3: 2000–2999, C4: ≥3000, and C5: university hospitals. The exposure variables were defined as quiet, optimal, and busy days determined based on daily delivery volume distribution in each hospital category. Quiet and busy days included approximately 10% of the lowest and highest delivery volume days, while the rest were defined as optimal. Outcome measures were unplanned caesarean section (CS), instrumental delivery, induction of labour, and epidural analgesia. We compared the incidence of outcomes in quiet vs. optimal, busy vs. optimal, and busy vs. quiet days using logistic regression. The statistical significance level was set at 99% to reduce the likelihood of significant spurious findings.

Results

In the total population, the incidence of instrumental delivery was 8% (99% CI 2–15%) lower on quiet than on optimal days. In smaller hospitals (C1 and C2), unplanned caesarean sections were performed up to one-third less frequently on busy than optimal and quiet days. More (27%, 99% CI 12–44%) instrumental deliveries were performed in higher delivery volume hospitals (C4) on busy than quiet days. In C1-C3, deliveries were induced (12–35%) less often and in C5 (37%, 99% CI 28–45%) more often on busy than optimal delivery days. More (59–61%) epidural analgesia was performed on busy than optimal and quiet days in C4 and 8% less in C2 hospitals.

Conclusions

Pooled analysis showed that busyness had no effect on outcomes at the obstetric ecosystem level, but 10% fewer instrumental deliveries were performed in quiet than on busy days overall. Furthermore, dissecting the data shows that small hospitals perform less, and large non-tertiary hospitals perform more interventions during busy days.

Real-time data analysis using a machine learning model significantly improves prediction of successful vaginal deliveries

BACKGROUND

The process of childbirth is one of the most crucial events in the future health and development of the offspring. The vulnerability of parturients and fetuses during the delivery process led to the development of intrapartum monitoring methods and to the emergence of alternative methods of delivery. However, current monitoring methods fail to accurately discriminate between cases in which intervention is unnecessary, partly contributing to the high rates of cesarean deliveries worldwide. Machine learning methods are applied in various medical fields to create personalized prediction models. These methods are used to analyze abundant, complex data with intricate associations to aid in decision making. Initial attempts to predict vaginal delivery vs cesarean deliveries using machine learning tools did not utilize the vast amount of data recorded during labor. The data recorded during labor represent the dynamic process of labor and therefore may be invaluable for dynamic prediction of vaginal delivery.

OBJECTIVE

We aimed to create a personalized machine learning-based prediction model to predict successful vaginal deliveries using real-time data acquired during the first stage of labor.

STUDY DESIGN

Electronic medical records of labor occurring during a 12-year period in a tertiary referral center were explored and labeled. Four different models were created using input from multiple maternal and fetal parameters. Initial risk assessments for vaginal delivery were calculated using data available at the time of admission to the delivery unit, followed by models incorporating cervical examination data and fetal heart rate data, and finally, a model that integrates additional data available during the first stage of labor was created.

RESULTS

A total of 94,480 cases in which a trial of labor was attempted were identified. Based on approximately 180 million data points from the first stage of labor, machine learning models were developed to predict successful vaginal deliveries. A model using data available at the time of admission to the delivery unit yielded an area under the curve of 0.817 (95% confidence interval, 0.811-0.823). Models that used real-time data increased prediction accuracy. A model that includes real-time cervical examination data had an initial area under the curve of 0.819 (95% confidence interval, 0.813-0.825) at first examination, which increased to an area under the curve of 0.917 (95% confidence interval, 0.913-0.921) by the end of the first stage. Adding the real-time fetal heart monitor data provided an area under the curve of 0.824 (95% confidence interval, 0.818-0.830) at first examination, which increased to an area under the curve of 0.928 (95% confidence interval, 0.924-0.932) by the end of the first stage. Finally, adding additional real-time data increased the area under the curve initially to 0.833 (95% confidence interval, 0.827-0.838) at the first cervical examination and up to 0.932 (95% confidence interval, 0.928-0.935) by the end of the first stage.

CONCLUSION

Real-time data acquired throughout the process of labor significantly increased the prediction accuracy for vaginal delivery using machine learning models. These models enable translation and quantification of the data gathered in the delivery unit into a clinical tool that yields a reliable personalized risk score and helps avoid unnecessary interventions.