Effective Prediction Model for Adverse Neonatal Outcomes at the Onset of the Second Stage of Labor

The experts of the study developed a prediction model for adverse neonatal outcomes using electronic fetal monitoring (EFM) interpretation data and other significant clinical information at the beginning of the second stage of labor.

The present retrospective cohort study included women who labored and delivered between July 2016 and June 2020 and had a singleton gestation at term (more than 37 weeks of gestation), a vertex-presenting, nonanomalous fetus, and planned vaginal delivery. The primary outcome was a composite of severe adverse neonatal outcomes, which occurred in 3.2% of the 22,454 patients analyzed. Among the three evaluated modeling approaches, traditional logistic regression, LASSO, and extreme gradient boosting, the logistic regression model demonstrated the best discrimination (0.690) and was well calibrated. When risk was stratified into three groups, the rates of adverse outcomes increased significantly with risk level: 2.6% for no increased risk, 6.7% for higher risk, and 10.3% for highest risk. Important factors associated with the composite adverse neonatal outcome included the presence of meconium (aOR 2.10), fetal tachycardia in the two hours before the second stage (aOR 1.94), and the number of prior deliveries (aOR 0.77).

Thus, the study concluded that the logistic regression model could effectively predict adverse neonatal outcomes and stratify risk, which could assist clinicians in decision-making during labor.

Source: Clapp MA, Li S, James KE, Reiff ES, Little SE, McCoy TH, Perlis RH, Kaimal AJ. Development of a Practical Prediction Model for Adverse Neonatal Outcomes at the Start of the Second Stage of Labor. Obstet Gynecol. 2024 Oct 31. doi: 10.1097/AOG.0000000000005776. Epub ahead of print. PMID: 39481108.