Clinical Applications of AI-Based Fetal Monitoring in Labor Management and Its Impact on Maternal and Neonatal Outcomes

Abstract

Objective: To investigate the clinical application of AI-based labor monitoring in labor management and its impact on maternal and fetal outcomes. Methods: A total of 240 pregnant women scheduled for vaginal trial of labor admitted to our hospital from January 2024 to June 2025 were selected as study subjects. They were randomly divided into a control group and an observation group, each comprising 120 cases. The control group underwent traditional manual timed monitoring, while the observation group received AI-based labor monitoring. This study compared the duration of each stage of labor, mode of delivery, incidence of related complications, and rate of neonatal adverse events between the two groups, and evaluated the accuracy of identifying abnormal labor patterns and differences in healthcare workload. Results: The duration of the first and second stages of labor, as well as the total duration of labor, was significantly shorter in the observation group than in the control group; the incidence of cesarean sections without medical indications, postpartum hemorrhage, and puerperal infections was significantly lower in the observation group than in the control group (p < 0.05); the incidence of meconium-stained amniotic fluid, mild asphyxia, and neonatal intensive care unit admission rates were all lower in the observation group than in the control group (p < 0.05); the observation group had lower rates of missed or misdiagnosed labor abnormalities, and the workload associated with medical documentation and repetitive monitoring was significantly reduced (p < 0.05). Conclusion: The AI-based labor monitoring system enables comprehensive, continuous, and precise management throughout labor, effectively accelerating labor progression, avoiding overtreatment, and reducing the risk of adverse maternal and neonatal complications. It also optimizes obstetric workflows and enhances the standardization of diagnosis and treatment, demonstrating promising prospects for clinical implementation.