Labor management remains a critical issue in obstetrics, with dystocic labor presenting significant challenges in both management and outcomes. Recent advancements in intrapartum ultrasound have facilitated substantial progress in monitoring labor progression. This paper explores the integration of artificial intelligence (AI) into obstetric care, focusing on the Artificial Intelligence Dystocia Algorithm (AIDA) for assessing spatial dystocia during labor. The AIDA utilizes intrapartum ultrasonography to measure four geometric parameters: the angle of progression, the degree of asynclitism, the head-symphysis distance, and the midline angle. These measurements are analyzed using machine learning techniques to predict delivery outcomes and stratify risk. The AIDA classification system categorizes labor events into five classes, providing a nuanced assessment of labor progression. This approach offers several potential advantages, including objective assessment of fetal position, earlier detection of malpositions, and improved risk stratification, placing labor events within a broader context of labor dystocia and obstetric care and discussing their potential impact on clinical practice. This paper serves as a more comprehensive overview and discussion of the AIDA approach, its implications, perspectives, and future directions. However, challenges such as the technological requirements, training needs, and integration with clinical workflows are also addressed. This study emphasizes the necessity for additional validation across diverse populations and careful consideration of its ethical implications. The AIDA represents a significant advancement in applying AI to intrapartum care, potentially enhancing clinical decision-making and improving outcomes in cases of suspected dystocia. This paper explicates the key methodological approaches underpinning the AIDA, illustrating the integration of artificial intelligence and clinical expertise. The innovative framework presented offers a paradigm for similar endeavors in other medical specialties, potentially catalyzing advancements in AI-assisted healthcare beyond obstetrics.
Read full abstract