Neo-maternal diagnosis is concerned with recognizing health-related problems in pregnant women and newborn infants at an early stage. The growing availability of analytical tools and clinical data has led to increased use of machine learning methods in studies related to maternal and neonatal care. These methods are mainly used to support disease detection, outcome estimation, and clinical judgment. This review summarizes previous studies that have employed machine learning for neo-maternal diagnosis, focusing on the methods used, the nature of the data, and the results obtained. The paper also discusses the major difficulties, practical limitations, and possible areas for future investigation in the development of dependable and understandable diagnostic systems to improve maternal and neonatal health care.
