Artificial Intelligence for Neonatal and Perinatal Mortality Prevention: A Systematic Review of Machine Learning and Deep Learning Applications

Background/Objectives: Maternal, perinatal, and neonatal mortality remain major global health challenges, causing approximately 2.5 million neonatal deaths annually, particularly in low- and middle-income countries (LMICs). Although Artificial Intelligence (AI), including Machine Learning (ML) and Deep Learning (DL), is increasingly used to support healthcare decision-making, a comprehensive synthesis of its application to prevent prenatal, preterm birth, and neonatal deaths is lacking. This study systematically reviews the current state of research in this field. Methods: A Structured Literature Review (SLR) was conducted following a combined methodological framework integrating Massaro’s protocol and PRISMA 2020 guidelines. Searches were performed in Scopus, IEEE Xplore, and Google Scholar using domain-specific keywords. From 459 identified publications, 46 peer-reviewed studies published between 2018 and 2024 were selected through a four-step filtering and quality assessment process. Bibliometric and thematic analyses were performed. Results: ML techniques accounted for 71.7% of the selected studies, whereas DL approaches represented 28.3%. Neonatal death prediction was the most frequently investigated outcome (34.7% of publications). Most studies originated from Europe (39.1%) and North America (30.4%), while research from Latin America and Sub-Saharan Africa was scarce despite the high mortality burden in these regions. Key barriers included non-standardized clinical records, limited interoperability of health information systems, and the underrepresentation of LMIC populations in training datasets. Conclusions: AI shows significant potential for reducing maternal and neonatal mortality through predictive analytics. However, important geographical and methodological gaps remain. Future research should prioritize inclusive datasets and predictive frameworks adapted to resource-constrained healthcare settings.