Artificial Intelligence for Neonatal and Perinatal Mortality Prevention: A Systematic Review of Machine Learning and Deep Learning Applications
Abstract
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…
How strong is the evidence?
Evidence Hub reads this as a systematic review, done in computer models (in silico), not in people. Its evidence level is 5 of 5 (Very low · case / narrative / animal / in vitro / in silico). Case reports, narrative reviews, and animal, cell or computer-model studies give the weakest evidence for human health.
Read the paper
Related studies
- Active Learning during Federated Learning for Object Detection
- Fairness-aware federated learning
- Decentralized Federated Learning
- Building a Personally Identifiable Information Recognizer in a Privacy Preserved Manner Using Automated Annotation and Federated Learning
- Preservation of Patient Level Privacy: Federated Classification and Calibration Models
- Efficient explainable federated learning
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.