Related Experiment Videos
Artificial Intelligence for Neonatal and Perinatal Mortality Prevention: A Systematic Review of Machine Learning and
Emmanuel Gutiérrez Jiménez1, José Duván Márquez Díaz1
1System Engineering Department, Universidad del Norte, Barranquilla 081007, Colombia.
Healthcare (Basel, Switzerland)
|August 13, 2026
Summary
Artificial Intelligence (AI) shows promise in reducing maternal and neonatal deaths. However, research gaps and underrepresentation of low- and middle-income countries (LMICs) hinder its global application.
Area of Science:
- Medical Informatics
- Public Health
- Artificial Intelligence in Healthcare
Background:
- Maternal, perinatal, and neonatal mortality are critical global health issues, with millions of neonatal deaths annually, especially in LMICs.
- Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) are increasingly used in healthcare, but their specific application to prevent prenatal, preterm birth, and neonatal mortality needs comprehensive review.
Purpose of the Study:
- To systematically review the current research on AI applications for preventing maternal, prenatal, preterm birth, and neonatal mortality.
- To identify trends, methodologies, and geographical distribution of AI research in this domain.
Main Methods:
- A Structured Literature Review (SLR) integrating Massaro's protocol and PRISMA 2020 guidelines.
- Searches conducted in Scopus, IEEE Xplore, and Google Scholar, filtering 459 publications down to 46 peer-reviewed studies (2018-2024).
- Bibliometric and thematic analyses performed on selected studies.
Main Results:
- Machine Learning (ML) dominated (71.7%), followed by Deep Learning (DL) (28.3%).
- Neonatal death prediction was the most common focus (34.7%).
- Research is concentrated in Europe and North America, with scarce studies from high-burden regions like Latin America and Sub-Saharan Africa. Key barriers include data standardization, interoperability, and underrepresentation of LMIC populations.
Conclusions:
- AI, particularly predictive analytics, holds significant potential for reducing maternal and neonatal mortality.
- Geographical and methodological gaps persist, highlighting the need for more inclusive datasets and AI frameworks tailored for resource-constrained settings.