Use of machine learning in the early detection of neonatal complications: a bibliographic review
Sage Sphere Multidisciplinary Studies · 06.07.2026 · 3 (1) · 1-24
DOI: 10.63688/r7kbw843 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sage Sphere Multidisciplinary Studies, online erschienen am 06.07.2026. Verfasst von Patricia Graciela Nieto Gómez und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Introduction
Neonatal complications remain one of the leading causes of infant morbidity and mortality worldwide. In recent years, Machine Learning has emerged as an innovative tool capable of analyzing large volumes of clinical data and contributing to the early detection of diseases in newborns.
Objective
To analyze the available scientific evidence on the use of Machine Learning for the early detection of neonatal complications, identifying the main conditions studied, the most frequently used algorithms, and their predictive performance.
Method
A bibliographic review was conducted using a qualitative approach and a documentary research design. The search was performed in specialized scientific databases, selecting 12 studies published between 2023 and 2026 that addressed Machine Learning applications in neonatology. The collected information was organized and analyzed through data extraction matrices.
Results
Neonatal sepsis was the most frequently investigated complication, followed by respiratory disorders, retinopathy of prematurity, and neonatal mortality. The most commonly used algorithms were Random Forest, XGBoost, Support Vector Machine, and Artificial Neural Networks. The models demonstrated high predictive performance, with AUC values generally above 0.80 and reaching up to 0.98 in some studies.
Conclusion
Machine Learning represents a promising tool for improving the early detection of neonatal complications, supporting clinical decision-making, and optimizing care in neonatal units. However, further multicenter clinical validation studies are required before widespread implementation in routine clinical practice.
Zitieren
APA
Gómez, P. G. N., Villamar, K. M. C., & Paucar, E. K. A. (2026). Use of machine learning in the early detection of neonatal complications: a bibliographic review. Sage Sphere Multidisciplinary Studies, 3(1), 1-24. https://doi.org/10.63688/r7kbw843
Vancouver
Gómez PGN, Villamar KMC, Paucar EKA. Use of machine learning in the early detection of neonatal complications: a bibliographic review. Sage Sphere Multidisciplinary Studies. 2026;3(1):1-24. doi:10.63688/r7kbw843
BibTeX
@article{Gmez2026,
author = {Gómez, Patricia Graciela Nieto and Villamar, Karely Maria Cabrera and Paucar, Evelyn kuskaya Aguachela},
title = {Use of machine learning in the early detection of neonatal complications: a bibliographic review},
journal = {Sage Sphere Multidisciplinary Studies},
year = {2026},
volume = {3},
number = {1},
pages = {1--24},
doi = {10.63688/r7kbw843}
}
EUVIMED