Developing adjustable birth weight cutoffs based on maternal height and Apgar scores
Machine Learning: Health · 2025
DOI: 10.1088/3049-477x/adfd63 ↗Kurz gefasst
Fachartikel in der Zeitschrift Machine Learning: Health, 2025. Verfasst von Sumaiya Sultana Dola und 2 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University of Winnipeg.
Abstract (Originalsprache)
Birth weight is crucial for evaluating an infant's health and nutritional status. The World Health Organization (WHO) defines low birth weight (LBW) as being under 2,500 g, considering it a risk condition. However, this standard may not apply universally because it was derived using a European-descendant population. To address this, previous research has recommended using ethnicity-specific birth weight charts, but with globalization and mixed-race families rising, ethnicity-specific birth weight charts may not be reliable. Therefore, alternative measurements to identify at-risk newborns are needed. This study addresses this limitation using Apgar scores to derive LBW cutoffs based on maternal height, an approach that has not been previously explored. To that aim, using the 2022 CDC birth dataset, we implemented a two-stage analytical approach. First, a conditional inference tree and a fuzzy inference model were applied to explore the relationship between maternal height, birth weight, and Apgar scores. In the second stage, we employed an ensemble of five machine learning regressors to estimate birth weight thresholds associated with normal Apgar scores. Our findings suggest that under the fixed WHO LBW standard, the probability of achieving a normal Apgar score decreases as maternal height increases. This finding suggests that some newborns above the standard LBW cutoff may still face health risks. An adjustable LBW threshold based on maternal height is essential for more accurately assessing newborn health and ensuring better outcomes.
Förderung
- University of Winnipeg
Zitieren
APA
Dola, S. S., Nur, M. M. T., & Valderrama, C. E. (2025). Developing adjustable birth weight cutoffs based on maternal height and Apgar scores. Machine Learning: Health. https://doi.org/10.1088/3049-477x/adfd63
Vancouver
Dola SS, Nur MMT, Valderrama CE. Developing adjustable birth weight cutoffs based on maternal height and Apgar scores. Machine Learning: Health. 2025. doi:10.1088/3049-477x/adfd63
BibTeX
@article{Dola2025,
author = {Dola, Sumaiya Sultana and Nur, Mir Md Taosif and Valderrama, Camilo E},
title = {Developing adjustable birth weight cutoffs based on maternal height and Apgar scores},
journal = {Machine Learning: Health},
year = {2025},
doi = {10.1088/3049-477x/adfd63}
}
EUVIMED