Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Jul;63(7):640-647.
doi: 10.3349/ymj.2022.63.7.640.

Application of Machine Learning Approaches to Predict Postnatal Growth Failure in Very Low Birth Weight Infants

Jung Ho Han  1 , So Jin Yoon  1 , Hye Sun Lee  2 , Goeun Park  2 , Joohee Lim  1 , Jeong Eun Shin  1 , Ho Seon Eun  1 , Min Soo Park  1 , Soon Min Lee  3
Affiliations

Application of Machine Learning Approaches to Predict Postnatal Growth Failure in Very Low Birth Weight Infants

Jung Ho Han et al. Yonsei Med J. 2022 Jul.

Erratum in

Abstract

Purpose: The aims of the study were to develop and evaluate a machine learning model with which to predict postnatal growth failure (PGF) among very low birth weight (VLBW) infants.

Materials and methods: Of 10425 VLBW infants registered in the Korean Neonatal Network between 2013 and 2017, 7954 infants were included. PGF was defined as a decrease in Z score >1.28 at discharge, compared to that at birth. Six metrics [area under the receiver operating characteristic curve (AUROC), accuracy, precision, sensitivity, specificity, and F1 score] were obtained at five time points (at birth, 7 days, 14 days, 28 days after birth, and at discharge). Machine learning models were built using four different techniques [extreme gradient boosting (XGB), random forest, support vector machine, and convolutional neural network] to compare against the conventional multiple logistic regression (MLR) model.

Results: The XGB algorithm showed the best performance with all six metrics across the board. When compared with MLR, XGB showed a significantly higher AUROC (p=0.03) for Day 7, which was the primary performance metric. Using optimal cut-off points, for Day 7, XGB still showed better performances in terms of AUROC (0.74), accuracy (0.68), and F1 score (0.67). AUROC values seemed to increase slightly from birth to 7 days after birth with significance, almost reaching a plateau after 7 days after birth.

Conclusion: We have shown the possibility of predicting PGF through machine learning algorithms, especially XGB. Such models may help neonatologists in the early diagnosis of high-risk infants for PGF for early intervention.

Keywords: Growth failure; machine learning; neonatal intensive care unit; prediction; very low birth weight infants.

PubMed Disclaimer

Conflict of interest statement

The authors have no potential conflicts of interest to disclose.

Figures

Fig. 1
Fig. 1. Schematic flow chart of the enrolled very low birth weight (VLBW) infants.
See this image and copyright information in PMC

References

    1. Horbar JD, Ehrenkranz RA, Badger GJ, Edwards EM, Morrow KA, Soll RF, et al. Weight growth velocity and postnatal growth failure in infants 501 to 1500 grams: 2000-2013. Pediatrics. 2015;136:e84–e92. - PubMed
    1. Lee SM, Kim N, Namgung R, Park M, Park K, Jeon J. Prediction of postnatal growth failure among very low birth weight infants. Sci Rep. 2018;8:3729. - PMC - PubMed
    1. Griffin IJ, Tancredi DJ, Bertino E, Lee HC, Profit J. Postnatal growth failure in very low birthweight infants born between 2005 and 2012. Arch Dis Child Fetal Neonatal Ed. 2016;101:F50–F55. - PubMed
    1. Ziegler EE, Thureen PJ, Carlson SJ. Aggressive nutrition of the very low birthweight infant. Clin Perinatol. 2002;29:225–244. - PubMed
    1. Lima PA, Carvalho Md, Costa AC, Moreira ME. Variables associated with extra uterine growth restriction in very low birth weight infants. J Pediatr (Rio J) 2014;90:22–27. - PubMed