115 350

Cited 4 times in

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

Authors
 Jung Ho Han  ;  So Jin Yoon  ;  Hye Sun Lee  ;  Goeun Park  ;  Joohee Lim  ;  Jeong Eun Shin  ;  Ho Seon Eun  ;  Min Soo Park  ;  Soon Min Lee 
Citation
 YONSEI MEDICAL JOURNAL, Vol.63(7) : 640-647, 2022-07 
Journal Title
YONSEI MEDICAL JOURNAL
ISSN
 0513-5796 
Issue Date
2022-07
MeSH
Growth Disorders ; Humans ; Infant ; Infant, Newborn ; Infant, Very Low Birth Weight* ; Machine Learning* ; Prostaglandins F ; Support Vector Machine
Keywords
Growth failure ; machine learning ; neonatal intensive care unit ; prediction ; very low birth weight infants
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.
Files in This Item:
T202205123.pdf Download
DOI
10.3349/ymj.2022.63.7.640
Appears in Collections:
1. College of Medicine (의과대학) > Dept. of Pediatrics (소아과학교실) > 1. Journal Papers
1. College of Medicine (의과대학) > Yonsei Biomedical Research Center (연세의생명연구원) > 1. Journal Papers
Yonsei Authors
Park, Goeun(박고은)
Park, Min Soo(박민수) ORCID logo https://orcid.org/0000-0002-4395-9938
Shin, Jeong Eun(신정은) ORCID logo https://orcid.org/0000-0002-4376-8541
Yoon, So Jin(윤소진) ORCID logo https://orcid.org/0000-0002-7028-7217
Eun, Ho Seon(은호선) ORCID logo https://orcid.org/0000-0001-7212-0341
Lee, Soon Min(이순민) ORCID logo https://orcid.org/0000-0003-0174-1065
Lee, Hye Sun(이혜선) ORCID logo https://orcid.org/0000-0001-6328-6948
Lim, Joo Hee(임주희) ORCID logo https://orcid.org/0000-0003-4376-6607
Han, Jung Ho(한정호) ORCID logo https://orcid.org/0000-0001-6661-8127
URI
https://ir.ymlib.yonsei.ac.kr/handle/22282913/191728
사서에게 알리기
  feedback

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse

Links