Machine learning-based risk factor analysis of necrotizing enterocolitis in very low birth weight infantsopen access
- Authors
- Cho, Hannah; Lee, Eun Hee; Lee, Kwang-Sig; Heo, Ju Sun
- Issue Date
- Dec-2022
- Publisher
- Nature Publishing Group
- Citation
- Scientific Reports, v.12, no.1
- Indexed
- SCIE
SCOPUS
- Journal Title
- Scientific Reports
- Volume
- 12
- Number
- 1
- URI
- https://scholarworks.korea.ac.kr/kumedicine/handle/2021.sw.kumedicine/62321
- DOI
- 10.1038/s41598-022-25746-6
- ISSN
- 2045-2322
- Abstract
- This study used machine learning and a national prospective cohort registry database to analyze the major risk factors of necrotizing enterocolitis (NEC) in very low birth weight (VLBW) infants, including environmental factors. The data consisted of 10,353 VLBW infants from the Korean Neonatal Network database from January 2013 to December 2017. The dependent variable was NEC. Seventy-four predictors, including ambient temperature and particulate matter, were included. An artificial neural network, decision tree, logistic regression, naive Bayes, random forest, and support vector machine were used to evaluate the major predictors of NEC. Among the six prediction models, logistic regression and random forest had the best performance (accuracy: 0.93 and 0.93, area under the receiver-operating-characteristic curve: 0.73 and 0.72, respectively). According to random forest variable importance, major predictors of NEC were birth weight, birth weight Z-score, maternal age, gestational age, average birth year temperature, birth year, minimum birth year temperature, maximum birth year temperature, sepsis, and male sex. To the best of our knowledge, the performance of random forest in this study was among the highest in this line of research. NEC is strongly associated with ambient birth year temperature, as well as maternal and neonatal predictors.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - 4. Research institute > Institute of Human Behavior and Genetics > 1. Journal Articles
- 2. Clinical Science > Department of Pediatrics > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.