AUTHOR=Lei Jintao , Sun Tiankai , Jiang Yongjiang , Wu Ping , Fu Jinjian , Zhang Tao , McGrath Eric 

TITLE=Risk Identification of Bronchopulmonary Dysplasia in Premature Infants Based on Machine Learning

JOURNAL=Frontiers in Pediatrics

VOLUME=Volume 9 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/pediatrics/articles/10.3389/fped.2021.719352

DOI=10.3389/fped.2021.719352

ISSN=2296-2360

ABSTRACT=Bronchopulmonary dysplasia (BPD) is one of the most common complications of premature infants. This disease takes a long time for supplementary oxygen, which seriously affects the lung function of the child and brings a heavy burden to the family and society. This research aims to adopt the method of ensemble learning in machine learning, combining the Boruta algorithm and the Random Forest algorithm to determine the predictors of premature infants with BPD and establish a predictive model to help clinicians to conduct the optimal treatment plan.

Data collected from clinical records of 996 premature infants treated in the neonatology department of Liuzhou Maternal and Child Health Hospital in Western China. In this study, premature infants with congenital anomaly, death and premature infants with incomplete data before the diagnosis of BPD were excluded from the data set. After exclusion, we included 980 premature infants in the study.Boruta and tenfold cross validation were used for feature selection in this study. Six variables were finally selected from the 27 variables and the random forest model was established. The AUC of the model was as high as 0.939 with excellent predictive performance.The use of machine learning methods can help clinicians predict the disease so as to formulate the best treatment plan.