JMIR Publications

ABSTRACT

Background:

Respiratory distress syndrome (RDS) is a disease that commonly affects premature infants whose lungs are not fully developed. It results from a lack of surfactant in the lungs. The more premature the infant, the greater the likelihood of having RDS. However, even though not all premature infants have RDS, preemptive treatment with artificial pulmonary surfactant is administered in most cases.

Objective:

We aimed to develop an artificial intelligence (AI) model to predict RDS in premature infants to avoid unnecessary treatment.

Methods:

This study was conducted for the evaluation of 13,087 very low birth weight infants (VLBWIs) who were newborns weighing less than 1,500g (n=76 hospitals). To predict RDS in VLBWIs, we used basic infant information, maternity history, pregnancy/birth process, family history, resuscitation procedure, and test results at birth such as blood gas analysis and Apgar score. A comparison of the prediction performances from seven different machine learning models was performed, and a 5-layer deep neural network (DNN) was then proposed in order to enhance the prediction performance from the selected features. An ensemble approach combining multiple models from 5-fold cross-validation was subsequently developed.

Results:

Our proposed ensemble 5-layer DNN including the top-20 features provided high sensitivity (83.03%), specificity (87.50%), accuracy (84.07%), balanced accuracy (85.26%), and an area under the curve (0.9187). Based on the model that we developed, a public web application that enables easy access for the prediction of RDS in premature was deployed.

Conclusions:

This AI may find it useful to incorporate the use of this tool in their preparations for neonatal resuscitation, particularly in cases involving the delivery of very low birth weight infants, as it can aid in predicting the likelihood of respiratory distress syndrome and inform decisions regarding the administration of surfactant.