Data_Sheet_1.docx

Abstract

Bronchopulmonary dysplasia (BPD) is the most prevalent and clinically significant compli-cation of prematurity. Accurate identification of at-risk infants would enable ongoing intervention to improve outcomes. Although postnatal exposures are known to affect an infant’s likelihood of developing BPD, most existing BPD prediction models do not allow risk to be evaluated at differ-ent time points, and/or are not suitable for use in ethno-diverse populations. A comprehensive ap-proach to developing clinical prediction models avoids assumptions as to which method will yield the optimal results by testing multiple algorithms/models. We compared the performance of ma-chine learning and logistic regression models in predicting BPD/death. Our main cohort included infants <33 weeks’ gestational age (GA) admitted to a Canadian Neonatal Network site from 2016-2018 (n=9,006) with all analyses repeated for the <29 weeks’ GA subcohort (n=4,246). Models were developed to predict, on days 1, 7 and 14 of admission to neonatal intensive care, the compo-site outcome of BPD/death prior to discharge. Ten-fold cross-validation and a 20% hold-out sam-ple were used to measure area under the curve (AUC). Calibration intercepts and slopes were esti-mated by regressing the outcome on the log-odds of the predicted probabilities. The model AUCs ranged from 0.811-0.886. Model discrimination was lower in the <29 weeks’ GA subcohort (AUCs 0.699-0.790). Several machine learning models had a suboptimal calibration intercept and/or slope (k-nearest neighbor, random forest, artificial neural network, stacking neural network ensemble). The top-performing algorithms will be used to develop multinomial models and an online risk estimator for predicting BPD severity and death that does not require information on ethnicity.