Early prediction of bronchopulmonary dysplasia in preterm infants using chest X-rays through a comparative analysis of 13 CNN models across different post-birth days

Bronchopulmonary dysplasia (BPD) in preterm infants is a major concern in neonatal intensive care, necessitating early and accurate detection for improved outcomes. Despite the use of clinical information in previous studies to assess BPD severity, there is a gap in early prediction through imaging techniques. This paper proposed a novel method using convolutional neural networks (CNNs) for the early prediction of BPD from neonatal chest X-rays. We employed two strategies: first, analyzing chest X-ray images taken on specific days post-birth to evaluate day-wise BPD predictive performance using CNN models; and second, aggregating these images to enhance the training dataset. Thirteen specific CNN architectures were evaluated using a five-fold cross-validation method on a dataset acquired at four distinct time points: 3, 7, 14, and 28-days post-birth. The dataset included 115 preterm infants, 51 with BPD and 64 normal, classified based on their condition at 36 weeks of post-menstrual age. MobileNetV2 demonstrated consistent and fairly above-moderate performance among the networks used, with calculated metrics showing an accuracy of 0.665 ± 0.045, an AUC of 0.736 ± 0.053, a recall of 0.635 ± 0.042, a precision of 0.647 ± 0.046, and an F1-score of 0.641 ± 0.042. The results highlight the potential of CNNs in enhancing early diagnostic accuracy for BPD in neonatal patients using chest X-ray images.