Researchers found bronchopulmonary dysplasia (BPD) was one of the premature birth’s most common and significant consequences. It was critical to make a timely diagnosis by utilizing prediction techniques so that action could be taken quickly to mitigate any negative impacts. The study aimed to use machine learning and the idea that BPD has a developmental genesis to create a tool for predicting whether or not a person would acquire BPD. Preliminary model development made use of datasets including prenatal variables and early postnatal respiratory assistance; subsequent model combinations made use of logistic regression to yield an ensemble model. The simulation of medical situations was carried out. Results from 689 newborns were included. For model building, investigators randomly chose data from 80% of newborns, while data from 20% was used for validation. Receiver operating characteristic curves used to evaluate the final model’s performance yielded values of 0.921 (95% CI: 0.899-0.943) for the training dataset and 0.899 (95% CI]: 0.848-0.949) for the validation dataset. Compared to NIPPV, extubation to CPAP appears to improve BPD-free survival in simulations. Successful extubation may also be defined as the absence of the need for reintubation within 9 days of the initial extubation. Clinical utility of machine learning-based BPD prediction using perinatal characteristics and respiratory data may exist to facilitate early targeted intervention in high-risk infants.