Search

Abstract Background Bronchopulmonary dysplasia-associated pulmonary hypertension (BPD-PH) remains a devastating clinical complication seriously affecting the therapeutic outcome of preterm infants. Hence, early prevention and timely diagnosis prior to pathological change is the key to reducing morbidity and improving prognosis. Our primary objective is to utilize machine learning techniques to build predictive models that could accurately identify BPD infants at risk of developing PH. Methods The data utilized in this study were collected from neonatology departments of four tertiary-level hospitals in China. To address the issue of imbalanced data, oversampling algorithms synthetic minority over-sampling technique (SMOTE) was applied to improve the model. Results Seven hundred sixty one clinical records were collected in our study. Following data pre-processing and feature selection, 5 of the 46 features were used to build models, including duration of invasive respiratory support (day), the severity of BPD, ventilator-associated pneumonia, pulmonary hemorrhage, and early-onset PH. Four machine learning models were applied to predictive learning, and after comprehensive selection a model was ultimately selected. The model achieved 93.8% sensitivity, 85.0% accuracy, and 0.933 AUC. A score of the logistic regression formula greater than 0 was identified as a warning sign of BPD-PH. Conclusions We comprehensively compared different machine learning models and ultimately obtained a good prognosis model which was sufficient to support pediatric clinicians to make early diagnosis and formulate a better treatment plan for pediatric patients with BPD-PH.

Abstract Background This article summarizes the treatment experience for congenital complete atrioventricular block (CCAVB) in newborns and infants, and discusses the necessity and feasibility of treating CCAVB with permanent pacemaker implantation in this population. Methods In this study, the clinical data and follow-up results of nine children admitted at our center with CCAVB from January 2005 to March 2023 were retrospectively analyzed. Among them, two children received early implantation of permanent pacemakers (within 1 year of age), two children received non-early implantation (1 year or older), and the remaining five children received no pacemaker implantation. CCAVB diagnosis was confirmed by clinical symptoms and clinical examinations, including electrocardiography and echocardiography before surgery. After surgery, the pacing and sensing functions of the pacemaker were observed using electrocardiography, echocardiography, and pacing threshold monitoring. A comprehensive assessment of the treatment efficacy was conducted, encompassing improvements in clinical symptoms, growth and development, as well as the absence of any additional potential complications. The children who did not receive pacemaker implantation were followed up. Results Among the four children who successfully received pacemaker implantation, one child who received non-early implantation died. For the remaining three children, the threshold level, amplitude, impedance, and minute ventilation sensor function of the pacemaker were good during the follow-up period, with a heart rate at the pacing rate. The growth and development of the aforementioned patients who received pacemaker implantation demonstrated adherence to the percentile curve, and their motor and cognitive development remained unaffected. However, among the children who did not undergo pacemaker implantation, two experienced death, while three were lost to follow-up, thereby limiting the evaluation of their long-term outcomes. Conclusions Early implantation of an epicardial pacemaker at an early stage in newborns and infants diagnosed with CCAVB can significantly improve clinical symptoms without affecting their growth and development. These data are in line with current literature and suggest that early implantation of an epicardial pacemaker in newborns and infants diagnosed with CCAVB but further studies are needed.