A comprehensive study on machine learning models combining with oversampling for bronchopulmonary dysplasia-associated pulmonary hypertension in very preterm infants.

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.

[Clinical characteristics and pathogens of infancy lower respiratory tract infections in infants with bronchopulmonary dysplasia]. / æ”¯æ°”ç®¡è‚ºå‘è‚²ä¸è‰¯æ‚£å„¿å©´å„¿æœŸä¸‹å‘¼å¸é“æ„ŸæŸ“çš„ä¸´åºŠç‰¹å¾åŠç— åŽŸå­¦åˆ†æž.

OBJECTIVES: To study the clinical characteristics and pathogen features of infants with bronchopulmonary dysplasia (BPD) who were readmitted during infancy due to lower respiratory tract infections. METHODS: A retrospective analysis was conducted on 128 preterm infants with BPD who were admitted for lower respiratory tract infections in Qingdao Women and Children's Hospital from January 2020 to December 2022. An equal number of non-BPD preterm infants admitted during the same period were selected as controls. General information, clinical characteristics, lung function parameters, and respiratory pathogen results were compared between the two groups. RESULTS: Compared with the non-BPD group, the BPD group had a lower gestational age and birth weight, were more likely to experience shortness of breath, wheezing, and cyanosis, and had a longer duration of wheezing relief (P<0.05). Compared with the non-BPD group, the BPD group had lower lung function parameters, including tidal volume per kilogram of body weight, ratio of time to peak tidal expiratory flow to total expiratory time, ratio of volume at peak tidal expiratory flow to expiratory tidal volume, tidal expiratory flow at 25%, 50%, and 75% of tidal volume, and increased respiratory rate (P<0.05). The detection rates of gram-negative bacteria, such as Klebsiella pneumoniae and Acinetobacter baumannii, were higher in the BPD group than in the non-BPD group (P<0.05). CONCLUSIONS: Infants with BPD who develop infancy lower respiratory tract infections require closer attention to the clinical characteristics such as shortness of breath, wheezing, and cyanosis. Lung function is characterized by obstructive changes and small airway dysfunction. Gram-negative bacteria, including Klebsiella pneumoniae and Acinetobacter baumannii, are more likely to be detected as respiratory pathogens.

Flufenamic acid alleviates sepsis-induced lung injury by up-regulating CBR1.

Investigate the effect of flufenamic acid (FFA) on lung injury of sepsis rats. Rat sepsis model was established using cecal ligation and puncture (CLP). The pathomorphology of lung tissue was detected by Hematoxylin-eosin (H&E) staining. The expression levels of tumor necrosis factor alpha (TNF-α), interleukin-6 (IL-6), and high mobility group box-1 (HMGB-1) in serum and TNF-α, IL-6, malondialdehyde (MDA), glutathione (GSH), and superoxide dismutase (SOD) in lung tissues. The viability of RLE-6TN cells was detected by CCK-8 assay. The expression of carbonyl reductase 1 (CBR1) in RLE-6TN cells was analyzed by Western blot analysis and reverse transcription-quantitative polymerase chain reaction (RT-qPCR) analysis. The inflammatory response was obviously enhanced in CLP-constructed sepsis rats and alleviated by FFA treatment. Sepsis induced the increase of W/D ratio, promoted the levels of TNF-α, IL-6, HMGBR1, and MDA and inhibited the levels of SOD and GSH. FFA could effectively alleviate the sepsis-induced lung injury. The viability of RLE-6TN cells induced by LPS was improved with the treatment of FFA. CBR1 expression in LPS-induced RLE-6TN cells was decreased and FFA could up-regulate the CBR1 expression. In addition, LPS-induced lung injury promoted the inflammatory response in lung tissues, increased the W/D ratio and levels of TNF-α, IL-6, HMGBR1, and MDA while inhibited the levels of SOD and GSH. FFA could effectively improve the LPS-induced lung injury while the effect of FFA on LPS-induced lung injury was alleviated by CBR1 interference. FFA may alleviate sepsis-induced lung injury by up-regulating CBR1.