Development and validation of a predictive model for early diagnosis of neonatal acute respiratory distress syndrome based on the Montreux definition

• DOI: 10.3389/fped.2023.1276915
• Publication Date: 2023-11-02T12:15:47Z
• Authors: Leilei Shen; Na Cai; Shaoyou Wan; Sheng Chen
• Keywords: prediction model; neonate; acute respiratory distress syndrome; Pediatrics; RJ1-570; 3. Good health; Montreux definition; early diagnosis

Based on the Montreux definition, we aim to develop and validate a predictive model for early diagnosis of neonatal acute respiratory distress syndrome (ARDS). A retrospective analysis clinical data 198 neonates with from January 2018 2022 was conducted. Neonates meeting definition were classified as ARDS group (n = 79), while rest non-ARDS 119). Univariate identified indicators ARDS, followed by logistic regression construct diagnosis. The ability predictors models predict evaluated using area under curve (AUC), performance estimated through bootstrap resampling. Maternal prenatal fever, abnormal fetal heart beat, meconium-stained amniotic fluid (MSAF), white blood cell (WBC), absolute neutrophil count (ANC), percentage (NE%), platelet (PLT), C-reactive protein (CRP), procalcitonin (PCT), creatine kinase (CK), activated partial thromboplastin time (APTT), serum calcium (Ca) sodium (Na)exhibited significant differences between (P < 0.05). MSAF (OR=5.037; 95% CI: 1.523-16.657; P 0.05), ANC (OR 1.324; 1.172-1.495; PLT 0.979; 0.971-0.986; Ca 0.020; 0.004-0.088; 0.05) emerged independent risk factors development ARDS. respective AUC values MSAF, ANC, PLT, Ca, combined prediction 0.606, 0.691, 0.808, 0.761 0.931. Internal validation showed that C-index Early application combining may have good effect