Development and Validation of a Nomogram for Predicting Bronchopulmonary Dysplasia in Very Preterm Infants ≤32 Weeks

Development and Validation of a Nomogram for Predicting Bronchopulmonary Dysplasia in Very Preterm Infants ≤32 Weeks | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Development and Validation of a Nomogram for Predicting Bronchopulmonary Dysplasia in Very Preterm Infants ≤32 Weeks Cheng Wen, Ju-Shuangzi Feng, Jie-Ling Ma, Zhen Yang, Li-Juan Zhang, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8355766/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 8 You are reading this latest preprint version Abstract Background Bronchopulmonary dysplasia (BPD) remains the most common chronic lung disease in very preterm infants. This study aimed to develop and validate a nomogram for predicting BPD risk using data available by postnatal day 14. Methods This retrospective study analyzed data from 476 very preterm infants admitted to the neonatal intensive care unit (NICU) of the First Affiliated Hospital of Army Medical University in China between January 2015 and June 2025. The participants were randomly divided into a training cohort (n = 333) and a validation cohort (n = 143) at a ratio of 7:3. Based on the 2019 Jensen criteria, infants in the training cohort were categorized as non-BPD (n = 184) or BPD (n = 149), with the BPD group encompassing mild, moderate, and severe cases, as well as those with fatal severe respiratory disease. Least absolute shrinkage and selection operator (LASSO) regression was employed for predictor selection. Model performance was assessed for discrimination using the receiver operating characteristic (ROC) curve, calibration with calibration plots, and clinical utility via decision curve analysis. Results Six predictors were identified in the training cohort: birth weight, number of red blood cell transfusions, number of surfactant doses, fraction of inspired oxygen at postnatal day 14, neonatal respiratory distress syndrome, and duration of invasive ventilation. The nomogram demonstrated adequate discriminatory ability, with an area under the ROC curve of 0.810 (95% CI: 0.764–0.856) in the training cohort and 0.753 (95% CI: 0.671–0.835) in the validation cohort. Calibration curves and decision curve analysis supported the model's accuracy and clinical utility. An online tool was developed to facilitate clinical application ( https://neo-care-predict.shinyapps.io/dynnomapp/ ). Conclusion This nomogram provides an accurate and individualized method for predicting BPD risk in very preterm infants by postnatal day 14, which may facilitate timely clinical interventions. Bronchopulmonary dysplasia Very preterm infant Nomogram Prediction model Risk factors Neonatology Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 Figure 8 1. Introduction Bronchopulmonary dysplasia (BPD) is the most frequent chronic respiratory sequelae in very preterm infants with a gestational age (GA) of ≤ 32 weeks (incidence from 11% to 50%) [ 1 ]. Despite a marked improvement in survival with modern neonatal intensive care unit (NICU) care, the incidence of BPD worldwide remains high. For instance, the incidence of BPD in the United States has increased from 33.4% in 1997 to 43.3% in 2021 [ 2 ]. Similarly, high incidences have also been reported in other countries, with an incidence of 40.7% in China and 52.0% in Japan [ 3 , 4 ]. The pathogenesis of BPD results from prenatal insults like inflammation and infection that predispose infants to barotrauma and oxygen toxicity insults postnatally [ 5 ]. Infants with BPD are at increased risk for extended hospital stays, repeated hospitalizations, and long-term sequelae such as asthma and neurodevelopmental impairments [ 6 – 9 ]. In the absence of therapies to reverse established BPD, management remains supportive and focuses on providing respiratory support and improving nutrition [ 10 ]. Accurate early prediction models are crucial for identifying high-risk infants and enabling timely targeted interventions to improve long-term outcomes. Postnatal day 14 represents a pivotal timepoint for BPD prediction. Prediction models exhibit optimal performance at this time point, with reported area under the curve (AUC) values of 0.89–0.93, outperforming assessments performed at birth or in the immediate postnatal period [ 11 ]. At this point, babies have usually moved on from the stage of acute respiratory distress. As a result, long-term dependence on a ventilator is more likely to be a sign of a chronic, progressive problem with lung development than a short-term problem. Based on this rationale, the 2022 American Academy of Pediatrics (AAP) guideline recommends low-to-moderate dose dexamethasone for ventilator-dependent very preterm infants aged 7–14 days to reduce BPD risk [ 12 ]. Accurate prediction also requires diagnostic criteria aligned with contemporary practice. A revised set of Jensen criteria [ 13 ] that stratifies severity of disease by respiratory support level at 36 weeks' postmenstrual age (PMA) enhances diagnostic consistency and shows stronger association with long-term outcomes [ 14 – 16 ]. Most published prediction models use these outdated criteria (2001) and therefore have high false-positive rates and are of poor clinical value [ 17 , 18 ]. For instance, the calculator on the well-known site, Eunice Kennedy Shriver National Institute of Child Health and Human Development (NICHD) website, is hampered by using data from 2000–2004, not using the Jensen criteria, and failing to consider many advances made since (including widespread use of non-invasive ventilation) [ 11 ]. Therefore, based on the Jensen standard in 2019, we want to develop and verify a new nomogram tool by using the data that can be easily obtained within 14 days after birth, and provide a practical clinical method for accurately predicting the risk of BPD at an early stage. 2. Materials and Methods 2.1 Study Design and Population This retrospective cohort study analyzed data from 476 very preterm infants (GA ≤ 32 weeks) admitted to the NICU of the First Affiliated Hospital of Army Medical University between January 2015 and June 2025. Our method of doing this research was approved by the hospital ethics committee (Approval No. (B) KY2025189), and we strictly adhered to the moral standards stipulated in "Declaration of Helsinki". Inclusion criteria comprised: (1) GA ≤ 32 weeks; (2) admission within 24 hours of birth; and (3) survival beyond 14 days; (4) severe respiratory death. Exclusion criteria included: (1) severe congenital malformations; (2) chromosomal abnormalities or congenital metabolic diseases; (3) readmission following initial discharge (data from the first admission were retained for analysis); (4) automatic discharge or transfer to another facility following treatment withdrawal before 36 weeks' PMA; and (5) incomplete clinical records. Application of these criteria led to the exclusion of 156 cases, resulting in a final study population of 476 infants. The participant screening process is detailed in Fig. 1 . 2.2 Diagnosis of BPD BPD severity was classified according to the Jensen criteria, which stratify infants based on the mode of respiratory support at 36 weeks PMA into three grades: Mild (nasal cannula ≤ 2 L/min), Moderate (noninvasive support or nasal cannula > 2 L/min), and Severe (invasive mechanical ventilation) [ 13 ]. 2.3 Collection of Clinical Data Diagnostic Criteria Diagnostic criteria for neonatal conditions were defined as follows. Neonatal respiratory distress syndrome (NRDS) was diagnosed based on progressive respiratory distress shortly after birth, manifested by tachypnea, grunting, and retractions, in addition to characteristic chest X-ray findings such as ground-glass opacity and air bronchograms [ 19 ]. The number of surfactant doses refers to the total count of separate administrations required for each infant based on the persistence or recurrence of respiratory symptoms. Neonatal sepsis was diagnosed by either a positive blood culture or clinical signs of infection accompanied by abnormalities in at least two inflammatory markers, for example, leukocyte count, C-reactive protein, or procalcitonin [ 20 ]. Abnormal amniotic fluid volume was defined as either polyhydramnios (amniotic fluid volume > 2000 mL) or oligohydramnios (amniotic fluid volume < 500 mL) [ 21 ]. Persistent pulmonary hypertension of the newborn (PPHN) was confirmed via echocardiography demonstrating right-to-left or bidirectional shunting in the absence of structural heart defects, alongside corresponding hypoxemia [ 22 ]. The diagnosis of neonatal pneumonia integrated respiratory symptoms, auscultatory abnormalities, pulmonary infiltrates on imaging, and laboratory evidence of inflammation or pathogenic confirmation [ 22 ]. A hemodynamically significant patent ductus arteriosus (hsPDA) was defined as an echocardiographically confirmed PDA with supporting hemodynamic evidence (e.g., ductal diameter ≥ 1.5 mm, left atrial enlargement) that ultimately required pharmacological treatment [ 23 ]. Data Collection Clinical data were extracted from medical records for two variable categories: very preterm infant characteristics and maternal perinatal factors. Very preterm infant characteristics included the occurrence of BPD, categorized as mild, moderate, severe, or respiratory-related death; GA; birth weight (BW); gender; multiple gestations; 5-minute Apgar score; duration of invasive and non-invasive ventilation within the first 14 days; feeding method; frequency of red blood cell (RBC) transfusions; duration of parenteral nutrition (PN); caffeine administration; surfactant administration (number of doses); definitive bacterial pathogens from sputum culture; and diagnoses of NRDS, neonatal pneumonia, intracranial hemorrhage (ICH), sepsis, PPHN, hsPDA, and pulmonary hemorrhage. The fraction of inspired oxygen (FiO 2 ) at 14 days of life was also recorded. Maternal perinatal data encompassed advanced maternal age pregnancy (≥ 35 years); mode of delivery; gestational diabetes; gestational hypertension; preeclampsia; preterm premature rupture of membranes (PPROM); abnormal amniotic fluid volume; chorioamnionitis; and antenatal corticosteroid. 2.4 Statistical Methods The dataset was randomly split into training and validation cohorts at a 7:3 ratio. Comparative analysis of variables between groups were conducted as follows: continuous variables with significant normality testing were shown as mean ± standard deviation and compared between groups using the independent samples t-test; continuous variables with poor significant normality testing were shown as median (interquartile range) and compared between groups using the Mann-Whitney U test. Categorical variables were shown as count (percentage) and compared between groups using the chi-square test or Fisher’s exact test when appropriate. For modeling purposes, all continuous variables were converted to z-score (mean = 0 and standard deviation = 1) and categorical variables were retained as their original 0/1 encoding. Feature selection was achieved through least absolute shrinkage and selection operator (LASSO) regression with L1 regularization. Specifically, the optimal penalty parameter λ was identified through 10-fold cross-validation. This method not only facilitated modeling by reducing multicollinearity, but also shrank coefficients of irrelevant variables to zero. Because our EPV ratio was 24.8 (149/6) > 10 (typical rule of thumb), model stability in terms of variable selection was not an issue. Additionally, only predictors with confirmed biological significance were retained to ensure the clinical validity of our model. We then retained only these selected predictors in the modeling process and entered them into a multivariable logistic regression model one by one. Finally, our standardized nomogram was constructed based on the coefficients estimated from the multivariable models. Model performance was assessed using the AUC for discrimination, calibration curves to evaluate the agreement between predicted and observed probabilities, and decision curve analysis (DCA) to determine clinical net benefit. Internal validation was performed with 1000 bootstrap resamples. All analyses were conducted separately in the training and validation cohorts. Statistical analyses were carried out using R version 4.3.0, with a two-sided P -value < 0.05 considered statistically significant. 3. Results 3.1 Clinical Characteristics of BPD in Very Preterm Infants The study population included 476 very preterm infants (encompassing both survivors to 36 weeks' PMA and cases of severe respiratory death before this timepoint) who were randomly assigned to training (n = 333) and validation (n = 143) cohorts in a 7:3 ratio (Fig. 1 ). This ratio balances the number of cases needed for model stability and the sample size needed to ensure the reliability of verification. Table 1 shows the baseline demographic and clinical characteristics of the two cohorts. The two cohorts did not differ significantly in the distribution of the severity of BPD ( P = 0.387). The overall incidence of BPD (any grade) was 44.7% in the training cohort and 44.8% in the validation cohort. Most baseline characteristics showed no statistically significant differences ( P > 0.05): GA, BW, gender, multiplicity of gestation, cesarean delivery, 5-minute Apgar score, advanced maternal age pregnancy, and gestational diabetes, suggesting well-balanced cohorts. The incidence rate of preeclampsia was significantly lower in the validation cohort (11.9% versus 19.5%, P = 0.043). In addition, the incidence rate of chorioamnionitis was also significantly lower in the validation cohort (4.2% versus 9.6%, P = 0.046). In the training cohort, very preterm infants were categorized into non-BPD (n = 184) and BPD (n = 149) groups. Compared with the non-BPD group, infants with BPD exhibited significantly lower GA (208 vs. 214 days, P < 0.001) and BW (1180 g vs. 1415 g, P < 0.001). No significant differences were observed in gender distribution, multiplicity of gestation, cesarean delivery, advanced maternal age pregnancy, or gestational diabetes. However, the BPD group showed significantly higher incidences of gestational hypertension (31.5% vs. 19.0%, P = 0.008) and preeclampsia (25.5% vs. 14.7%, P = 0.013), along with lower rates of chorioamnionitis (6.0% vs. 12.5%, P = 0.047) and PPROM (25.5% vs. 39.1%, P = 0.009). Infants with BPD had significantly higher rates of several complications compared to those without BPD, including NRDS (86.6% vs. 58.2%, P < 0.001), hsPDA (21.5% vs. 6.5%, P < 0.001), PPHN (18.1% vs. 4.9%, P < 0.001), ICH (23.5% vs. 7.1%, P < 0.001), pulmonary hemorrhage (12.8% vs. 2.7%, P < 0.001), neonatal pneumonia (83.9% vs. 71.2%, P = 0.006), and definitive bacterial pathogens from sputum culture (20.8% vs. 9.8%, P = 0.005). Regarding therapeutic interventions, infants with BPD received more frequent caffeine citrate administration (75.7% vs. 60.9%, P = 0.004), required higher cumulative surfactant doses and more frequent surfactant administration, received more RBC transfusions (all P < 0.001), needed higher FiO 2 at 14 days of life (25.0% vs. 23.0%, P < 0.001), had longer durations of invasive ventilation (median 5.0 vs. 0.0 days, P < 0.001), and had prolonged PN ( P < 0.001). No significant differences were observed in the duration of noninvasive ventilation or rates of exclusive breastfeeding. Table 1 Patient demographics and baseline characteristics. Training cohort (n = 333) Validation cohort (n = 143) P 1 Non-BPD (n = 184) BPD (n = 149) P 2 BPD_grade, n (%) 0.387 < 0.001 Non 184 (55.3%) 79 (55.2%) 184 (100.0%) 0 (0.0%) Mild 101 (30.3%) 45 (31.5%) 0 (0.0%) 101 (67.8%) Moderate 27 (8.1%) 15 (10.5%) 0 (0.0%) 27 (18.1%) Severe or Dead 21 (6.3%) 4 (2.8%) 0 (0.0%) 21 (14.1%) Gestational age (days) 212 (203, 219) 211 (204, 219) 0.997 214 (208, 219) 208 (199, 216) < 0.001 Birth weight (g) 1,310 (1,090, 1,510) 1,320 (1,150, 1,515) 0.342 1415 (1230, 1598) 1180 (1010, 1350) < 0.001 Male (yes, %) 177 (53.2%) 75 (52.4%) 0.888 94 (51.1%) 83 (55.7%) 0.401 Multiple gestations (yes, %) 102 (30.6%) 34 (23.8%) 0.129 56 (30.4%) 46 (30.9%) 0.931 Cesarean delivery (yes, %) 221 (66.4%) 93 (65.0%) 0.779 114 (62.0%) 107 (71.8%) 0.058 5-min Apgar score 10.00 (9.00, 10.00) 10.00 (9.00, 10.00) 0.183 10.00 (10.00, 10.00) 10.00 (8.00, 10.00) < 0.001 Advanced maternal age pregnancy (yes, %) 74 (22.2%) 36 (25.2%) 0.484 42 (22.8%) 32 (21.5%) 0.768 Gestational diabetes mellitus (yes, %) 82 (24.6%) 32 (22.4%) 0.598 50 (27.2%) 32 (21.5%) 0.230 Gestational hypertension (yes, %) 82 (24.6%) 26 (18.2%) 0.124 35 (19.0%) 47 (31.5%) 0.008 Preeclampsia (yes, %) 65 (19.5%) 17 (11.9%) 0.043 27 (14.7%) 38 (25.5%) 0.013 Amniotic fluid abnormalities (yes, %) 39 (11.7%) 21 (14.7%) 0.370 17 (9.2%) 22 (14.8%) 0.119 Chorioamnionitis (yes, %) 32 (9.6%) 6 (4.2%) 0.046 23 (12.5%) 9 (6.0%) 0.047 Premature rupture of membranes (yes, %) 110 (33.0%) 54 (37.8%) 0.320 72 (39.1%) 38 (25.5%) 0.009 Antenatal dexamethasone (yes, %) 147 (44.1%) 66 (46.2%) 0.686 90 (48.9%) 57 (38.3%) 0.051 NRDS (yes, %) 236 (70.9%) 102 (71.3%) 0.920 107 (58.2%) 129 (86.6%) < 0.001 hsPDA (yes, %) 44 (13.2%) 16 (11.2%) 0.542 12 (6.5%) 32 (21.5%) < 0.001 PPHN (yes, %) 36 (10.8%) 13 (9.1%) 0.571 9 (4.9%) 27 (18.1%) < 0.001 SEPSIS (yes, %) 60 (18.0%) 26 (18.2%) 0.966 28 (15.2%) 32 (21.5%) 0.139 ICH (yes, %) 48 (14.4%) 20 (14.0%) 0.903 13 (7.1%) 35 (23.5%) < 0.001 Pulmonary hemorrhage (yes, %) 24 (7.2%) 9 (6.3%) 0.719 5 (2.7%) 19 (12.8%) < 0.001 Neonatal pneumonia (yes, %) 256 (76.9%) 115 (80.4%) 0.393 131 (71.2%) 125 (83.9%) 0.006 Definitive bacterial pathogens from sputum culture (yes, %) 49 (14.7%) 30 (21.0%) 0.092 18 (9.8%) 31 (20.8%) 0.005 Exclusive breastfeeding (yes, %) 137 (41.1%) 68 (47.6%) 0.195 70 (38.0%) 67 (45.0%) 0.202 Caffeine citrate use (yes, %) 224 (67.5%) 93 (65.5%) 0.675 112 (60.9%) 112 (75.7%) 0.004 Number of surfactant doses 1.00 (0.00, 1.00) 1.00 (0.00, 1.00) 0.603 1.00 (0.00, 1.00) 1.00 (1.00, 1.00) < 0.001 Surfactant dose (mg/kg) 140 (0, 140) 140 (0, 140) 0.558 140 (0, 140) 140 (70, 140) < 0.001 Number of RBC transfusions 1.00 (0.00, 2.00) 1.00 (0.00, 2.00) 0.952 0.00 (0.00, 1.00) 2.00 (0.00, 3.00) < 0.001 FiO₂ at day 14 23.0 (23.0, 30.0) 23.0 (23.0, 26.0) 0.525 23.0 (21.0, 25.0) 25.0 (23.0, 30.0) < 0.001 Invasive ventilation (days) 2.0 (0.0, 7.0) 2.0 (0.0, 5.0) 0.969 0.0 (0.0, 3.0) 5.0 (1.0, 12.0) < 0.001 Noninvasive ventilation (days) 5.0 (3.0, 8.0) 6.0 (3.0, 8.0) 0.798 5.0 (3.0, 8.0) 6.0 (2.0, 9.0) 0.907 Duration of PN (days) 14.00 (14.00, 14.00) 14.00 (14.00, 14.00) 0.325 14.00 (14.00, 14.00) 14.00 (14.00, 14.00) < 0.001 Data are presented as n (%), or median (interquartile range). Exploratory P- values, interpret with caution due to multiple testing: p 1 for comparison between the training cohort and validation cohort, and p 2 for comparison between the Non-BPD group and BPD group in the training cohort. BPD, bronchopulmonary dysplasia; NRDS, neonatal respiratory distress syndrome; hsPDA, hemodynamically significant patent ductus arteriosus; PPHN, persistent pulmonary hypertension of the newborn; ICH, intracranial hemorrhage; PN, parenteral nutrition. 3.2 Predictor Selection Using LASSO Regression All baseline variables presented in Table 1 , which included demographic characteristics, perinatal factors, and complications occurring within the first 14 postnatal days, were included as candidate predictors without preliminary filtering. This approach minimized the risk of omitting potentially significant variables due to clinical preconceptions or arbitrary statistical thresholds. The LASSO regression analysis yielded six predictors with non-zero coefficients (Fig. 2 ): NRDS, number of surfactant doses, number of RBC transfusions, FiO 2 at day 14, duration of invasive ventilation, and BW (Fig. 3 A). Figure 3 B displays the ROC curves and associated AUC values for six sequentially developed models that incorporated the selected predictors. The corresponding AUC values were 0.642, 0.670, 0.720, 0.717, 0.742, and 0.720. 3.3 Construction of the Nomogram Model A multivariate logistic regression model incorporating the six selected predictors was developed and presented as a nomogram (Fig. 4 ). The final regression model is represented by the formula: ln(P/1-P) = − 0.518 + 0.821 × (NRDS) + 0.388 × (number of surfactant doses) + 0.219 × (number of RBC transfusions) + 0.036 × (FiO₂ at day 14) + 0.069 × (invasive ventilation days) − 0.002 × (BW). In this model, a higher total score indicates an increased risk of BPD. A lower BW was negatively associated with BPD risk, while higher values of all other variables were positively associated. To show the application of the nomogram in a clinical practice, we used the data from an infant with NRDS. This infant received two doses of surfactant, had received three transfusions of RBC, had FiO₂ of 30% at day 14, had invasive ventilation for 7 days, and had a BW of 1200 g. Points assigned by the nomogram for these variables were as follows: 25 points for NRDS, 23 points for surfactant doses, 20 points for transfusion of RBC, 11 points for FiO₂, 15 points for invasive ventilation days, and 60 points for BW. The total score of 154 points corresponds to a predicted BPD probability of 78.7%. To facilitate clinical implementation, we developed an interactive web-based calculator ( https://neo-care-predict.shinyapps.io/dynnomapp/ ) that automatically computes individualized BPD risk probabilities for very preterm infants. As shown in Fig. 5 , real-time predictions can be obtained by entering the relevant clinical parameters. Figure 5. Online nomogram for BPD prediction in very preterm infants (≤ 32 weeks) ( https://neo-care-predict.shinyapps.io/dynnomapp/ ). Left panel: input variables; right panel: predicted probability (95% CI). Example variables and probabilities are shown in the table. 3.4 Validation of the Nomogram Model The predictive model demonstrated good discriminative ability, with area under the ROC curve values of 0.810 (95% CI: 0.764–0.856) in the training cohort and 0.753 (95% CI: 0.671–0.835) in the validation cohort (Fig. 6 ). Internal validation using 1000 bootstrap replicates indicated satisfactory calibration in both cohorts, as shown by the reasonable alignment between the calibration curves and the ideal reference line (Fig. 7 A and B ). DCA further showed net clinical benefit across clinically relevant threshold probabilities (0.05–0.8) in both cohorts (Fig. 8 A and B ). Collectively, these validation results support the potential clinical utility of the model. To assess the predictive model's performance in the highest-risk population, we conducted a subgroup analysis of very preterm infants with GA ≤ 28 weeks (n = 54). This subgroup exhibited a high baseline BPD incidence of 72.2% (39/54). The model maintained excellent discriminative ability in this cohort, achieving an AUC of 0.793 (95% CI: 0.658–0.929; Supplementary Fig. 1 ). 4. Discussion In this study, we developed and validated a personalized prediction model for BPD risk in very preterm infants (GA ≤ 32 weeks) based on the 2019 Jensen criteria [ 13 ]. Six predictors were identified through LASSO regression and incorporated into the final multivariable logistic model. These indicators, all available within the first 14 postnatal days: BW, NRDS, number of RBC transfusions, number of surfactant doses, duration of invasive ventilation, and FiO 2 at day 14. This model demonstrated strong performance, with good discrimination (training cohort AUC 0.810, validation cohort AUC 0.753), satisfactory calibration, and clinical utility. We also created an online tool ( https://neo-care-predict.shinyapps.io/dynnomapp/ ) to facilitate early triage by predicting any grade of BPD, thereby identifying infants at highest risk for progressive disease who should be prioritized for severity-based interventions. The final model chose between BW and GA with a winner-takes-all approach. LASSO regression chose BW as the more informative variable; clinical reasoning favors BW over GA: GA reflects the “ideal” time course of lung development, whereas BW gives a net summary of the intrauterine environment experienced by the fetus, which in turn reflects fetal nutrition, placental function, and overall maturity [ 24 ]. Therefore, as compared to GA alone, measures of intrauterine growth such as small for gestational age (SGA) have stronger correlations with the development of BPD [ 24 – 26 ]. Overall, this suggests that BW allows for better discrimination of high-risk infants with an impaired pulmonary developmental potential. Predictors in this model are related to linked components of the BPD pathophysiology continuum [ 1 ]. BW reflects a composite measure of intrauterine growth, potential for lung maturation and nutritional reserves that set the stage for BPD susceptibility [ 27 , 28 ]; thus, it supports Jobe's statement that "immature lung development is the initial event leading to the development of BPD [ 27 ]. NRDS and amount of required pulmonary surfactant (PS) doses reflect the degree of initial injury. NRDS reflects structural immaturity of the lungs through dysfunction of alveolar type II cells and endogenous PS deficiency [ 29 ]. Repeated PS doses reflect both initial injury severity and persistent inflammation that impairs endogenous PS recovery, signaling failed repair and a vicious cycle of lung injury [ 30 ]. When acute lung injury transitions to a persistent state, both the duration of invasive ventilation and the FiO 2 required at day 14 serve as critical dynamic indicators of ongoing damage. Mechanical ventilation induces ventilator-induced (baro)trauma and volutrauma that disrupt alveolar architecture and induce inflammation [ 31 ]; cwhereas hyperoxia induces oxidative stress that exceeds the neonatal antioxidant capacity, leading to oxidative stress, apoptosis, and mitochondrial dysfunction [ 32 ]. These processes contribute to the "second hit" in BPD pathogenesis by impairing alveolar and vascular development. RBC transfusion frequency was an independent predictor of BPD, and this discovery extended BPD pathophysiology beyond the lungs to include systemic factors [ 33 , 34 ].Transfusions may contribute to BPD by circulatory overload, inflammatory reactions to stored blood components, and oxidative stress generated by iron overload [ 35 , 36 ].Therefore, we recommend delaying cord clamping, reducing iatrogenic blood loss, and applying strict transfusion thresholds to prevent transfusion-associated lung injury. Due to its multifactorial pathogenesis, high morbidity, and short window of opportunity for early intervention, accurate prediction models are essential for the clinical management of BPD. Currently, models are heterogeneous with considerable variation in their selected predictors, timing of assessment, and clinical relevance. For example, Leigh et al. developed a machine learning model (2019 Jensen criteria) based on perinatal factors and common patterns of respiratory support through day 14 (AUC 0.899) [ 37 ];Laughon et al. developed a predictor (2001 NICHD standards) based on respiratory support and blood gas parameters within the first 7 days (AUC 0.814) [ 11 ];and Tang et al. developed a nomogram (2018 NICHD standards) with resuscitation methods and SNAPPE-II scores (AUC 0.894) [ 38 ].However, these models exhibit considerable variation in their strategies for selection of variables, predicted time courses, and clinical interpretability. This study introduces several refinements to existing approaches. Firstly, application of the 2019 Jensen criteria [ 13 ] enables more accurate assessment of pulmonary lesion severity and its correlation with long-term outcomes, reducing overdiagnosis. Secondly, we set the prediction timepoint as postnatal day 14, at which point infants usually have passed the acute attack period, and thus the respiratory support situation that persisted more closely reflected the chronic progression of BPD, making the model more clinically relevant. Methodologically, LASSO regression eliminated any subject bias during initial variable selection, and subsequent multivariate logistic regression verified our findings, thus guaranteeing both the reliability of the model and its interpretability. Compared with established prediction tools such as the NICHD calculator [ 11 ], our model using the Jensen criteria shows better accuracy in assessing pulmonary lesion severity. As the model is designed based on recent clinical data, it is highly contemporaneous. Crucially, its predictors capture the transition from acute respiratory failure to a persistent, progressive lung disease. The difference between AUC of internal validation (0.753) and external report may well be due to the difference of study population, data collecting intervals and criteria of BPD diagnosis, and hence external validation is warranted. The advantage of this model lies in its contemporary validation and being a concise and adaptable clinical tool. Subgroup analysis of highest risk infants (GA ≤ 28 weeks) also supported the good prediction ability (AUC = 0.793) of model in this high risk group. Notably, our model's definition of the severe outcome included fatal respiratory cases, capturing the extreme end of the disease spectrum and enhancing its clinical relevance for predicting adverse outcomes. The model and its associated online tool facilitate rapid individual risk quantification, thereby supporting stratified clinical management. Infants with a forecasted risk surpassing 30% should get early intensive measures, which encompass enhanced respiratory support and stringent transfusion standards. Cases classified as very high-risk, characterized by a predicted risk exceeding 50%, necessitate escalation to a proactive multidisciplinary management strategy. This study has several limitations. Although developed in a single-center cohort, the model's generalizability requires validation through future multi-center, prospective studies. Additionally, the reliance on routine clinical data without specific biomarkers may limit predictive accuracy and obscure the underlying biology. Furthermore, while the tool effectively predicts short-term BPD outcomes, its performance for long-term sequelae, including neurodevelopment and hospital readmissions, remains unknown. Future research should integrate multi-omics data and extend follow-up periods to better assess the model's clinical utility. 5. Conclusions In summary, this study validated a nomogram using six clinical parameters available on the 14th postnatal day to predict BPD risk in very preterm infants. The model had good discrimination and calibration. Deployed as an online calculator, it provides a practical tool for the early identification of high-risk infants, enabling timely risk stratification and evidence-based interventions to optimize management and potentially improve long-term respiratory outcomes. Declarations Availability of data and materials The data that support the findings of this study are available from the corresponding author upon reasonable request. Ethics approval and consent to participate This study was approved by the Ethics Committee of the First Affiliated Hospital of Army Medical University (Approval No. (B)KY2025189). Both ethical approval and informed consent were obtained prior to the commencement of the study. All procedures were performed in accordance with the ethical standards outlined in the Declaration of Helsinki and its subsequent amendments. Author contributions Cheng Wen: Conceptualization, Methodology, Software, Formal analysis, Writing - Original Draft, Writing - Review & Editing, Visualization. Ju-Shuangzi Feng: Investigation, Data Curation, Writing - Original Draft, Writing - Review & Editing. Jie-Ling Ma: Investigation, Data Curation,Writing - Review & Editing. Zhen Yang: Conceptualization, Software, Validation, Writing - Review & Editing. Li-Juan Zhang: Resources, Supervision, Writing - Review & Editing. Ling Yan: Conceptualization, Resources, Writing - Original Draft, Writing - Review & Editing, Supervision, Project administration. Funding This research received no external funding. Competing interests The authors confirm the absence of any conflicts of interest. Statement on the Use of Artificial Intelligence The authors hereby declare that no generative artificial intelligence tools were used in the writing or creative development of this manuscript. Publisher’s Statement The views and conclusions presented in this work are those of the authors alone and do not necessarily reflect the positions of their affiliated institutions, or of the publisher, the editorial team, or reviewers. Mention of any commercial products or assertions regarding their performance does not imply endorsement or warranty by the publisher. Consent for publication Not applicable. Clinical trial number Not applicable. References Thébaud B, Goss KN, Laughon M, Whitsett JA, Abman SH, Steinhorn RH, Aschner JL, Davis PG, McGrath-Morrow SA, Soll RF, Jobe AH. Bronchopulmonary dysplasia. NAT REV DIS PRIMERS. 2019;5(1):78. Horbar JD, Greenberg LT, Buzas JS, Ehret DEY, Soll RF, Edwards EM. Trends in mortality and morbidities for infants born 24 to 28 weeks in the us: 1997–2021. Pediatrics. 2024;153(1):e2024066036. Nakashima T, Inoue H, Sakemi Y, Ochiai M, Yamashita H, Ohga S. Trends in bronchopulmonary dysplasia among extremely preterm infants in japan, 2003–2016. J PEDIATR. 2021;230:119–e125117. Zhu Z, He Y, Yuan L, Chen L, Yu Y, Liu L, Sun H, Xu L, Wei Q, Cui S, Lai C, Zhang J, Tan Y, Yu X, Jiang C, Chen C. Trends in bronchopulmonary dysplasia and respiratory support among extremely preterm infants in china over a decade. PEDIATR PULMONOL. 2024;59(2):399–407. Collins JJP, Tibboel D, de Kleer IM, Reiss IKM, Rottier RJ. The future of bronchopulmonary dysplasia: Emerging pathophysiological concepts and potential new avenues of treatment. FRONT MED (LAUSANNE). 2017;4:61. Choi HJ, Lee G, Shin SH, Lee SM, Lee HC, Sohn JA, Lee JA, Kim HS. Development and external validation of a machine learning model to predict bronchopulmonary dysplasia using dynamic factors. SCI REP. 2025;15(1):13620. Doyle LW, Carse E, Adams AM, Ranganathan S, Opie G, Cheong JLY. Ventilation in extremely preterm infants and respiratory function at 8 years. N ENGL J MED. 2017;377(4):329–37. Moreira A, Coleman M, Aziz K, Triviño V, Randolph L, Bierwirth NC, Valadie CT, Arya S, Meunier JA, McOmber B, Winter C, Lee GC, Decker I, Smith AM, Petershack M, Blanco CL, Kwinta P, Ahuja SK. Bronchopulmonary dysplasia in preterm neonates: Th2-eosinophilic inflammation and asthma-like features. PEDIATR RES. 2025. Stoll BJ, Hansen NI, Bell EF, Walsh MC, Carlo WA, Shankaran S, Laptook AR, Sánchez PJ, Van Meurs KP, Wyckoff M, Das A, Hale EC, Ball MB, Newman NS, Schibler K, Poindexter BB, Kennedy KA, Cotten CM, Watterberg KL, D'Angio CT, DeMauro SB, Truog WE, Devaskar U, Higgins RD. Trends in care practices, morbidity, and mortality of extremely preterm neonates, 1993–2012. JAMA. 2015;314(10):1039–51. Tana M, Tirone C, Aurilia C, Lio A, Paladini A, Fattore S, Esposito A, De Tomaso D, Vento G. Respiratory management of the preterm infant: Supporting evidence-based practice at the bedside. Child (BASEL). 2023;10(3). Laughon MM, Langer JC, Bose CL, Smith PB, Ambalavanan N, Kennedy KA, Stoll BJ, Buchter S, Laptook AR, Ehrenkranz RA, Cotten CM, Wilson-Costello DE, Shankaran S, Van Meurs KP, Davis AS, Gantz MG, Finer NN, Yoder BA, Faix RG, Carlo WA, Schibler KR, Newman NS, Rich W, Das A, Higgins RD, Walsh MC. Prediction of bronchopulmonary dysplasia by postnatal age in extremely premature infants. AM J RESPIR CRIT CARE MED. 2011;183(12):1715–22. Cummings JJ, Pramanik AK. Postnatal corticosteroids to prevent or treat chronic lung disease following preterm birth. Pediatrics. 2022;149(6). Jensen EA, Dysart K, Gantz MG, McDonald S, Bamat NA, Keszler M, Kirpalani H, Laughon MM, Poindexter BB, Duncan AF, Yoder BA, Eichenwald EC, DeMauro SB. The diagnosis of bronchopulmonary dysplasia in very preterm infants. An evidence-based approach. AM J RESPIR CRIT CARE MED. 2019;200(6):751–9. Gilfillan M, Bhandari A, Bhandari V. Diagnosis and management of bronchopulmonary dysplasia. BMJ. 2021;375:n1974. Li R, Wang X, Wu Y, Bu Q, Guo J, Liu D, Wang Y, Zhang X, Zhu C, Kang W. Comparative analysis of three bronchopulmonary dysplasia diagnostic criteria in predicting longterm neurodevelopmental outcomes in preterm infants. SCI REP. 2025;15(1):29276. Onland W, Debray TP, Laughon MM, Miedema M, Cools F, Askie LM, Asselin JM, Calvert SA, Courtney SE, Dani C, Durand DJ, Marlow N, Peacock JL, Pillow JJ, Soll RF, Thome UH, Truffert P, Schreiber MD, Van Reempts P, Vendettuoli V, Vento G, van Kaam AH, Moons KG, Offringa M. Clinical prediction models for bronchopulmonary dysplasia: A systematic review and external validation study. BMC Pediatr. 2013;13:207. Sucasas-Alonso A, Pértega-Díaz S, Balboa-Barreiro V, García-Muñoz Rodrigo F, Avila-Alvarez A. Prediction of bronchopulmonary dysplasia in very preterm infants: Competitive risk model nomogram. FRONT PEDIATR. 2024;12:1335891. Yu Z, Wang L, Wang Y, Zhang M, Xu Y, Liu A. Development and validation of a risk scoring tool for bronchopulmonary dysplasia in preterm infants based on a systematic review and meta-analysis. HEALTHCARE (BASEL). 2023;11(5). Sweet DG, Carnielli V, Greisen G, Hallman M, Ozek E, Plavka R, Saugstad OD, Simeoni U, Speer CP, Vento M, Halliday HL. European consensus guidelines on the management of neonatal respiratory distress syndrome in preterm infants–2013 update. NEONATOLOGY. 2013;103(4):353–68. Stoll BJ, Hansen N, Fanaroff AA, Wright LL, Carlo WA, Ehrenkranz RA, Lemons JA, Donovan EF, Stark AR, Tyson JE, Oh W, Bauer CR, Korones SB, Shankaran S, Laptook AR, Stevenson DK, Papile LA, Poole WK. Late-onset sepsis in very low birth weight neonates: The experience of the nichd neonatal research network. Pediatrics. 2002;110(2 Pt 1):285–91. Dubil EA, Magann EF. Amniotic fluid as a vital sign for fetal wellbeing. AUSTRALAS J ULTRASOUND MED. 2013;16(2):62–70. Sankaran D, Lakshminrusimha S. Pulmonary hypertension in the newborn- etiology and pathogenesis. SEMIN FETAL NEONATAL MED. 2022;27(4):101381. Ambalavanan N, Aucott SW, Salavitabar A, Levy VY. Patent ductus arteriosus in preterm infants. Pediatrics. 2025;155(5). Lal MK, Manktelow BN, Draper ES, Field DJ. Chronic lung disease of prematurity and intrauterine growth retardation: A population-based study. Pediatrics. 2003;111(3):483–7. Bose C, Van Marter LJ, Laughon M, O'Shea TM, Allred EN, Karna P, Ehrenkranz RA, Boggess K, Leviton A. Fetal growth restriction and chronic lung disease among infants born before the 28th week of gestation. Pediatrics. 2009;124(3):e450–458. Zhang R, Xu FL, Li WL, Qin FY, Jin XY, Zhang Y, Zhang C, Zhu C. Construction of early risk prediction models for bronchopulmonary dysplasia in preterm infants. ZHONGGUO DANG DAI ER KE ZA ZHI. 2021;23(10):994–1001. Jobe AH, Bancalari E. Bronchopulmonary dysplasia. AM J RESPIR CRIT CARE MED. 2001;163(7):1723–9. Lapcharoensap W, Gage SC, Kan P, Profit J, Shaw GM, Gould JB, Stevenson DK, O'Brodovich H, Lee HC. Hospital variation and risk factors for bronchopulmonary dysplasia in a population-based cohort. JAMA PEDIATR. 2015;169(2):e143676. Hallman M, Herting E. Historical perspective on surfactant therapy: Transforming hyaline membrane disease to respiratory distress syndrome. SEMIN FETAL NEONATAL MED. 2023;28(6):101493. Hascoët JM, Picaud JC, Ligi I, Blanc T, Daoud P, Zupan V, Moreau F, Guilhoto I, Rouabah M, Alexandre C, Saliba E, Storme L, Patkai J, Pomedio M, Hamon I. Review shows that using surfactant a number of times or as a vehicle for budesonide may reduce the risk of bronchopulmonary dysplasia. ACTA PAEDIATR. 2018;107(7):1140–4. Geetha O, Rajadurai VS, Anand AJ, Dela Puerta R, Huey Quek B, Khoo PC, Chua MC, Agarwal P. New bpd-prevalence and risk factors for bronchopulmonary dysplasia/mortality in extremely low gestational age infants ≤ 28 weeks. J PERINATOL. 2021;41(8):1943–50. Perrone S, Santacroce A, Longini M, Proietti F, Bazzini F, Buonocore G. The free radical diseases of prematurity: From cellular mechanisms to bedside. OXID MED CELL LONGEV. 2018;2018:7483062. Bahr TM, Snow GL, Christensen TR, Davenport P, Henry E, Tweddell SM, Ilstrup SJ, Yoder BA, Ohls RK, Sola-Visner MC, Christensen RD. Can red blood cell and platelet transfusions have a pathogenic role in bronchopulmonary dysplasia? J PEDIATR. 2024;265:113836. Ohls RK, Bahr TM, Peterson TG, Christensen RD. A practical guide to reducing/eliminating red blood cell transfusions in the neonatal intensive care unit. SEMIN FETAL NEONATAL MED. 2025;30(1):101545. Keir AK, McPhee AJ, Andersen CC, Stark MJ. Plasma cytokines and markers of endothelial activation increase after packed red blood cell transfusion in the preterm infant. PEDIATR RES. 2013;73(1):75–9. Kitsommart R, Limrungsikul A, Tongsawang N, Thamwiriyakul N, Deesomchok A, Pithakton N, Paes B. Impact of level of neonatal care on phlebotomy and blood transfusion in extremely low birthweight infants: A prospective, multicenter, observational study. FRONT PEDIATR. 2023;11:1238402. Leigh RM, Pham A, Rao SS, Vora FM, Hou G, Kent C, Rodriguez A, Narang A, Tan JBC, Chou FS. Machine learning for prediction of bronchopulmonary dysplasia-free survival among very preterm infants. BMC Pediatr. 2022;22(1):542. Tang L, Wu W, Huang W, Bi G. Predictive modeling of bronchopulmonary dysplasia in premature infants: The impact of new diagnostic standards. FRONT PEDIATR. 2024;12:1434823. Additional Declarations No competing interests reported. Supplementary Files SupplementaryFigure1.jpg Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 21 Jan, 2026 Reviews received at journal 07 Jan, 2026 Reviewers agreed at journal 07 Jan, 2026 Reviewers invited by journal 07 Jan, 2026 Editor invited by journal 17 Dec, 2025 Editor assigned by journal 16 Dec, 2025 Submission checks completed at journal 16 Dec, 2025 First submitted to journal 13 Dec, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8355766","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":571317633,"identity":"c518c9ec-1d58-491f-885e-974fab5d061f","order_by":0,"name":"Cheng Wen","email":"","orcid":"","institution":"First Affiliated Hospital of Army Medical University","correspondingAuthor":false,"prefix":"","firstName":"Cheng","middleName":"","lastName":"Wen","suffix":""},{"id":571317634,"identity":"cabde2fa-10b2-43f5-86ee-81e6f0d38862","order_by":1,"name":"Ju-Shuangzi Feng","email":"","orcid":"","institution":"First Affiliated Hospital of Army Medical University","correspondingAuthor":false,"prefix":"","firstName":"Ju-Shuangzi","middleName":"","lastName":"Feng","suffix":""},{"id":571317635,"identity":"d960fb4d-98cf-4c7c-ab3e-ec581a0c9de9","order_by":2,"name":"Jie-Ling Ma","email":"","orcid":"","institution":"First Affiliated Hospital of Army Medical University","correspondingAuthor":false,"prefix":"","firstName":"Jie-Ling","middleName":"","lastName":"Ma","suffix":""},{"id":571317636,"identity":"6ba843b5-e7ef-4132-928a-0cfa7466a959","order_by":3,"name":"Zhen Yang","email":"","orcid":"","institution":"First Affiliated Hospital of Army Medical University","correspondingAuthor":false,"prefix":"","firstName":"Zhen","middleName":"","lastName":"Yang","suffix":""},{"id":571317637,"identity":"22e1331b-3eeb-46e9-86a2-d961d0fe1165","order_by":4,"name":"Li-Juan Zhang","email":"","orcid":"","institution":"First Affiliated Hospital of Army Medical University","correspondingAuthor":false,"prefix":"","firstName":"Li-Juan","middleName":"","lastName":"Zhang","suffix":""},{"id":571317638,"identity":"801ac1fc-7644-4304-be7e-a0286b418735","order_by":5,"name":"Ling Yan","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAv0lEQVRIiWNgGAWjYPACGyjNRryWNAmStRwmQYvB8bPHJD7uOF+nO+2MAcOHssMM/LMbCGg5k5cmOfPMbQmz2zkGjDPOHWaQuHOAgJYDOWa3edsgWph52w4zGEgkENBy/o3Z7b9t5yBa/hKl5QbQFsa2AxAtjMRokbzxxvxnb1uy5LbbaQUHe86l80jcIKCF73yOscHPNjt+s9vJGx/8KLOW459BQIvCASQOiM2DXz0QyDcQVDIKRsEoGAUjHgAAzWVFv4V6x98AAAAASUVORK5CYII=","orcid":"","institution":"First Affiliated Hospital of Army Medical University","correspondingAuthor":true,"prefix":"","firstName":"Ling","middleName":"","lastName":"Yan","suffix":""}],"badges":[],"createdAt":"2025-12-14 03:53:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8355766/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8355766/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":100361622,"identity":"f9bd508c-bf82-4acb-9697-0676ce2092d7","added_by":"auto","created_at":"2026-01-16 07:45:23","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":478027,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.docx","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/f965c2fc6bce441797979aeb.docx"},{"id":100009878,"identity":"6f82e21c-16d8-4d1e-8a2d-83eee3894040","added_by":"auto","created_at":"2026-01-12 06:03:19","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8036,"visible":true,"origin":"","legend":"","description":"","filename":"70052cec24a944568c2cf1e9450d5ffc.json","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/cb107b62099c339b951d893b.json"},{"id":100009886,"identity":"25f55db8-8e02-4f9d-8f78-ebfc4f45c9d8","added_by":"auto","created_at":"2026-01-12 06:03:19","extension":"zip","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2982650,"visible":true,"origin":"","legend":"","description":"","filename":"attachment.zip","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/e4a429fd2a5dcebac0e12821.zip"},{"id":100009890,"identity":"285ce5d4-83c6-4ade-8c56-949656442b80","added_by":"auto","created_at":"2026-01-12 06:03:19","extension":"xml","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":138826,"visible":true,"origin":"","legend":"","description":"","filename":"70052cec24a944568c2cf1e9450d5ffc1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/466abda45fba1d8c5dc80b44.xml"},{"id":100009892,"identity":"7791dc18-c909-4157-a03a-ea5a33eb823c","added_by":"auto","created_at":"2026-01-12 06:03:19","extension":"eps","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":102706,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage2.eps","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/ef1edd270a7b0fa82edb5d84.eps"},{"id":100361052,"identity":"8b20af24-5e92-4325-bf98-4e7c9c728b74","added_by":"auto","created_at":"2026-01-16 07:44:20","extension":"eps","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":102746,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage3.eps","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/a542cc8345cbe65eac73570d.eps"},{"id":100009894,"identity":"0c88b726-63cb-4a9f-b14a-2cbe0f2e1491","added_by":"auto","created_at":"2026-01-12 06:03:20","extension":"eps","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":98392,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage4.eps","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/8681673f591a1f73b74f76a7.eps"},{"id":100361579,"identity":"ba0ecb88-a77f-478a-8035-ba978d5f8d6b","added_by":"auto","created_at":"2026-01-16 07:45:20","extension":"eps","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":156601,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage5.eps","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/75708e7a38b0b59b3f98f377.eps"},{"id":100360610,"identity":"0def8e82-cd85-480c-bb0b-5601ecda39a7","added_by":"auto","created_at":"2026-01-16 07:39:44","extension":"eps","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2529,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage6.eps","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/264e3dd2e96d2edb0a5aa76f.eps"},{"id":100360965,"identity":"ef74f02e-89cc-4ac3-a775-60cd95f821b7","added_by":"auto","created_at":"2026-01-16 07:44:15","extension":"eps","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":110111,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage7.eps","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/2b59f84b8e481a1e2c09be87.eps"},{"id":100009917,"identity":"097dff8e-9989-48c8-bd78-5757d8d60ac9","added_by":"auto","created_at":"2026-01-12 06:03:21","extension":"eps","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":111693,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage8.eps","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/19281d367b579e66f834c294.eps"},{"id":100009904,"identity":"72db5666-29fc-4cad-8bd5-53a7dda40c54","added_by":"auto","created_at":"2026-01-12 06:03:20","extension":"eps","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2619,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage9.eps","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/21347e65abe2ced335baad45.eps"},{"id":100009906,"identity":"e57b2998-9413-465c-b08f-7df7adb44a53","added_by":"auto","created_at":"2026-01-12 06:03:20","extension":"jpeg","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1074,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/7832689562a34ecccd1c261b.jpeg"},{"id":100009888,"identity":"09b0f789-8ad8-4083-b023-993f7f3a76b5","added_by":"auto","created_at":"2026-01-12 06:03:19","extension":"jpeg","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":327525,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/9f63c15dad160a8cdc0a8444.jpeg"},{"id":100361491,"identity":"ad19c5fe-c194-47c4-97b9-3e5698920b2f","added_by":"auto","created_at":"2026-01-16 07:45:13","extension":"jpeg","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":264556,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/710b2c34b03ac91f04d33760.jpeg"},{"id":100009900,"identity":"31c3bd78-cdb5-48ee-ac6b-99c495723a66","added_by":"auto","created_at":"2026-01-12 06:03:20","extension":"jpeg","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":356364,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/6bff9ec38b0931f3c0fe321e.jpeg"},{"id":100361615,"identity":"f5b207ce-8510-49f6-8a46-a84c5f318304","added_by":"auto","created_at":"2026-01-16 07:45:22","extension":"jpeg","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":100369,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/aff65ff4b470aa67760f50da.jpeg"},{"id":100361785,"identity":"17476034-30c9-4049-80c1-11901757fc2f","added_by":"auto","created_at":"2026-01-16 07:45:43","extension":"jpeg","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":215659,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/9ea717691407dd81743eda4f.jpeg"},{"id":100009919,"identity":"f61ec072-227a-4515-b380-caa11592c071","added_by":"auto","created_at":"2026-01-12 06:03:21","extension":"jpeg","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":283919,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/999de737a322850c0e5eafe5.jpeg"},{"id":100009895,"identity":"ca705dba-1375-4c42-948c-6ca37e1d9d3e","added_by":"auto","created_at":"2026-01-12 06:03:20","extension":"jpeg","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":285520,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage8.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/9b9f8faeabf725704ddb1c1f.jpeg"},{"id":100361713,"identity":"5ae16fe3-0a11-4ae3-92c5-8c3e07cf29e9","added_by":"auto","created_at":"2026-01-16 07:45:34","extension":"jpeg","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":27325,"visible":true,"origin":"","legend":"","description":"","filename":"groupimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/7449e1763cb0e2ece37cf56a.jpeg"},{"id":100009897,"identity":"7735175f-99d1-4fe9-8c8a-343ba9f38c50","added_by":"auto","created_at":"2026-01-12 06:03:20","extension":"png","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":935,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/89839970468fba8b6022b508.png"},{"id":100361576,"identity":"55b9f0f9-7be2-42c7-8319-41a29de1a890","added_by":"auto","created_at":"2026-01-16 07:45:20","extension":"png","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":60040,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/aed0b0bdc614185fe668d691.png"},{"id":100361320,"identity":"3967494c-6f1b-434d-9d03-e734c27afcc3","added_by":"auto","created_at":"2026-01-16 07:44:55","extension":"png","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":52694,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/f7b2d43d9e423cb522e7a3d0.png"},{"id":100009907,"identity":"eeda0cf9-0926-48b3-96df-c0cfc2062c2c","added_by":"auto","created_at":"2026-01-12 06:03:20","extension":"png","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":59812,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/9494434dcb2426c9eec69b8e.png"},{"id":100009914,"identity":"74f32b08-5a63-4f81-96bd-99ff3075c38f","added_by":"auto","created_at":"2026-01-12 06:03:20","extension":"png","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":50817,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/e4cf5b1e85398cb3f56dcf7a.png"},{"id":100009915,"identity":"12b1c8c2-6bb3-4f99-acf0-d022fee62783","added_by":"auto","created_at":"2026-01-12 06:03:20","extension":"png","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":40447,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/dc2c61fc8e1c00a147c6da73.png"},{"id":100009898,"identity":"d1ef387c-e63c-4ec6-9c1e-140ff5b860ce","added_by":"auto","created_at":"2026-01-12 06:03:20","extension":"png","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":55652,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/b672e4b9630c399df7b5fdaf.png"},{"id":100009899,"identity":"fb96bf5d-60a7-4432-a700-26c4e5521f9f","added_by":"auto","created_at":"2026-01-12 06:03:20","extension":"png","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":67108,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/7f87c5e0ba6ea7f53d2b4125.png"},{"id":100009909,"identity":"ffd0475d-5c59-48a9-9765-36cd071d6eb5","added_by":"auto","created_at":"2026-01-12 06:03:20","extension":"png","order_by":30,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":15738,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinegroupimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/807a045c188d375030a259d7.png"},{"id":100360516,"identity":"ef564348-7c7c-4be4-b74e-7f05170e98f7","added_by":"auto","created_at":"2026-01-16 07:39:10","extension":"xml","order_by":31,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":139616,"visible":true,"origin":"","legend":"","description":"","filename":"70052cec24a944568c2cf1e9450d5ffc1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/b250ec1467586de4675d483a.xml"},{"id":100009912,"identity":"9a340185-df88-42c3-8649-4f095e9df1a9","added_by":"auto","created_at":"2026-01-12 06:03:20","extension":"html","order_by":32,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":151946,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/9d45d4fe3a86442f5656ff00.html"},{"id":100361829,"identity":"db330179-1858-492a-9152-c4aead1c6a9a","added_by":"auto","created_at":"2026-01-16 07:45:48","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":34971,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eFlowchart of patient selection.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/debdbb61bede43cd2e2ee4a3.png"},{"id":100009879,"identity":"5c18af7c-4a09-4db8-b9d0-033a7d9ba008","added_by":"auto","created_at":"2026-01-12 06:03:19","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":344535,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eFeatures were selected using LASSO binary logistic regression. (A) Ten-fold cross-validation utilizing the minimum criterion was performed to identify the optimal λ. (B) The trajectory of coefficients for the 6 features is plotted against a range of log(λ) values.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/fc20df6a2d8387de3f400c4d.png"},{"id":100361831,"identity":"f6a0577a-46dd-4eae-a992-c65598204ab5","added_by":"auto","created_at":"2026-01-16 07:45:48","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":251439,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eFeature selection with LASSO regression. (A) Coefficients of the features selected by the LASSO algorithm. A positive coefficient indicates that a higher value of the variable is associated with an increased risk of BPD, whereas the negative coefficient for Birth Weight indicates that a lower value is associated with increased risk. (B) ROC curve evaluating the performance of the prediction model.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/708417989fa9559de2fed60e.png"},{"id":100009885,"identity":"e6a8b5d6-c9b6-4d8c-b6a3-fe962efbe823","added_by":"auto","created_at":"2026-01-12 06:03:19","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":218941,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eNomogram for predicting the development of BPD in very preterm infants.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"4.png","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/a302971510c8a964aaccd1ee.png"},{"id":100009889,"identity":"a125c802-30e6-4eb4-aef7-070901f85390","added_by":"auto","created_at":"2026-01-12 06:03:19","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":321765,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eOnline nomogram for BPD prediction in very preterm infants (≤32 weeks) (https://neo-care-predict.shinyapps.io/dynnomapp/). Left panel: input variables; right panel: predicted probability (95% CI). Example variables and probabilities are shown in the table.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"5.png","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/d83c97f0fbe2e7a2311f2477.png"},{"id":100361751,"identity":"cd5faf55-98c4-416d-9069-8732a4146cca","added_by":"auto","created_at":"2026-01-16 07:45:41","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":149925,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eROC curves for BPD prediction in very preterm infants: training cohort and validation cohort.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"6.png","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/e0b5f697bdd2284114f51c3a.png"},{"id":100360566,"identity":"4b3e5a61-0bd8-434c-8458-b6b981455205","added_by":"auto","created_at":"2026-01-16 07:39:31","extension":"png","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":177458,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eCalibration curves depicting observed versus predicted probabilities of BPD in the training (A) and validation (B) cohorts. The x-axis corresponds to the nomogram-predicted probability, while the y-axis indicates the actual observed frequency.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"7.png","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/da21c930934aabb0f5c6e431.png"},{"id":100009902,"identity":"e95027fd-168a-409d-8751-beed041d4501","added_by":"auto","created_at":"2026-01-12 06:03:20","extension":"png","order_by":8,"title":"Figure 8","display":"","copyAsset":false,"role":"figure","size":177178,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eDCA curves for BPD prediction in very preterm infants: (A) training cohort; (B) validation cohort\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"8.png","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/35aa1489452e4de0bad31dbe.png"},{"id":100406418,"identity":"dd9ad2ef-4a13-4faf-874a-a0805322f205","added_by":"auto","created_at":"2026-01-16 13:01:48","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3011621,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/3963e5d6-e40b-4e4d-901c-0b3d73c9f12e.pdf"},{"id":100009883,"identity":"0332c794-0957-47e8-827b-81e4d1cf45f5","added_by":"auto","created_at":"2026-01-12 06:03:19","extension":"jpg","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":458033,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryFigure1.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8355766/v1/804e1679f24305d87b6d5539.jpg"}],"financialInterests":"No competing interests reported.","formattedTitle":"Development and Validation of a Nomogram for Predicting Bronchopulmonary Dysplasia in Very Preterm Infants ≤32 Weeks","fulltext":[{"header":"1. Introduction","content":"\u003cp\u003eBronchopulmonary dysplasia (BPD) is the most frequent chronic respiratory sequelae in very preterm infants with a gestational age (GA) of \u0026le;\u0026thinsp;32 weeks (incidence from 11% to 50%) [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. Despite a marked improvement in survival with modern neonatal intensive care unit (NICU) care, the incidence of BPD worldwide remains high. For instance, the incidence of BPD in the United States has increased from 33.4% in 1997 to 43.3% in 2021 [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. Similarly, high incidences have also been reported in other countries, with an incidence of 40.7% in China and 52.0% in Japan [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e, \u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]. The pathogenesis of BPD results from prenatal insults like inflammation and infection that predispose infants to barotrauma and oxygen toxicity insults postnatally [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]. Infants with BPD are at increased risk for extended hospital stays, repeated hospitalizations, and long-term sequelae such as asthma and neurodevelopmental impairments [\u003cspan additionalcitationids=\"CR7 CR8\" citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]. In the absence of therapies to reverse established BPD, management remains supportive and focuses on providing respiratory support and improving nutrition [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]. Accurate early prediction models are crucial for identifying high-risk infants and enabling timely targeted interventions to improve long-term outcomes.\u003c/p\u003e \u003cp\u003ePostnatal day 14 represents a pivotal timepoint for BPD prediction. Prediction models exhibit optimal performance at this time point, with reported area under the curve (AUC) values of 0.89\u0026ndash;0.93, outperforming assessments performed at birth or in the immediate postnatal period [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e]. At this point, babies have usually moved on from the stage of acute respiratory distress. As a result, long-term dependence on a ventilator is more likely to be a sign of a chronic, progressive problem with lung development than a short-term problem. Based on this rationale, the 2022 American Academy of Pediatrics (AAP) guideline recommends low-to-moderate dose dexamethasone for ventilator-dependent very preterm infants aged 7\u0026ndash;14 days to reduce BPD risk [\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eAccurate prediction also requires diagnostic criteria aligned with contemporary practice. A revised set of Jensen criteria [\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e] that stratifies severity of disease by respiratory support level at 36 weeks' postmenstrual age (PMA) enhances diagnostic consistency and shows stronger association with long-term outcomes [\u003cspan additionalcitationids=\"CR15\" citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e]. Most published prediction models use these outdated criteria (2001) and therefore have high false-positive rates and are of poor clinical value [\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e, \u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e]. For instance, the calculator on the well-known site, Eunice Kennedy Shriver National Institute of Child Health and Human Development (NICHD) website, is hampered by using data from 2000\u0026ndash;2004, not using the Jensen criteria, and failing to consider many advances made since (including widespread use of non-invasive ventilation) [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eTherefore, based on the Jensen standard in 2019, we want to develop and verify a new nomogram tool by using the data that can be easily obtained within 14 days after birth, and provide a practical clinical method for accurately predicting the risk of BPD at an early stage.\u003c/p\u003e"},{"header":"2. Materials and Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003e2.1 Study Design and Population\u003c/h2\u003e \u003cp\u003eThis retrospective cohort study analyzed data from 476 very preterm infants (GA\u0026thinsp;\u0026le;\u0026thinsp;32 weeks) admitted to the NICU of the First Affiliated Hospital of Army Medical University between January 2015 and June 2025. Our method of doing this research was approved by the hospital ethics committee (Approval No. (B) KY2025189), and we strictly adhered to the moral standards stipulated in \"Declaration of Helsinki\".\u003c/p\u003e \u003cp\u003eInclusion criteria comprised: (1) GA\u0026thinsp;\u0026le;\u0026thinsp;32 weeks; (2) admission within 24 hours of birth; and (3) survival beyond 14 days; (4) severe respiratory death. Exclusion criteria included: (1) severe congenital malformations; (2) chromosomal abnormalities or congenital metabolic diseases; (3) readmission following initial discharge (data from the first admission were retained for analysis); (4) automatic discharge or transfer to another facility following treatment withdrawal before 36 weeks' PMA; and (5) incomplete clinical records. Application of these criteria led to the exclusion of 156 cases, resulting in a final study population of 476 infants. The participant screening process is detailed in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003e2.2 Diagnosis of BPD\u003c/h2\u003e \u003cp\u003eBPD severity was classified according to the Jensen criteria, which stratify infants based on the mode of respiratory support at 36 weeks PMA into three grades: Mild (nasal cannula\u0026thinsp;\u0026le;\u0026thinsp;2 L/min), Moderate (noninvasive support or nasal cannula\u0026thinsp;\u0026gt;\u0026thinsp;2 L/min), and Severe (invasive mechanical ventilation) [\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e].\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003e2.3 Collection of Clinical Data\u003c/h2\u003e \u003cp\u003e \u003cb\u003eDiagnostic Criteria\u003c/b\u003e \u003c/p\u003e \u003cp\u003eDiagnostic criteria for neonatal conditions were defined as follows. Neonatal respiratory distress syndrome (NRDS) was diagnosed based on progressive respiratory distress shortly after birth, manifested by tachypnea, grunting, and retractions, in addition to characteristic chest X-ray findings such as ground-glass opacity and air bronchograms [\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]. The number of surfactant doses refers to the total count of separate administrations required for each infant based on the persistence or recurrence of respiratory symptoms. Neonatal sepsis was diagnosed by either a positive blood culture or clinical signs of infection accompanied by abnormalities in at least two inflammatory markers, for example, leukocyte count, C-reactive protein, or procalcitonin [\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]. Abnormal amniotic fluid volume was defined as either polyhydramnios (amniotic fluid volume\u0026thinsp;\u0026gt;\u0026thinsp;2000 mL) or oligohydramnios (amniotic fluid volume\u0026thinsp;\u0026lt;\u0026thinsp;500 mL) [\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e]. Persistent pulmonary hypertension of the newborn (PPHN) was confirmed via echocardiography demonstrating right-to-left or bidirectional shunting in the absence of structural heart defects, alongside corresponding hypoxemia [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e]. The diagnosis of neonatal pneumonia integrated respiratory symptoms, auscultatory abnormalities, pulmonary infiltrates on imaging, and laboratory evidence of inflammation or pathogenic confirmation [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e]. A hemodynamically significant patent ductus arteriosus (hsPDA) was defined as an echocardiographically confirmed PDA with supporting hemodynamic evidence (e.g., ductal diameter\u0026thinsp;\u0026ge;\u0026thinsp;1.5 mm, left atrial enlargement) that ultimately required pharmacological treatment [\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e].\u003c/p\u003e \u003cp\u003e \u003cb\u003eData Collection\u003c/b\u003e \u003c/p\u003e \u003cp\u003eClinical data were extracted from medical records for two variable categories: very preterm infant characteristics and maternal perinatal factors.\u003c/p\u003e \u003cp\u003eVery preterm infant characteristics included the occurrence of BPD, categorized as mild, moderate, severe, or respiratory-related death; GA; birth weight (BW); gender; multiple gestations; 5-minute Apgar score; duration of invasive and non-invasive ventilation within the first 14 days; feeding method; frequency of red blood cell (RBC) transfusions; duration of parenteral nutrition (PN); caffeine administration; surfactant administration (number of doses); definitive bacterial pathogens from sputum culture; and diagnoses of NRDS, neonatal pneumonia, intracranial hemorrhage (ICH), sepsis, PPHN, hsPDA, and pulmonary hemorrhage. The fraction of inspired oxygen (FiO\u003csub\u003e2\u003c/sub\u003e) at 14 days of life was also recorded.\u003c/p\u003e \u003cp\u003eMaternal perinatal data encompassed advanced maternal age pregnancy (\u0026ge;\u0026thinsp;35 years); mode of delivery; gestational diabetes; gestational hypertension; preeclampsia; preterm premature rupture of membranes (PPROM); abnormal amniotic fluid volume; chorioamnionitis; and antenatal corticosteroid.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003e2.4 Statistical Methods\u003c/h2\u003e \u003cp\u003eThe dataset was randomly split into training and validation cohorts at a 7:3 ratio. Comparative analysis of variables between groups were conducted as follows: continuous variables with significant normality testing were shown as mean\u0026thinsp;\u0026plusmn;\u0026thinsp;standard deviation and compared between groups using the independent samples t-test; continuous variables with poor significant normality testing were shown as median (interquartile range) and compared between groups using the Mann-Whitney U test. Categorical variables were shown as count (percentage) and compared between groups using the chi-square test or Fisher\u0026rsquo;s exact test when appropriate. For modeling purposes, all continuous variables were converted to z-score (mean\u0026thinsp;=\u0026thinsp;0 and standard deviation\u0026thinsp;=\u0026thinsp;1) and categorical variables were retained as their original 0/1 encoding. Feature selection was achieved through least absolute shrinkage and selection operator (LASSO) regression with L1 regularization. Specifically, the optimal penalty parameter λ was identified through 10-fold cross-validation. This method not only facilitated modeling by reducing multicollinearity, but also shrank coefficients of irrelevant variables to zero. Because our EPV ratio was 24.8 (149/6)\u0026thinsp;\u0026gt;\u0026thinsp;10 (typical rule of thumb), model stability in terms of variable selection was not an issue. Additionally, only predictors with confirmed biological significance were retained to ensure the clinical validity of our model. We then retained only these selected predictors in the modeling process and entered them into a multivariable logistic regression model one by one. Finally, our standardized nomogram was constructed based on the coefficients estimated from the multivariable models. Model performance was assessed using the AUC for discrimination, calibration curves to evaluate the agreement between predicted and observed probabilities, and decision curve analysis (DCA) to determine clinical net benefit. Internal validation was performed with 1000 bootstrap resamples. All analyses were conducted separately in the training and validation cohorts. Statistical analyses were carried out using R version 4.3.0, with a two-sided \u003cem\u003eP\u003c/em\u003e-value\u0026thinsp;\u0026lt;\u0026thinsp;0.05 considered statistically significant.\u003c/p\u003e \u003c/div\u003e"},{"header":"3. Results","content":"\u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003e3.1 Clinical Characteristics of BPD in Very Preterm Infants\u003c/h2\u003e \u003cp\u003eThe study population included 476 very preterm infants (encompassing both survivors to 36 weeks' PMA and cases of severe respiratory death before this timepoint) who were randomly assigned to training (n\u0026thinsp;=\u0026thinsp;333) and validation (n\u0026thinsp;=\u0026thinsp;143) cohorts in a 7:3 ratio (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e). This ratio balances the number of cases needed for model stability and the sample size needed to ensure the reliability of verification. Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e shows the baseline demographic and clinical characteristics of the two cohorts. The two cohorts did not differ significantly in the distribution of the severity of BPD (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.387). The overall incidence of BPD (any grade) was 44.7% in the training cohort and 44.8% in the validation cohort. Most baseline characteristics showed no statistically significant differences (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026gt;\u0026thinsp;0.05): GA, BW, gender, multiplicity of gestation, cesarean delivery, 5-minute Apgar score, advanced maternal age pregnancy, and gestational diabetes, suggesting well-balanced cohorts. The incidence rate of preeclampsia was significantly lower in the validation cohort (11.9% versus 19.5%, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.043). In addition, the incidence rate of chorioamnionitis was also significantly lower in the validation cohort (4.2% versus 9.6%, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.046).\u003c/p\u003e \u003cp\u003eIn the training cohort, very preterm infants were categorized into non-BPD (n\u0026thinsp;=\u0026thinsp;184) and BPD (n\u0026thinsp;=\u0026thinsp;149) groups. Compared with the non-BPD group, infants with BPD exhibited significantly lower GA (208 vs. 214 days, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001) and BW (1180 g vs. 1415 g, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001). No significant differences were observed in gender distribution, multiplicity of gestation, cesarean delivery, advanced maternal age pregnancy, or gestational diabetes. However, the BPD group showed significantly higher incidences of gestational hypertension (31.5% vs. 19.0%, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.008) and preeclampsia (25.5% vs. 14.7%, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.013), along with lower rates of chorioamnionitis (6.0% vs. 12.5%, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.047) and PPROM (25.5% vs. 39.1%, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.009).\u003c/p\u003e \u003cp\u003eInfants with BPD had significantly higher rates of several complications compared to those without BPD, including NRDS (86.6% vs. 58.2%, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001), hsPDA (21.5% vs. 6.5%, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001), PPHN (18.1% vs. 4.9%, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001), ICH (23.5% vs. 7.1%, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001), pulmonary hemorrhage (12.8% vs. 2.7%, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001), neonatal pneumonia (83.9% vs. 71.2%, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.006), and definitive bacterial pathogens from sputum culture (20.8% vs. 9.8%, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.005).\u003c/p\u003e \u003cp\u003eRegarding therapeutic interventions, infants with BPD received more frequent caffeine citrate administration (75.7% vs. 60.9%, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.004), required higher cumulative surfactant doses and more frequent surfactant administration, received more RBC transfusions (all \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001), needed higher FiO\u003csub\u003e2\u003c/sub\u003e at 14 days of life (25.0% vs. 23.0%, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001), had longer durations of invasive ventilation (median 5.0 vs. 0.0 days, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001), and had prolonged PN (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001). No significant differences were observed in the duration of noninvasive ventilation or rates of exclusive breastfeeding.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003ePatient demographics and baseline characteristics.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"7\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eTraining cohort\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;333)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eValidation cohort\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;143)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u003csup\u003e\u003cem\u003e1\u003c/em\u003e\u003c/sup\u003e\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eNon-BPD\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;184)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eBPD\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;149)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u003csup\u003e\u003cem\u003e2\u003c/em\u003e\u003c/sup\u003e\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eBPD_grade, n (%)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.387\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNon\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e184 (55.3%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e79 (55.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e184 (100.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0 (0.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMild\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e101 (30.3%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e45 (31.5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0 (0.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e101 (67.8%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eModerate\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e27 (8.1%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e15 (10.5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0 (0.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e27 (18.1%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSevere or Dead\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e21 (6.3%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4 (2.8%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0 (0.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e21 (14.1%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGestational age (days)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e212 (203, 219)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e211 (204, 219)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.997\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e214 (208, 219)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e208 (199, 216)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBirth weight (g)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1,310 (1,090, 1,510)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1,320 (1,150, 1,515)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.342\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e1415 (1230, 1598)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e1180 (1010, 1350)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMale (yes, %)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e177 (53.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e75 (52.4%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.888\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e94 (51.1%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e83 (55.7%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.401\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMultiple gestations (yes, %)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e102 (30.6%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e34 (23.8%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.129\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e56 (30.4%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e46 (30.9%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.931\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCesarean delivery (yes, %)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e221 (66.4%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e93 (65.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.779\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e114 (62.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e107 (71.8%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.058\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e5-min Apgar score\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e10.00 (9.00, 10.00)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e10.00 (9.00, 10.00)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.183\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e10.00 (10.00, 10.00)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e10.00 (8.00, 10.00)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAdvanced maternal age pregnancy (yes, %)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e74 (22.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e36 (25.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.484\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e42 (22.8%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e32 (21.5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.768\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGestational diabetes mellitus (yes, %)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e82 (24.6%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e32 (22.4%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.598\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e50 (27.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e32 (21.5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.230\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGestational hypertension (yes, %)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e82 (24.6%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e26 (18.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.124\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e35 (19.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e47 (31.5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.008\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePreeclampsia (yes, %)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e65 (19.5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e17 (11.9%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.043\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e27 (14.7%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e38 (25.5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.013\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAmniotic fluid abnormalities (yes, %)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e39 (11.7%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e21 (14.7%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.370\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e17 (9.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e22 (14.8%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.119\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eChorioamnionitis (yes, %)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e32 (9.6%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e6 (4.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.046\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e23 (12.5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e9 (6.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.047\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePremature rupture of membranes (yes, %)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e110 (33.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e54 (37.8%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.320\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e72 (39.1%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e38 (25.5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.009\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAntenatal dexamethasone (yes, %)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e147 (44.1%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e66 (46.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.686\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e90 (48.9%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e57 (38.3%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.051\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNRDS (yes, %)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e236 (70.9%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e102 (71.3%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.920\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e107 (58.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e129 (86.6%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ehsPDA (yes, %)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e44 (13.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e16 (11.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.542\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e12 (6.5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e32 (21.5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePPHN (yes, %)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e36 (10.8%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e13 (9.1%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.571\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e9 (4.9%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e27 (18.1%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSEPSIS (yes, %)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e60 (18.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e26 (18.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.966\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e28 (15.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e32 (21.5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.139\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eICH (yes, %)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e48 (14.4%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e20 (14.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.903\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e13 (7.1%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e35 (23.5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePulmonary hemorrhage (yes, %)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e24 (7.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e9 (6.3%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.719\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e5 (2.7%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e19 (12.8%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNeonatal pneumonia (yes, %)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e256 (76.9%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e115 (80.4%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.393\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e131 (71.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e125 (83.9%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.006\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDefinitive bacterial pathogens from sputum culture (yes, %)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e49 (14.7%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e30 (21.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.092\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e18 (9.8%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e31 (20.8%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.005\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eExclusive breastfeeding (yes, %)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e137 (41.1%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e68 (47.6%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.195\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e70 (38.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e67 (45.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.202\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCaffeine citrate use (yes, %)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e224 (67.5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e93 (65.5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.675\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e112 (60.9%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e112 (75.7%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.004\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNumber of surfactant doses\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00 (0.00, 1.00)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00 (0.00, 1.00)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.603\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e1.00 (0.00, 1.00)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e1.00 (1.00, 1.00)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSurfactant dose (mg/kg)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e140 (0, 140)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e140 (0, 140)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.558\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e140 (0, 140)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e140 (70, 140)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNumber of RBC transfusions\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00 (0.00, 2.00)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00 (0.00, 2.00)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.952\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.00 (0.00, 1.00)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e2.00 (0.00, 3.00)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFiO₂ at day 14\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e23.0 (23.0, 30.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e23.0 (23.0, 26.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.525\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e23.0 (21.0, 25.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e25.0 (23.0, 30.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eInvasive ventilation (days)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2.0 (0.0, 7.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2.0 (0.0, 5.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.969\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.0 (0.0, 3.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e5.0 (1.0, 12.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNoninvasive ventilation (days)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e5.0 (3.0, 8.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e6.0 (3.0, 8.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.798\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e5.0 (3.0, 8.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e6.0 (2.0, 9.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.907\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDuration of PN (days)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e14.00 (14.00, 14.00)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e14.00 (14.00, 14.00)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.325\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e14.00 (14.00, 14.00)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e14.00 (14.00, 14.00)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"7\" nameend=\"c7\" namest=\"c1\"\u003e \u003cp\u003eData are presented as n (%), or median (interquartile range).\u003c/p\u003e \u003cp\u003eExploratory \u003cem\u003eP-\u003c/em\u003evalues, interpret with caution due to multiple testing: \u003cem\u003ep\u003c/em\u003e\u003csup\u003e\u003cem\u003e1\u003c/em\u003e\u003c/sup\u003e for comparison between the training cohort and validation cohort, and \u003cem\u003ep\u003c/em\u003e\u003csup\u003e\u003cem\u003e2\u003c/em\u003e\u003c/sup\u003e for comparison between the Non-BPD group and BPD group in the training cohort. BPD, bronchopulmonary dysplasia; NRDS, neonatal respiratory distress syndrome; hsPDA, hemodynamically significant patent ductus arteriosus; PPHN, persistent pulmonary hypertension of the newborn; ICH, intracranial hemorrhage; PN, parenteral nutrition.\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec9\" class=\"Section2\"\u003e \u003ch2\u003e3.2 Predictor Selection Using LASSO Regression\u003c/h2\u003e \u003cp\u003eAll baseline variables presented in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e, which included demographic characteristics, perinatal factors, and complications occurring within the first 14 postnatal days, were included as candidate predictors without preliminary filtering. This approach minimized the risk of omitting potentially significant variables due to clinical preconceptions or arbitrary statistical thresholds. The LASSO regression analysis yielded six predictors with non-zero coefficients (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e): NRDS, number of surfactant doses, number of RBC transfusions, FiO\u003csub\u003e2\u003c/sub\u003e at day 14, duration of invasive ventilation, and BW (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003eA). Figure\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003eB displays the ROC curves and associated AUC values for six sequentially developed models that incorporated the selected predictors. The corresponding AUC values were 0.642, 0.670, 0.720, 0.717, 0.742, and 0.720.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec10\" class=\"Section2\"\u003e \u003ch2\u003e3.3 Construction of the Nomogram Model\u003c/h2\u003e \u003cp\u003eA multivariate logistic regression model incorporating the six selected predictors was developed and presented as a nomogram (Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e). The final regression model is represented by the formula: ln(P/1-P)\u0026thinsp;=\u0026thinsp;\u0026minus;\u0026thinsp;0.518\u0026thinsp;+\u0026thinsp;0.821 \u0026times; (NRDS)\u0026thinsp;+\u0026thinsp;0.388 \u0026times; (number of surfactant doses)\u0026thinsp;+\u0026thinsp;0.219 \u0026times; (number of RBC transfusions)\u0026thinsp;+\u0026thinsp;0.036 \u0026times; (FiO₂ at day 14)\u0026thinsp;+\u0026thinsp;0.069 \u0026times; (invasive ventilation days)\u0026thinsp;\u0026minus;\u0026thinsp;0.002 \u0026times; (BW). In this model, a higher total score indicates an increased risk of BPD. A lower BW was negatively associated with BPD risk, while higher values of all other variables were positively associated.\u003c/p\u003e \u003cp\u003eTo show the application of the nomogram in a clinical practice, we used the data from an infant with NRDS. This infant received two doses of surfactant, had received three transfusions of RBC, had FiO₂ of 30% at day 14, had invasive ventilation for 7 days, and had a BW of 1200 g. Points assigned by the nomogram for these variables were as follows: 25 points for NRDS, 23 points for surfactant doses, 20 points for transfusion of RBC, 11 points for FiO₂, 15 points for invasive ventilation days, and 60 points for BW. The total score of 154 points corresponds to a predicted BPD probability of 78.7%.\u003c/p\u003e \u003cp\u003eTo facilitate clinical implementation, we developed an interactive web-based calculator (\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://neo-care-predict.shinyapps.io/dynnomapp/\u003c/span\u003e\u003cspan address=\"https://neo-care-predict.shinyapps.io/dynnomapp/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003cb\u003e)\u003c/b\u003e that automatically computes individualized BPD risk probabilities for very preterm infants. As shown in \u003cb\u003eFig.\u0026nbsp;5\u003c/b\u003e, real-time predictions can be obtained by entering the relevant clinical parameters.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"No\" id=\"Taba\" border=\"1\"\u003e \u003ccolgroup cols=\"1\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eFigure\u0026nbsp;5. Online nomogram for BPD prediction in very preterm infants (\u0026le;\u0026thinsp;32 weeks) (\u003c/b\u003e\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://neo-care-predict.shinyapps.io/dynnomapp/\u003c/span\u003e\u003cspan address=\"https://neo-care-predict.shinyapps.io/dynnomapp/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003cb\u003e). Left panel: input variables; right panel: predicted probability (95% CI). Example variables and probabilities are shown in the table.\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec11\" class=\"Section2\"\u003e \u003ch2\u003e3.4 Validation of the Nomogram Model\u003c/h2\u003e \u003cp\u003eThe predictive model demonstrated good discriminative ability, with area under the ROC curve values of 0.810 (95% CI: 0.764\u0026ndash;0.856) in the training cohort and 0.753 (95% CI: 0.671\u0026ndash;0.835) in the validation cohort (Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e6\u003c/span\u003e). Internal validation using 1000 bootstrap replicates indicated satisfactory calibration in both cohorts, as shown by the reasonable alignment between the calibration curves and the ideal reference line (Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e7\u003c/span\u003eA \u003cb\u003eand B\u003c/b\u003e). DCA further showed net clinical benefit across clinically relevant threshold probabilities (0.05\u0026ndash;0.8) in both cohorts (Fig.\u0026nbsp;\u003cspan refid=\"Fig7\" class=\"InternalRef\"\u003e8\u003c/span\u003eA \u003cb\u003eand B\u003c/b\u003e). Collectively, these validation results support the potential clinical utility of the model.\u003c/p\u003e \u003cp\u003eTo assess the predictive model's performance in the highest-risk population, we conducted a subgroup analysis of very preterm infants with GA\u0026thinsp;\u0026le;\u0026thinsp;28 weeks (n\u0026thinsp;=\u0026thinsp;54). This subgroup exhibited a high baseline BPD incidence of 72.2% (39/54). The model maintained excellent discriminative ability in this cohort, achieving an AUC of 0.793 (95% CI: 0.658\u0026ndash;0.929; \u003cb\u003eSupplementary Fig.\u0026nbsp;1\u003c/b\u003e).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e"},{"header":"4. Discussion","content":"\u003cp\u003eIn this study, we developed and validated a personalized prediction model for BPD risk in very preterm infants (GA\u0026thinsp;\u0026le;\u0026thinsp;32 weeks) based on the 2019 Jensen criteria [\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e]. Six predictors were identified through LASSO regression and incorporated into the final multivariable logistic model. These indicators, all available within the first 14 postnatal days: BW, NRDS, number of RBC transfusions, number of surfactant doses, duration of invasive ventilation, and FiO\u003csub\u003e2\u003c/sub\u003e at day 14. This model demonstrated strong performance, with good discrimination (training cohort AUC 0.810, validation cohort AUC 0.753), satisfactory calibration, and clinical utility. We also created an online tool (\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://neo-care-predict.shinyapps.io/dynnomapp/\u003c/span\u003e\u003cspan address=\"https://neo-care-predict.shinyapps.io/dynnomapp/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003cb\u003e)\u003c/b\u003e to facilitate early triage by predicting any grade of BPD, thereby identifying infants at highest risk for progressive disease who should be prioritized for severity-based interventions.\u003c/p\u003e \u003cp\u003eThe final model chose between BW and GA with a winner-takes-all approach. LASSO regression chose BW as the more informative variable; clinical reasoning favors BW over GA: GA reflects the \u0026ldquo;ideal\u0026rdquo; time course of lung development, whereas BW gives a net summary of the intrauterine environment experienced by the fetus, which in turn reflects fetal nutrition, placental function, and overall maturity [\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e]. Therefore, as compared to GA alone, measures of intrauterine growth such as small for gestational age (SGA) have stronger correlations with the development of BPD [\u003cspan additionalcitationids=\"CR25\" citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e]. Overall, this suggests that BW allows for better discrimination of high-risk infants with an impaired pulmonary developmental potential.\u003c/p\u003e \u003cp\u003ePredictors in this model are related to linked components of the BPD pathophysiology continuum [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. BW reflects a composite measure of intrauterine growth, potential for lung maturation and nutritional reserves that set the stage for BPD susceptibility [\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e, \u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e]; thus, it supports Jobe's statement that \"immature lung development is the initial event leading to the development of BPD [\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e]. NRDS and amount of required pulmonary surfactant (PS) doses reflect the degree of initial injury. NRDS reflects structural immaturity of the lungs through dysfunction of alveolar type II cells and endogenous PS deficiency [\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e]. Repeated PS doses reflect both initial injury severity and persistent inflammation that impairs endogenous PS recovery, signaling failed repair and a vicious cycle of lung injury [\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eWhen acute lung injury transitions to a persistent state, both the duration of invasive ventilation and the FiO\u003csub\u003e2\u003c/sub\u003e required at day 14 serve as critical dynamic indicators of ongoing damage. Mechanical ventilation induces ventilator-induced (baro)trauma and volutrauma that disrupt alveolar architecture and induce inflammation [\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e]; cwhereas hyperoxia induces oxidative stress that exceeds the neonatal antioxidant capacity, leading to oxidative stress, apoptosis, and mitochondrial dysfunction [\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e]. These processes contribute to the \"second hit\" in BPD pathogenesis by impairing alveolar and vascular development. RBC transfusion frequency was an independent predictor of BPD, and this discovery extended BPD pathophysiology beyond the lungs to include systemic factors [\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e, \u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e].Transfusions may contribute to BPD by circulatory overload, inflammatory reactions to stored blood components, and oxidative stress generated by iron overload [\u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e35\u003c/span\u003e, \u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e].Therefore, we recommend delaying cord clamping, reducing iatrogenic blood loss, and applying strict transfusion thresholds to prevent transfusion-associated lung injury.\u003c/p\u003e \u003cp\u003eDue to its multifactorial pathogenesis, high morbidity, and short window of opportunity for early intervention, accurate prediction models are essential for the clinical management of BPD. Currently, models are heterogeneous with considerable variation in their selected predictors, timing of assessment, and clinical relevance. For example, Leigh et al. developed a machine learning model (2019 Jensen criteria) based on perinatal factors and common patterns of respiratory support through day 14 (AUC 0.899) [\u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e];Laughon et al. developed a predictor (2001 NICHD standards) based on respiratory support and blood gas parameters within the first 7 days (AUC 0.814) [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e];and Tang et al. developed a nomogram (2018 NICHD standards) with resuscitation methods and SNAPPE-II scores (AUC 0.894) [\u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e].However, these models exhibit considerable variation in their strategies for selection of variables, predicted time courses, and clinical interpretability.\u003c/p\u003e \u003cp\u003eThis study introduces several refinements to existing approaches. Firstly, application of the 2019 Jensen criteria [\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e] enables more accurate assessment of pulmonary lesion severity and its correlation with long-term outcomes, reducing overdiagnosis. Secondly, we set the prediction timepoint as postnatal day 14, at which point infants usually have passed the acute attack period, and thus the respiratory support situation that persisted more closely reflected the chronic progression of BPD, making the model more clinically relevant. Methodologically, LASSO regression eliminated any subject bias during initial variable selection, and subsequent multivariate logistic regression verified our findings, thus guaranteeing both the reliability of the model and its interpretability.\u003c/p\u003e \u003cp\u003eCompared with established prediction tools such as the NICHD calculator [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e], our model using the Jensen criteria shows better accuracy in assessing pulmonary lesion severity. As the model is designed based on recent clinical data, it is highly contemporaneous. Crucially, its predictors capture the transition from acute respiratory failure to a persistent, progressive lung disease. The difference between AUC of internal validation (0.753) and external report may well be due to the difference of study population, data collecting intervals and criteria of BPD diagnosis, and hence external validation is warranted. The advantage of this model lies in its contemporary validation and being a concise and adaptable clinical tool. Subgroup analysis of highest risk infants (GA\u0026thinsp;\u0026le;\u0026thinsp;28 weeks) also supported the good prediction ability (AUC\u0026thinsp;=\u0026thinsp;0.793) of model in this high risk group. Notably, our model's definition of the severe outcome included fatal respiratory cases, capturing the extreme end of the disease spectrum and enhancing its clinical relevance for predicting adverse outcomes.\u003c/p\u003e \u003cp\u003eThe model and its associated online tool facilitate rapid individual risk quantification, thereby supporting stratified clinical management. Infants with a forecasted risk surpassing 30% should get early intensive measures, which encompass enhanced respiratory support and stringent transfusion standards. Cases classified as very high-risk, characterized by a predicted risk exceeding 50%, necessitate escalation to a proactive multidisciplinary management strategy.\u003c/p\u003e \u003cp\u003eThis study has several limitations. Although developed in a single-center cohort, the model's generalizability requires validation through future multi-center, prospective studies. Additionally, the reliance on routine clinical data without specific biomarkers may limit predictive accuracy and obscure the underlying biology. Furthermore, while the tool effectively predicts short-term BPD outcomes, its performance for long-term sequelae, including neurodevelopment and hospital readmissions, remains unknown. Future research should integrate multi-omics data and extend follow-up periods to better assess the model's clinical utility.\u003c/p\u003e"},{"header":"5. Conclusions","content":"\u003cp\u003eIn summary, this study validated a nomogram using six clinical parameters available on the 14th postnatal day to predict BPD risk in very preterm infants. The model had good discrimination and calibration. Deployed as an online calculator, it provides a practical tool for the early identification of high-risk infants, enabling timely risk stratification and evidence-based interventions to optimize management and potentially improve long-term respiratory outcomes.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eAvailability of data and materials\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe data that support the findings of this study are available from the corresponding author upon reasonable request.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthics approval and consent to participate\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study was approved by the Ethics Committee of the First Affiliated Hospital of Army Medical University (Approval No. (B)KY2025189). Both ethical approval and informed consent were obtained prior to the commencement of the study. All procedures were performed in accordance with the ethical standards outlined in the Declaration of Helsinki and its subsequent amendments.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthor contributions\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eCheng Wen: Conceptualization, Methodology, Software, Formal analysis, Writing - Original Draft, Writing - Review \u0026amp; Editing, Visualization. Ju-Shuangzi Feng: Investigation, Data Curation, Writing - Original Draft, Writing - Review \u0026amp; Editing. Jie-Ling Ma: Investigation, Data Curation,Writing - Review \u0026amp; Editing. Zhen Yang: Conceptualization, Software, Validation, Writing - Review \u0026amp; Editing. Li-Juan Zhang: Resources, Supervision, Writing - Review \u0026amp; Editing. Ling Yan: Conceptualization, Resources, Writing - Original Draft, Writing - Review \u0026amp; Editing, Supervision, Project administration.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding\u003c/strong\u003e \u0026nbsp;\u003c/p\u003e\n\u003cp\u003eThis research received no external funding.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting interests\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors confirm the absence of any conflicts of interest.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eStatement on the Use of Artificial Intelligence\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors hereby declare that no generative artificial intelligence tools were used in the writing or creative development of this manuscript.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003ePublisher’s Statement\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe views and conclusions presented in this work are those of the authors alone and do not necessarily reflect the positions of their affiliated institutions, or of the publisher, the editorial team, or reviewers. Mention of any commercial products or assertions regarding their performance does not imply endorsement or warranty by the publisher.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for publication\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eClinical trial number\u003c/strong\u003e \u0026nbsp;\u003c/p\u003e\n\u003cp\u003eNot applicable.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eTh\u0026eacute;baud B, Goss KN, Laughon M, Whitsett JA, Abman SH, Steinhorn RH, Aschner JL, Davis PG, McGrath-Morrow SA, Soll RF, Jobe AH. Bronchopulmonary dysplasia. NAT REV DIS PRIMERS. 2019;5(1):78.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHorbar JD, Greenberg LT, Buzas JS, Ehret DEY, Soll RF, Edwards EM. Trends in mortality and morbidities for infants born 24 to 28 weeks in the us: 1997\u0026ndash;2021. Pediatrics. 2024;153(1):e2024066036.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eNakashima T, Inoue H, Sakemi Y, Ochiai M, Yamashita H, Ohga S. Trends in bronchopulmonary dysplasia among extremely preterm infants in japan, 2003\u0026ndash;2016. J PEDIATR. 2021;230:119\u0026ndash;e125117.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhu Z, He Y, Yuan L, Chen L, Yu Y, Liu L, Sun H, Xu L, Wei Q, Cui S, Lai C, Zhang J, Tan Y, Yu X, Jiang C, Chen C. Trends in bronchopulmonary dysplasia and respiratory support among extremely preterm infants in china over a decade. PEDIATR PULMONOL. 2024;59(2):399\u0026ndash;407.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCollins JJP, Tibboel D, de Kleer IM, Reiss IKM, Rottier RJ. The future of bronchopulmonary dysplasia: Emerging pathophysiological concepts and potential new avenues of treatment. FRONT MED (LAUSANNE). 2017;4:61.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChoi HJ, Lee G, Shin SH, Lee SM, Lee HC, Sohn JA, Lee JA, Kim HS. Development and external validation of a machine learning model to predict bronchopulmonary dysplasia using dynamic factors. SCI REP. 2025;15(1):13620.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDoyle LW, Carse E, Adams AM, Ranganathan S, Opie G, Cheong JLY. Ventilation in extremely preterm infants and respiratory function at 8 years. N ENGL J MED. 2017;377(4):329\u0026ndash;37.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMoreira A, Coleman M, Aziz K, Trivi\u0026ntilde;o V, Randolph L, Bierwirth NC, Valadie CT, Arya S, Meunier JA, McOmber B, Winter C, Lee GC, Decker I, Smith AM, Petershack M, Blanco CL, Kwinta P, Ahuja SK. Bronchopulmonary dysplasia in preterm neonates: Th2-eosinophilic inflammation and asthma-like features. PEDIATR RES. 2025.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eStoll BJ, Hansen NI, Bell EF, Walsh MC, Carlo WA, Shankaran S, Laptook AR, S\u0026aacute;nchez PJ, Van Meurs KP, Wyckoff M, Das A, Hale EC, Ball MB, Newman NS, Schibler K, Poindexter BB, Kennedy KA, Cotten CM, Watterberg KL, D'Angio CT, DeMauro SB, Truog WE, Devaskar U, Higgins RD. Trends in care practices, morbidity, and mortality of extremely preterm neonates, 1993\u0026ndash;2012. JAMA. 2015;314(10):1039\u0026ndash;51.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTana M, Tirone C, Aurilia C, Lio A, Paladini A, Fattore S, Esposito A, De Tomaso D, Vento G. Respiratory management of the preterm infant: Supporting evidence-based practice at the bedside. Child (BASEL). 2023;10(3).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLaughon MM, Langer JC, Bose CL, Smith PB, Ambalavanan N, Kennedy KA, Stoll BJ, Buchter S, Laptook AR, Ehrenkranz RA, Cotten CM, Wilson-Costello DE, Shankaran S, Van Meurs KP, Davis AS, Gantz MG, Finer NN, Yoder BA, Faix RG, Carlo WA, Schibler KR, Newman NS, Rich W, Das A, Higgins RD, Walsh MC. Prediction of bronchopulmonary dysplasia by postnatal age in extremely premature infants. AM J RESPIR CRIT CARE MED. 2011;183(12):1715\u0026ndash;22.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCummings JJ, Pramanik AK. Postnatal corticosteroids to prevent or treat chronic lung disease following preterm birth. Pediatrics. 2022;149(6).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJensen EA, Dysart K, Gantz MG, McDonald S, Bamat NA, Keszler M, Kirpalani H, Laughon MM, Poindexter BB, Duncan AF, Yoder BA, Eichenwald EC, DeMauro SB. The diagnosis of bronchopulmonary dysplasia in very preterm infants. An evidence-based approach. AM J RESPIR CRIT CARE MED. 2019;200(6):751\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGilfillan M, Bhandari A, Bhandari V. Diagnosis and management of bronchopulmonary dysplasia. BMJ. 2021;375:n1974.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLi R, Wang X, Wu Y, Bu Q, Guo J, Liu D, Wang Y, Zhang X, Zhu C, Kang W. Comparative analysis of three bronchopulmonary dysplasia diagnostic criteria in predicting longterm neurodevelopmental outcomes in preterm infants. SCI REP. 2025;15(1):29276.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eOnland W, Debray TP, Laughon MM, Miedema M, Cools F, Askie LM, Asselin JM, Calvert SA, Courtney SE, Dani C, Durand DJ, Marlow N, Peacock JL, Pillow JJ, Soll RF, Thome UH, Truffert P, Schreiber MD, Van Reempts P, Vendettuoli V, Vento G, van Kaam AH, Moons KG, Offringa M. Clinical prediction models for bronchopulmonary dysplasia: A systematic review and external validation study. BMC Pediatr. 2013;13:207.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSucasas-Alonso A, P\u0026eacute;rtega-D\u0026iacute;az S, Balboa-Barreiro V, Garc\u0026iacute;a-Mu\u0026ntilde;oz Rodrigo F, Avila-Alvarez A. Prediction of bronchopulmonary dysplasia in very preterm infants: Competitive risk model nomogram. FRONT PEDIATR. 2024;12:1335891.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYu Z, Wang L, Wang Y, Zhang M, Xu Y, Liu A. Development and validation of a risk scoring tool for bronchopulmonary dysplasia in preterm infants based on a systematic review and meta-analysis. HEALTHCARE (BASEL). 2023;11(5).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSweet DG, Carnielli V, Greisen G, Hallman M, Ozek E, Plavka R, Saugstad OD, Simeoni U, Speer CP, Vento M, Halliday HL. European consensus guidelines on the management of neonatal respiratory distress syndrome in preterm infants\u0026ndash;2013 update. NEONATOLOGY. 2013;103(4):353\u0026ndash;68.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eStoll BJ, Hansen N, Fanaroff AA, Wright LL, Carlo WA, Ehrenkranz RA, Lemons JA, Donovan EF, Stark AR, Tyson JE, Oh W, Bauer CR, Korones SB, Shankaran S, Laptook AR, Stevenson DK, Papile LA, Poole WK. Late-onset sepsis in very low birth weight neonates: The experience of the nichd neonatal research network. Pediatrics. 2002;110(2 Pt 1):285\u0026ndash;91.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDubil EA, Magann EF. Amniotic fluid as a vital sign for fetal wellbeing. AUSTRALAS J ULTRASOUND MED. 2013;16(2):62\u0026ndash;70.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSankaran D, Lakshminrusimha S. Pulmonary hypertension in the newborn- etiology and pathogenesis. SEMIN FETAL NEONATAL MED. 2022;27(4):101381.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAmbalavanan N, Aucott SW, Salavitabar A, Levy VY. Patent ductus arteriosus in preterm infants. Pediatrics. 2025;155(5).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLal MK, Manktelow BN, Draper ES, Field DJ. Chronic lung disease of prematurity and intrauterine growth retardation: A population-based study. Pediatrics. 2003;111(3):483\u0026ndash;7.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBose C, Van Marter LJ, Laughon M, O'Shea TM, Allred EN, Karna P, Ehrenkranz RA, Boggess K, Leviton A. Fetal growth restriction and chronic lung disease among infants born before the 28th week of gestation. Pediatrics. 2009;124(3):e450\u0026ndash;458.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhang R, Xu FL, Li WL, Qin FY, Jin XY, Zhang Y, Zhang C, Zhu C. Construction of early risk prediction models for bronchopulmonary dysplasia in preterm infants. ZHONGGUO DANG DAI ER KE ZA ZHI. 2021;23(10):994\u0026ndash;1001.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJobe AH, Bancalari E. Bronchopulmonary dysplasia. AM J RESPIR CRIT CARE MED. 2001;163(7):1723\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLapcharoensap W, Gage SC, Kan P, Profit J, Shaw GM, Gould JB, Stevenson DK, O'Brodovich H, Lee HC. Hospital variation and risk factors for bronchopulmonary dysplasia in a population-based cohort. JAMA PEDIATR. 2015;169(2):e143676.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHallman M, Herting E. Historical perspective on surfactant therapy: Transforming hyaline membrane disease to respiratory distress syndrome. SEMIN FETAL NEONATAL MED. 2023;28(6):101493.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHasco\u0026euml;t JM, Picaud JC, Ligi I, Blanc T, Daoud P, Zupan V, Moreau F, Guilhoto I, Rouabah M, Alexandre C, Saliba E, Storme L, Patkai J, Pomedio M, Hamon I. Review shows that using surfactant a number of times or as a vehicle for budesonide may reduce the risk of bronchopulmonary dysplasia. ACTA PAEDIATR. 2018;107(7):1140\u0026ndash;4.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGeetha O, Rajadurai VS, Anand AJ, Dela Puerta R, Huey Quek B, Khoo PC, Chua MC, Agarwal P. New bpd-prevalence and risk factors for bronchopulmonary dysplasia/mortality in extremely low gestational age infants\u0026thinsp;\u0026le;\u0026thinsp;28 weeks. J PERINATOL. 2021;41(8):1943\u0026ndash;50.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePerrone S, Santacroce A, Longini M, Proietti F, Bazzini F, Buonocore G. The free radical diseases of prematurity: From cellular mechanisms to bedside. OXID MED CELL LONGEV. 2018;2018:7483062.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBahr TM, Snow GL, Christensen TR, Davenport P, Henry E, Tweddell SM, Ilstrup SJ, Yoder BA, Ohls RK, Sola-Visner MC, Christensen RD. Can red blood cell and platelet transfusions have a pathogenic role in bronchopulmonary dysplasia? J PEDIATR. 2024;265:113836.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eOhls RK, Bahr TM, Peterson TG, Christensen RD. A practical guide to reducing/eliminating red blood cell transfusions in the neonatal intensive care unit. SEMIN FETAL NEONATAL MED. 2025;30(1):101545.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKeir AK, McPhee AJ, Andersen CC, Stark MJ. Plasma cytokines and markers of endothelial activation increase after packed red blood cell transfusion in the preterm infant. PEDIATR RES. 2013;73(1):75\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKitsommart R, Limrungsikul A, Tongsawang N, Thamwiriyakul N, Deesomchok A, Pithakton N, Paes B. Impact of level of neonatal care on phlebotomy and blood transfusion in extremely low birthweight infants: A prospective, multicenter, observational study. FRONT PEDIATR. 2023;11:1238402.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLeigh RM, Pham A, Rao SS, Vora FM, Hou G, Kent C, Rodriguez A, Narang A, Tan JBC, Chou FS. Machine learning for prediction of bronchopulmonary dysplasia-free survival among very preterm infants. BMC Pediatr. 2022;22(1):542.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTang L, Wu W, Huang W, Bi G. Predictive modeling of bronchopulmonary dysplasia in premature infants: The impact of new diagnostic standards. FRONT PEDIATR. 2024;12:1434823.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"bmc-pulmonary-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"pulm","sideBox":"Learn more about [BMC Pulmonary Medicine](http://bmcpulmmed.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/pulm/default.aspx","title":"BMC Pulmonary Medicine","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Bronchopulmonary dysplasia, Very preterm infant, Nomogram, Prediction model, Risk factors, Neonatology","lastPublishedDoi":"10.21203/rs.3.rs-8355766/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8355766/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003eBronchopulmonary dysplasia (BPD) remains the most common chronic lung disease in very preterm infants. This study aimed to develop and validate a nomogram for predicting BPD risk using data available by postnatal day 14.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003e This retrospective study analyzed data from 476 very preterm infants admitted to the neonatal intensive care unit (NICU) of the First Affiliated Hospital of Army Medical University in China between January 2015 and June 2025. The participants were randomly divided into a training cohort (n\u0026thinsp;=\u0026thinsp;333) and a validation cohort (n\u0026thinsp;=\u0026thinsp;143) at a ratio of 7:3. Based on the 2019 Jensen criteria, infants in the training cohort were categorized as non-BPD (n\u0026thinsp;=\u0026thinsp;184) or BPD (n\u0026thinsp;=\u0026thinsp;149), with the BPD group encompassing mild, moderate, and severe cases, as well as those with fatal severe respiratory disease. Least absolute shrinkage and selection operator (LASSO) regression was employed for predictor selection. Model performance was assessed for discrimination using the receiver operating characteristic (ROC) curve, calibration with calibration plots, and clinical utility via decision curve analysis.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eSix predictors were identified in the training cohort: birth weight, number of red blood cell transfusions, number of surfactant doses, fraction of inspired oxygen at postnatal day 14, neonatal respiratory distress syndrome, and duration of invasive ventilation. The nomogram demonstrated adequate discriminatory ability, with an area under the ROC curve of 0.810 (95% CI: 0.764\u0026ndash;0.856) in the training cohort and 0.753 (95% CI: 0.671\u0026ndash;0.835) in the validation cohort. Calibration curves and decision curve analysis supported the model's accuracy and clinical utility. An online tool was developed to facilitate clinical application (\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://neo-care-predict.shinyapps.io/dynnomapp/\u003c/span\u003e\u003cspan address=\"https://neo-care-predict.shinyapps.io/dynnomapp/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003cb\u003e).\u003c/b\u003e\u003c/p\u003e\u003ch2\u003eConclusion\u003c/h2\u003e \u003cp\u003eThis nomogram provides an accurate and individualized method for predicting BPD risk in very preterm infants by postnatal day 14, which may facilitate timely clinical interventions.\u003c/p\u003e","manuscriptTitle":"Development and Validation of a Nomogram for Predicting Bronchopulmonary Dysplasia in Very Preterm Infants ≤32 Weeks","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-12 06:03:14","doi":"10.21203/rs.3.rs-8355766/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"87424524274209358246577762296825326956","date":"2026-01-21T13:14:50+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-07T22:27:27+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"223503842041526686368125529393498008233","date":"2026-01-07T07:44:03+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-01-07T07:21:15+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-12-17T12:27:00+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-12-17T03:07:43+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-12-17T03:06:51+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Pulmonary Medicine","date":"2025-12-14T03:35:00+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-pulmonary-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"pulm","sideBox":"Learn more about [BMC Pulmonary Medicine](http://bmcpulmmed.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/pulm/default.aspx","title":"BMC Pulmonary Medicine","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"f71c0995-371d-4849-918a-254bb418f4a3","owner":[],"postedDate":"January 12th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-01-12T06:03:15+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-12 06:03:14","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8355766","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8355766","identity":"rs-8355766","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}