Construction and Application of Early Stratification Dynamic Prediction Model for Bronchopulmonary Dysplasia in Extremely Premature / Very Low Birth Weight Infants

Construction and Application of Early Stratification Dynamic Prediction Model for Bronchopulmonary Dysplasia in Extremely Premature / Very Low Birth Weight Infants | 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 Article Construction and Application of Early Stratification Dynamic Prediction Model for Bronchopulmonary Dysplasia in Extremely Premature / Very Low Birth Weight Infants Ning An, Jingwen Yang, Rong Zhang, Wen Han, Xuchen Zhou, Rong Yang, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4648257/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Objective To investigate the independent risk factors for Bronchopulmonary Dysplasia (BPD) at different time points within the first week in extremely premature/very low birth weight infants and to construct an early stratification dynamic prediction model for BPD through machine learning, aiming to achieve dynamic prediction of BPD for the early identification of high-risk groups and preemptive prevention. Methods A retrospective collection of clinical data was conducted on premature infants admitted to the Neonatology Department of the First Affiliated Hospital of Xinjiang Medical University from January 2017 to December 2022, with gestational age (GA) < 32 weeks or birth weight (BW) < 1500g. Eligible subjects were randomly divided into training and validation sets in a 7:3 ratio for model building and internal validation. Prospective clinical data from preterm infants admitted to six neonatal rescue centers in various districts of Xinjiang from January to October 2023 were independently collected to validate the practical application value of each model. Clinical parameters were collected, and study participants were divided into three groups: no BPD, mild BPD, and moderate to severe BPD (msBPD). Machine learning predictive models for BPD stratification employing logistic regression (LR), random forest (RF), XGBoost (XGB), and gradient boosting decision tree (GBDT) were constructed for postnatal days 1, 3, and 7. Comprehensive evaluation was performed to select the optimal model at each time point and proceed to external validation. Results The study retrospectively gathered data from 554 preterm infants (286 no BPD, 212 mild, and 56 msBPD cases). Prospectively, 387 preterm infants (208 no BPD, 138 mild, and 41 msBPD cases). On ordinal logistic regression, GA, BW, prenatal steroids, interruption of umbilical blood flow, severe preeclampsia, FIO2, CRP, RBC, systemic inflammatory response index (SIRI), prognostic nutritional index, platelet mass index, alveolar-arterial oxygen difference, and oxygenation index were independent risk factors for BPD severity at different times after birth. After comprehensive evaluation, the LR and XGB models were identified as better BPD stratification prediction models for postnatal days 1, 3, and 7 (AUC = 0.810,0.837 and 0.813 respectively). Conclusion Early stratification dynamic prediction machine learning models for BPD have been constructed for postnatal days 1, 3, and 7 in extremely premature/very low birth weight infants. These may serve as effective tools for the screening of high-risk BPD populations. Health sciences/Medical research Health sciences/Risk factors Bronchopulmonary Dysplasia Machine Learning Dynamic Prediction Preterm Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Introduction Bronchopulmonary Dysplasia (BPD) in infants is defined by the need for supplemental oxygen or respiratory support at 36 weeks postmenstrual age (PMA) [ 1 ] . BPD is not only the most common complication among preterm infants but also a significant risk factor for other complications and various chronic non-communicable diseases [ 2 ] . The advancements in perinatal care have significantly improved the survival rates of very preterm infants (VLBW) and extremely preterm infants (ELBW). Consequently, the incidence of most complications has declined except for BPD, which continues to rise globally [ 3 , 4 ] . BPD is the most prevalent chronic lung disease in preterm infants and a critical factor affecting their quality of life. The etiopathogenesis of BPD involves multiple factors before, during, and after birth [ 5 , 6 ] , although the exact mechanisms remain unknown. Symptomatic and supportive treatments may delay the onset and progression of BPD, but there is no specific treatment once BPD develops, making prevention the primary clinical approach. The diagnostic criteria for BPD are typically met at 28 days postnatally, at which point pulmonary damage is often irreversible, missing the optimal intervention window and increasing the risk of BPD-related complications [ 7 ] . Therefore, early prevention is crucial, and the early prediction of BPD remains a significant challenge. Identifying BPD risk factors and establishing predictive models to accurately forecast the onset of BPD can provide clinical “windows of opportunity” for intervention, a major focus of current research. Existing analyses of predictive models reveal that differences in the included predictive variables result in variable predictive performances. However, a major issue with current models is their limited generalizability and practical clinical utility due to the multitude of variables employed [ 8 , 9 ] . Consequently, enhancing predictive models remains a critical area of research in BPD prevention and treatment. Independent predictive factors for BPD may vary by region and ethnicity. Most BPD predictive models in China primarily focus on Han populations, with a notable lack of models tailored to the unique demographic characteristics of Xinjiang populations. Thus, developing a BPD predictive model specific to the Xinjiang area is imperative. In the present study we aimed to delineate independent BPD risk factors at varying postnatal junctures within the inaugural week. Predictive algorithms for BPD at postnatal days 1, 3, and 7 were formulated and subsequently appraised employing prospective, external multicenter data to ascertain their efficacy, thereby laying the groundwork for early BPD intervention, crafting novel individualized prevention methodologies, and mitigating the BPD burden. Methods Patients All premature infants with a gestational age (GA) < 32 weeks or birth weight (BW) < 1500 g who were admitted to the Neonatology Department of the First Affiliated Hospital of Xinjiang Medical University from Jan 01, 2017 to Dec. 31, 2022, were eligible. After excluding patients with incomplete clinical data and patients were admitted to the hospital after 24 hours of life. 554 patients remained for the final analysis. We also collected prospectively patients admitted to several centers: the First Affiliated Hospital of Xinjiang Medical University, the Friendship Hospital of Xinjiang Yili Kazakh Autonomous Prefecture, the First People’s Hospital of the Xinjiang Kashgar Area, the Karamay Central Hospital of Xinjiang, the Hospital of the First Division of Xinjiang Production and Construction Corps, and the Hami Central Hospital of Xinjiang, from Jan. 1, 2023 to Oct. 31, 2023, were eligible. This cohort was used for external validation of the BPD risk prediction model. All procedures in this study follow the Declaration of Helsinki. This study was approved by the Ethics Committee of the First Affiliated Hospital of Xinjiang Medical University (Ethics approval number: K202212-12). The patients flowchart is shown in Fig. 1. Potential predictor variables (1) Maternal clinical details: comprising gestational diseases, conception methods, and incidences of umbilical blood flow interruption. Administration of prenatal corticosteroids was documented. (2) Neonatal general information: Gestational age (GA), birth weight (BW), gender, and ethnicity (Han, Uighur, other) were recorded. (3) Fluid intake, nutritional status, respiratory support modalities, and neonatal weight variation on days 1, 3, and 7 postnatal. Serological markers encompassing complete blood counts, inflammatory markers, and blood gas analysis were obtained for days 1, 3, and 7 postnatal. (4) Derivative indices were calculated based on the laboratory evaluations, including Platelet Mass Index (PMI); Systemic Immune-Inflammation Index (SII); Pan-immune-inflammation Value (PIV); Systemic Inflammation Response Index (SIRI); Prognostic Nutritional Index (PNI); Oxygen Index (OI); and Alveolar-arterial Oxygen Difference (A-aDO2). Definition of study outcomes Diagnoses and classifications for BPD were based on the criteria set by Jensen in 2019 [ 10 ] . Patients were categorized into non-BPD, mild BPD (Grade I), and moderate to severe BPD (msBPD) (Grades II to III). Data analysis SPSS version 26.0 was used for date analysis. Numerical variables are expressed as the mean ± standard deviation (SD) or as the median with percentiles 25–75 (P25–P75). Normally distributed variables were analyzed using the analysis of variance, while non-normally distributed variables were analyzed using the Kruskal-Wallis H test. For variables with significant P values on the Kruskal-Wallis H test, we applied the non-parametric Mann-Whitney U test for further pairwise comparisons. Categorical data were compared using the chi-square test. We entered factors with a P value < 0.10 into the regression test. Ordinal logistic regression was used for univariate and multivariate analyses. All risk factors with statistical significance in multivariate analysis (P value < 0.05) were used to develop the prediction model. Model development Machine learning modeling was implemented using R 4.2.2 and Python 3.7 software Patients were randomly split into a training set (70%) and validation set (30%). Tenfold cross-validation was used to improve the models. Four types of algorithms were used to determine the optimal strategy and model:gradient boosting decision tree (GBDT), logistic regression (LR), XGBoost (XGB) and random forest (RF). Receiver operating characteristic (ROC) curves were plotted, and the area under the ROC curve (AUC) was used to evaluate the diagnostic value of each model. Results Basic Information Analysis A total of 554 infants were enrolled. Among all the patients, 286 (51.62%) were no BPD, the mean GA was (30.60 ± 1.39) w, and the mean BW was (1410.07 ± 230.70) g. 212 (38.26%) were mild, the mean GA was (29.58 ± 1.43) w, and the mean BW was (1243.44 ± 262.62) g. 56 (10.11%) were msBPD, the mean GA was (27.83 ± 1.80) w, and the mean BW was (1019.54 ± 222.57) g. Compared to the other groups, infants with msBPD had a higher incidence of asphyxia at birth, a higher proportion of endotracheal intubation resuscitation, and higher resuscitation oxygen concentrations. Mothers of msBPD infants were less likely to have received antenatal corticosteroids compared to those in the other two groups, and were more likely to experience interruption of umbilical blood flow ( P 0.05), shown in Table 1 . Table 1 Baseline characteristics among three groups Variable no (N = 286) mild (N = 212) msBPD (N = 56) P Male, n (%) 134 (46.85) 128 (60.38) 30 (53.57) 0.011 Ethnicity n (%) 0.067 Han 187 (65.38) 152 (71.70) 47 (83.93) Uyghur 42 (14.69) 28 (13.21) 3 (5.36) Other 57 (19.93) 32 (15.09) 6 (10.71) GA (w) 30.60 ± 1.39 29.58 ± 1.43 27.83 ± 1.80 < 0.001 BW (g) 1410.07 ± 230.70 1243.44 ± 62.62 1019.54 ± 222.57 < 0.001 Cesarean, n (%) 213 (74.48) 161 (75.94) 34 (60.71) 0.064 Multiple Pregnancy n (%) 71 (24.83) 57 (26.89) 19 (33.93) 0.366 Artificial Conception, n (%) 50 (17.48) 56 (26.42) 20 (35.71) 0.003 1-Apgar Score 7.51 ± 1.71 6.85 ± 1.99 6.59 ± 1.62 < 0.001 5-Apgar Score 9.04 ± 0.83 8.63 ± 1.15 8.55 ± 0.83 < 0.001 Resuscitation Methods, n (%) < 0.001 Initial Resuscitation 162 (56.64) 85 (40.09) 11 (19.64) Positive Pressure Ventilation 66 (23.08) 53 (25.00) 17 (30.36) Endotracheal Intubation 58 (20.28) 74 (34.91) 28 (50.00) Resuscitation Oxygen Concentration, n (%) < 0.001 21% 162 (56.64) 85 (40.09) 10 (17.86) 40% 67 (23.43) 34 (16.04) 12 (21.43) 100% 57 (19.93) 93 (43.87) 34 (60.71) Pregnancy-Induced Hypertension, n (%) 59 (20.63) 39 (18.40) 7 (12.50) 0.353 Preeclampsia, n (%) 50 (17.48) 53 (25.00) 13 (23.21) 0.114 Severe Eclampsia, n (%) 1 (0.35) 8 (3.77) 1 (1.79) 0.013 GDM, n (%) 51 (17.83) 47 (22.17) 12 (21.43) 0.464 Antenatal Infection, n (%) 8 (2.80) 19 (8.96) 3 (5.36) 0.011 Antenatal Steroids n (%) < 0.001 Not Used 40 (13.99) 88 (41.51) 24 (42.86) Inappropriately 77 (26.92) 53 (25.00) 16 (28.57) Appropriately 169 (59.09) 71 (33.49) 16 (28.57) Umbilical blood flow interruption n (%) 11 (3.85) 22 (10.38) 12 (21.43) < 0.001 GA Gestational age, BW Birth weight. Table 1 : Baseline characteristics among three groups Statistical significance was observed in differences in invasive respiratory support methods and FIO 2 across the three groups at different postnatal ages ( P < 0.05). Infants with msBPD had a higher prevalence of non-physiological weight reduction compared to those with no or mild BPD ( P < 0.001). As the severity of BPD increased, levels of RBC, PNI, OI, and a/APO 2 trended downward ( P < 0.05), while levels of A-aDO 2 trended upward with worsening conditions ( P < 0.05). Differences in SII levels were statistically significant across different postnatal ages ( P < 0.05). Significant differences were noted in levels of CRP, SIRI, RPR, PMI, PIV on postnatal days 1st and 3rd ( P < 0.05). Differences in PLT levels on day 1, MLR levels on3rd day, and PLR levels on 7th day were significant across the three groups ( P 0.05). Shown in supplementary Tables 1–4. External validation Prospectively, 387 infants treated by six independent neonatal rescue centers across various districts of Xinjiang were collected from Jan. 1, 2023, to October 31, 2023. This includes 146 cases from the First Affiliated Hospital of Xinjiang Medical University, 38 from the Friendship Hospital of Xinjiang Yili Kazakh Autonomous Prefecture, 152 from the First People’s Hospital of the Xinjiang Kashgar Area, 23 from the Karamay Central Hospital of Xinjiang, 14 from the Hospital of the First Division of Xinjiang Production and Construction Corps, and 14 from the Hami Central Hospital of Xinjiang. A comparison of clinical characteristics between internal and external datasets indicated certain heterogeneity, which imposes higher requirements on the robustness of the predictive models. Shown in supplementary Table 5. Multivariable analysis Ten independent predictors that influenced the severity of BPD on postnatal day 1: gender, GA, BW, severe preeclampsia, use of prenatal steroids, interruption of umbilical blood flow, FIO2, RBC, CRP, A-aDO2 (P < 0.05), which were incorporated into the model. Eleven variables were identified as independent predictors affecting the severity of BPD on day 3 postnatal: gender, GA, BW, severe preeclampsia, use of prenatal steroids, interruption of umbilical blood flow, FIO2, RBC, SIRI, PNI, A-aDO2 (P < 0.05) and incorporated into the model. Ten variables were identified as independent predictors affecting the severity of BPD on postnatal day 7: gender, GA, BW, prenatal infection, use of prenatal steroids, interruption of umbilical blood flow, FIO2, PMI, OI, A-aDO2 (P < 0.05), and were included in the model. The results of ordinal logistic regression analysis on the 1st, 3rd and 7th day after birth are shown in Table 2 . Table 2 Results of the ordinal logistic regression model for BPD severity levels at different point Time Characteristics OR SE Statistic 95% CI P 1d Gender 0.536 0.196 -3.181 0.363ཞ0.785 0.001 GA 0.526 0.130 -4.921 0.405ཞ0.676 < 0.001 BW 0.465 0.136 -5.627 0.354ཞ0.604 < 0.001 Severe eclampsia 4.125 0.645 2.197 1.173–14.875 0.028 Antenatal corticosteroids 0.425 0.238 -3.602 0.266ཞ0.676 < 0.001 Umbilical blood flow interruption 0.440 0.351 -2.334 0.220ཞ0.877 0.020 FIO 2 2.354 0.222 3.858 1.526ཞ3.646 < 0.001 RBC 0.801 0.097 -2.283 0.661ཞ0.968 0.022 CRP 1.342 0.098 3.016 1.110ཞ1.630 0.003 A-aDO 2 1.232 0.103 2.022 1.009ཞ1.516 0.043 3d Gender 0.504 0.207 -3.318 0.335ཞ0.753 < 0.001 GA 0.557 0.137 -4.285 0.424ཞ0.725 < 0.001 BW 0.530 0.132 -4.821 0.408ཞ0.684 < 0.001 Severe eclampsia 4.202 0.664 2.162 1.160-15.876 0.031 Antenatal corticosteroids 0.432 0.240 -3.498 0.269ཞ0.690 < 0.001 Umbilical blood flow interruption 0.389 0.358 -2.636 0.192ཞ0.784 0.008 FIO 2 2.502 0.225 4.074 1.613ཞ3.901 < 0.001 RBC 0.647 0.105 -4.134 0.525ཞ0.794 < 0.001 SIRI 1.579 0.139 3.287 1.219ཞ2.104 0.001 PNI 0.775 0.105 -2.421 0.629ཞ0.950 0.015 A-aDO 2 1.814 0.117 5.094 1.451ཞ2.300 < 0.001 7d Gender 0.669 0.203 -1.984 0.449ཞ0.994 0.047 GA 0.491 0.129 -5.517 0.379ཞ0.629 < 0.001 BW 0.590 0.135 -3.902 0.451ཞ0.767 < 0.001 Prenatal infection 2.183 0.393 1.988 1.016ཞ4.763 0.047 Antenatal corticosteroids 0.438 0.242 -3.417 0.272ཞ0.702 < 0.001 Umbilical blood flow interruption 0.460 0.366 -2.120 0.224ཞ0.943 0.034 FIO 2 2.459 0.226 3.979 1.582ཞ3.841 < 0.001 PMI 0.663 0.113 -3.645 0.530ཞ0.825 < 0.001 OI 0.787 0.115 -2.078 0.624ཞ0.982 0.038 A-aDO 2 1.980 0.150 4.559 1.503ཞ2.692 < 0.001 GA Gestational age, BW Birth weight, FiO 2 fraction of inspiration, RBC red blood cell, CRP C- reactive protein, SIRI Systemic Inflammation Response Index, PNI Prognostic Nutritional Index, PMI Platelet Mass Index, OI Oxygen Index, A-aDO 2 Alveolar-arterial Oxygen Difference,95% CI 95% confidence interval. Table 2 Results of the ordinal logistic regression model for BPD severity levels at different points Model performance All ten clinical factors with significant differences in multivariate analysis on the first day after birth were entered into the machine learning models. ROC curves were drawn for the validation set (Fig. 2). The AUCs of the LR, XGB, RF, and GBDT models were 0.861, 0.844, 0.853, and 0.852., respectively. All eleven clinical factors with significant differences in multivariate analysis on the first day after birth were entered into the machine learning models. ROC curves were drawn for the validation set (Fig. 3). The AUCs of the LR, XGB, RF, and GBDT models were 0.872, 0.874, 0.873, and 0.871., respectively. All ten clinical factors with significant differences in multivariate analysis on the first day after birth were entered into the machine learning models. ROC curves were drawn for the validation set (Fig. 4). The AUCs of the LR, XGB, RF, and GBDT models were 0.885, 0.906, 0.884, and 0.865., respectively. After comprehensive evaluation of the four models at different time points after birth, the LR and the XGB models showed better hierarchical prediction performance in identifying BPD high-risk newborns on the 1st, 3rd and 7th days after birth. The prediction performance using external data sets shows that the AUC of the model is 0.810, 0.837 and 0.813, respectively (Fig. 5). The detailed indexes for the four models are presented in the supplemental material (Supplementary Table 6–11). Discussion Although progress has been made in the research of BPD, the pathogenesis and etiology of the disease remain elusive. Stratified risk assessment for BPD in preterm infants is crucial. Through such assessments, we can identify risk factors and stratify BPD risk, giving clinicians a clearer management target for high-risk infants. This enables the formation of differential prevention and intervention strategies, thereby improving the treatment and quality of life for these infants. Currently, logistic regression dominates the field of BPD predictive modeling [ 8 ] . However, the pathogenesis of BPD is complex, and traditional statistical analysis methods may overlook important information variables. Machine learning algorithms, with their superior handling of complex data, are increasingly favored for BPD prediction studies. Yet, research constructing stratified prediction models for BPD using these algorithms is scarce [ 11 , 12 ] . This study aims to fill that gap by utilizing machine learning algorithms at different postnatal time points within the first week to construct stratified prediction models for BPD in extremely premature/very low birth weight infants. The optimal models for these specific time points were chosen to provide clinical guidance for early stratified prediction of BPD. In this study, the independent risk factors for the severity of BPD at three postnatal time points included gender, GA, BW, use of antenatal steroids, interruption of umbilical blood flow and FIO 2 . GA and BW are widely agreed upon as key factors for the occurrence of BPD [ 13 ] . Previous prediction models [ 14 ] have also identified GA, BW, and gender as critical early predictors for BPD, which is consistent with our findings The regulated use of antenatal corticosteroid (ACS) can reduce intrauterine inflammation, promote surfactant synthesis, stabilize alveolar architecture, minimize lung injury, foster pulmonary development, promote the maturation of fetal lungs and significantly reduce the incidence rate of BPD [ 15 – 18 ] . Studies by Greenberg et al [ 19 ] , have highlighted the predictive role of ACS on the first postnatal day for BPD, aligning with the NEOCOSUR model [ 20 ] , where ACS use is an early predictor for severe BPD or mortality postnatally. Our findings corroborate this. Umbilical blood flow abnormalities can cause various in utero anomalies, leading to fetal hypoxia and inflammatory responses, which through multiple pathways and cytokines, hinder alveolar and pulmonary vascular development, culminating in the development and progression of BPD [ 20 , 21 ] . FiO 2 was independently associated with BPD severity, consistent with BPD predictive models by Laughon [ 14 ] and Greenberg [ 19 ] . The heavier the infant’s condition, the higher the required respiratory support mode, oxygen concentration, and consequent lung damage, thus promoting the development and progression of BPD [ 22 ] . As severe preeclampsia was a significant risk factor for BPD severity on the1st and 3rd postnatal days in the present study, consistent with Shim research model [ 23 ] . Additionally, prenatal infections are identified as independent predictors of BPD severity on the 7th postnatal day. Prenatal infections not only result in a reduction of GA and BW, but also amplify the likelihood of sepsis in infants [ 24 ] . Moreover, prenatal infections activate the fetal immune response, trigger an inflammatory reaction, induce the excessive release of cytokines, provoke inflammatory cascades, worsen lung inflammation, impair lung development [ 25 ] , and elevate the risk of BPD onset and progression [ 26 ] , consistent with the predictive model for BPD developed by Zhang [ 27 ] . Underdevelopment of the lungs, lung injury, and abnormal repair post-injury represent three pivotal stages in BPD pathogenesis [ 28 ] , involving multiple mechanisms such as oxidative stress, inflammatory damage, immune dysregulation, and nutritional imbalance [ 29 , 30 ] , and involving various biomarkers. Inflammation affects the generation and maturation of red blood cells (RBC), RBC impacting immune function by inducing vascular dysfunction [ 31 ] . C-reactive protein (CRP) is an established marker of inflammation and has been validated for its value in early prediction of BPD and its severity [ 32 ] . SIRI derived from relevant inflammatory cells in peripheral blood, offers a more stable measure and compensatory function among neutrophils, lymphocytes, and monocytes, thereby providing a comprehensive reflection of the body’s inflammatory and immune status. Previous research has identified SIRI as a potential biomarker for predicting BPD [ 34 ] . PMI reflects the body’s inflammatory and immune statuses [ 33 ] , consistent with Sati research [ 35 ] . The PNI amalgamates albumin and peripheral blood lymphocyte levels, providing a cost-effective and utilitarian biomarker reflecting the body’s nutritional and immune status. A higher PNI suggests a favorable prognosis, whereas a lower index indicates a poorer outcome [ 36 ] . PNI was inversely proportional to the severity of BPD.The findings may epitomize the collective impact of nutritional and immune imbalances on the onset and progression of BPD [ 37 ] . Blood gas analysis serves as a critical component of neonatal respiratory management by directly measuring pulmonary ventilation and oxygenation functions. OI is indicative of an infant’s alveolar oxygenation efficiency. OI independently affects the severity of BPD, with a negative correlation to the disease’s severity, which corroborates previous studies [ 38 ] . A-aDO2 combines the inhaled oxygen concentration with carbon dioxide and oxygen partial pressures, serving as an index of pulmonary ventilation and alveolar oxygenation ability [ 39 ] . Elevated A-aDO2 levels, suggesting hypercapnia and hypoxic states, reflect impaired pulmonary function and extensive lung injury, suggesting that infants consequently require higher oxygen concentration and respiratory support to maintain normoxic conditions. Such injury may lead to lung damage via oxidative stress pathways, ultimately causing the development and progression of BPD [ 5 ] . With the advent of the big data era and the progression of artificial intelligence technologies, predictive modeling has advanced significantly, utilizing machine learning and other sophisticated data analytics techniques to establish more precise models. Studies employing machine learning algorithms for the prediction and management of BPD have shown substantial advancements [ 40 ] . Nevertheless, there persists contention regarding the performance of machine learning models in predicting BPD, where they haven’t conclusively outperformed traditional LR models [ 11 , 41 , 42 ] . Our research, by constructing LR, RF, GBDT, and XGB models at various timepoints within the first postnatal week, identified that the LR and XGBoost models in particular perform well on days 1, 3, and 7 for early stratified prediction of infants at high risk for BPD. In contrast with former machine learning models, our models have individually assessed the contribution of risk factors to predictive efficacy at each time point. Hence, the inclusion of different variables at distinct time points tailored to BPD’s dynamic nature has achieved effective dynamic stratified prediction within the first week postnatal with considerable predictive performance. This translation into professional academic language suitable for an SCI journal publication should undergo peer review for terminological accuracy and adherence to publication standards. The dataset used to construct the models in this study was derived from a single-center, retrospective investigation with an extensive time span, which does not guarantee complete homogeneity of all indicators and presents a multitude of confounding factors that might result in bias. Future multicenter, prospective studies to build models may enhance the performance and predictive power of these models. In conclusion, in this study developed various types of machine learning predictive models at different time points within the first postnatal week, which serve as useful tools for early stratified prediction of BPD in clinical practice. These models aid clinicians in the early personalized intervention of high-risk groups, potentially reducing the incidence of BPD. Declarations Author contributions Ning An: conceptualization, methodology, software, writing–original draft. Jingwen Yang, Rong Zhang, Wen Han, Xuchen Zhou and Rong Yang: investigation, formal analysis, data curation. Yanping Zhu and Ting Zhao: writing—review & editing. Mingxia Li: supervision, project administration, writing—review & editing. All authors discussed, revised, and approved the fnal manuscript as submitted and agreed to be accountable for all aspects of the work. Funding No. Data availability The datasets generated during and/or analyzed during the current study are available from the corresponding author on reasonable request. Conflict of interest No financial or non-financial benefits have been received or will be received from any party related directly or indirectly to the subject of this article. Ethical approval Study approval was granted by the Ethics Committee of the First Affiliated Hospital of Xinjiang Medical University (Ethics approval number: K202212-12). Informed consent to participation has been obtained from their parents. References Cao Y, Jiang S, Sun J, et al. Assessment of Neonatal Intensive Care Unit Practices, Morbidity, and Mortality Among Very Preterm Infants in China [J]. JAMA Netw Open, 2021, 4(8): e2118904. Homan TD, Nayak RP. Short- and Long-Term Complications of Bronchopulmonary Dysplasia [J]. Respiratory Care, 2021, 66(10): 1618–1629. Horbar JD, Greenberg LT, Buzas JS, et al. Trends in Mortality and Morbidities for Infants Born 24 to 28 Weeks in the US: 1997–2021 [J]. Pediatrics, 2024, 153(1): e2023064153. Bell EF, Hintz SR, Hansen NI, et al. Mortality, In-Hospital Morbidity, Care Practices, and 2-Year Outcomes for Extremely Preterm Infants in the US, 2013–2018 [J]. Jama, 2022, 327(3): 248–263. Dankhara N, Holla I, Ramarao S, et al. Bronchopulmonary Dysplasia: Pathogenesis and Pathophysiology [J]. J Clin Med, 2023, 12(13): 4207. Gilfillan M, Bhandari A, Bhandari V. Diagnosis and management of bronchopulmonary dysplasia [J]. Bmj, 2021, 375: n1974. Wang X, Guo J, Wu YY, et al. Comparing the prognostic value of 3 diagnostic criteria of bronchopulmonary dysplasia in preterm infants[J]. Zhonghua Er Ke Za Zhi, 2024, 62(1):36–42. Romijn M, Dhiman P, Finken MJJ, et al. Prediction Models for Bronchopulmonary Dysplasia in Preterm Infants: A Systematic Review and Meta-Analysis [J]. J Pediatr, 2023, 258: 113370. Yang Q, Fan X, Cao X, et al. Reporting and risk of bias of prediction models based on machine learning methods in preterm birth: A systematic review [J]. Acta Obstet Gynecol Scand, 2023, 102(1): 7–14. Jensen EA, Dysart K, Gantz MG, et al. The Diagnosis of Bronchopulmonary Dysplasia in Very Preterm Infants. An Evidence-based Approach [J]. Am J Respir Crit Care Med, 2019, 200(6): 751–759. Shah M, Jain D, Prasath S, et al. Artificial intelligence in bronchopulmonary dysplasia- current research and unexplored frontiers [J]. Pediatr Res, 2023, 93(2): 287–290. Mcadams RM, Kaur R, Sun Y, et al. Predicting clinical outcomes using artificial intelligence and machine learning in neonatal intensive care units: a systematic review [J]. J Perinatol, 2022, 42(12): 1561–1575. Bonadies L, Cavicchiolo ME, Priante E, et al. Prematurity and BPD: what general pediatricians should know [J]. Eur J Pediatr, 2023, 182(4): 1505–1516. Laughon MM, Langer JC, Bose CL, et al. Prediction of bronchopulmonary dysplasia by postnatal age in extremely premature infants [J]. Am J Respir Crit Care Med, 2011, 183(12): 1715–1722. Mcgoldrick E, Stewart F, Parker R, et al. Antenatal corticosteroids for accelerating fetal lung maturation for women at risk of preterm birth [J]. Cochrane Database Syst Rev, 2020, 12(12): Cd004454. Zhu J, Li S, Zhao Y, et al. The role of antenatal corticosteroids in twin pregnancy[J]. Front Pharmacol, 2023, 14:1072578. Papagianis PC, Pillow JJ, Moss TJ. Bronchopulmonary dysplasia: Pathophysiology and potential anti-inflammatory therapies [J]. Paediatric Respiratory Reviews, 2019, 30: 34–41. Gairabekova D, Van Rosmalen J, Duvekot JJ. Outcome of early-onset fetal growth restriction with or without abnormal umbilical artery Doppler flow [J]. Acta Obstet Gynecol Scand, 2021, 100(8): 1430–1438. Greenberg RG, Mcdonald SA, Laughon MM, et al. Online clinical tool to estimate risk of bronchopulmonary dysplasia in extremely preterm infants [J]. Arch Dis Child Fetal Neonatal Ed, 2022: 323573. Valenzuela-Stutman D, Marshall G, Tapia JL, et al. Bronchopulmonary dysplasia: risk prediction models for very-low- birth-weight infants [J]. J Perinatol, 2019, 39(9): 1275–1281. O'dwyer V, Burke G, Unterscheider J, et al. Defining the residual risk of adverse perinatal outcome in growth-restricted fetuses with normal umbilical artery blood flow[J]. Am J Obstet Gynecol, 2014, 211(4):420.e1-5. Kimble A, Robbins ME, Perez M. Pathogenesis of Bronchopulmonary Dysplasia: Role of Oxidative Stress from 'Omics' Studies [J]. Antioxidants (Basel), 2022, 11(12): 2380. Shim SY, Yun JY, Cho SJ, et al. The Prediction of Bronchopulmonary Dysplasia in Very Low Birth Weight Infants through Clinical Indicators within 1 Hour of Delivery [J]. J Korean Med Sci, 2021, 36(11): e81. Jain VG, Willis KA, Jobe A, et al. Chorioamnionitis and neonatal outcomes [J]. Pediatr Res, 2022, 91(2): 289–296. Perrone S, Manti S, Buttarelli L, et al. Vascular Endothelial Growth Factor as Molecular Target for Bronchopulmonary Dysplasia Prevention in Very Low Birth Weight Infants [J]. Int J Mol Sci, 2023, 24(3): 2729. Villamor-Martinez E, Álvarez-Fuente M, Ghazi AMT, et al. Association of Chorioamnionitis with Bronchopulmonary Dysplasia Among Preterm Infants: A Systematic Review, Meta-analysis, and Metaregression [J]. JAMA Netw Open, 2019, 2(11): e1914611. Zhang R, Xu FL, Li WL, et al. Construction of early risk prediction models fr bronchopulmonary dysplasia in preterm infants [J]. Zhongguo Dang Dai Er Ke Za Zhi, 2021, 23(10): 994–1001. Hwang JS, Rehan VK. Recent Advances in Bronchopulmonary Dysplasia: Pathophysiology, Prevention, and Treatment [J]. Lung, 2018, 196(2): 129–138. Sun T, Yu HY, Yang M, et al. Risk of asthma in preterm infants with bronchopulmonary dysplasia: a systematic review and meta-analysis [J]. World J Pediatr, 2023, 19(6): 549–556. Schmidt AR, Ramamoorthy C. Bronchopulmonary dysplasia [J]. Pediatric Anesthesia, 2022, 32(2): 174–180. Dobkin J, Mangalmurti NS. Immunomodulatory roles of red blood cells [J]. Curr Opin Hematol, 2022, 29(6): 306–309. Yang Y, Li J, Mao J. Early diagnostic value of C-reactive protein as an inflammatory marker for moderate-to-severe bronchopulmonary dysplasia in premature infants with birth weight less than 1500 g [J]. International Immunopharmacology, 2022, 103: 108462. Jiang J, Mao Y, Wu J, et al. Relationship between hematological parameters and bronchopulmonary dysplasia in premature infants [J]. J Int Med Res, 2023, 51(7): 3000605231187802. Cakir U, Tayman C, Tugcu AU, et al. Role of Systemic Inflammatory Indices in the Prediction of Moderate to Severe Bronchopulmonary Dysplasia in Preterm Infants[J]. Arch Bronconeumol, 2023, 59(4):216–22. Sati SK, Springer C, Kim R, et al. Platelet parameters as biomarker for bronchopulmonary dysplasia in very low birth weight neonates in the first two weeks of life [J]. Minerva Pediatr (Torino), 2023. Dai M, Sun Q. Prognostic and clinicopathological significance of prognostic nutritional index (PNI) in patients with oral cancer: a meta-analysis [J]. Aging (Albany NY), 2023, 15(5): 1615–1627. Saenz De Pipaon M, Nelin LD, Gehred A, et al. The role of nutritional interventions in the prevention and treatment of chronic lung disease of prematurity[J]. Pediatr Res, 2024. Chou FS, Leigh RM, Rao SS, et al. Oxygenation index in the first three weeks of life is a predictor of bronchopulmonary dysplasia grade in very preterm infants[J]. BMC Pediatr, 2023, 23(1):18. Stickland MK, Lindinger MI, Olfert IM, et al. Pulmonary gas exchange and acid-base balance during exercise[J]. Compr Physiol, 2013, 3(2):693–739. Keles E, Bagci U. The past, current, and future of neonatal intensive care units with artificial intelligence: a systematic review [J]. NPJ Digit Med, 2023, 6(1): 220. He W, Zhang L, Feng R, et al. Risk factors and machine learning prediction models for bronchopulmonary dysplasia severity in the Chinese population [J]. World J Pediatr, 2023, 19(6): 568–576. Khurshid F, Coo H, Khalil A, et al. Comparison of Multivariable Logistic Regression and Machine Learning Models for Predicting Bronchopulmonary Dysplasia or Death in Very Preterm Infants [J]. Front Pediatr, 2021, 9: 759776. Additional Declarations No competing interests reported. Supplementary Files supplementaryfiles.docx Cite Share Download PDF Status: Posted Version 1 posted 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-4648257","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":329246058,"identity":"89220ff8-b6ae-44eb-beb3-972ad29ca472","order_by":0,"name":"Ning An","email":"","orcid":"","institution":"Xinjiang Medical University","correspondingAuthor":false,"prefix":"","firstName":"Ning","middleName":"","lastName":"An","suffix":""},{"id":329246059,"identity":"c1c70230-26e6-497b-bd32-8b82e02714dd","order_by":1,"name":"Jingwen Yang","email":"","orcid":"","institution":"The first People’s Hospital of Kashi prefecture","correspondingAuthor":false,"prefix":"","firstName":"Jingwen","middleName":"","lastName":"Yang","suffix":""},{"id":329246064,"identity":"9f67bd62-be54-442d-a7d9-8d5c3c7262eb","order_by":2,"name":"Rong Zhang","email":"","orcid":"","institution":"Xinjiang Yili Friendship Hospital","correspondingAuthor":false,"prefix":"","firstName":"Rong","middleName":"","lastName":"Zhang","suffix":""},{"id":329246068,"identity":"59cc3a41-cdd9-41d6-9fb2-20f5c7e5ac16","order_by":3,"name":"Wen Han","email":"","orcid":"","institution":"Karamay Central Hospital of Xinjiang","correspondingAuthor":false,"prefix":"","firstName":"Wen","middleName":"","lastName":"Han","suffix":""},{"id":329246071,"identity":"fe098cf5-d7cb-424d-8cc1-fbf508427831","order_by":4,"name":"Xuchen Zhou","email":"","orcid":"","institution":"The first Division Hospital of Xinjiang Production and Construction Corps","correspondingAuthor":false,"prefix":"","firstName":"Xuchen","middleName":"","lastName":"Zhou","suffix":""},{"id":329246072,"identity":"9ff68e6e-7522-41e2-a30e-b1e4ac92015a","order_by":5,"name":"Rong Yang","email":"","orcid":"","institution":"The Central Hospital of Hami District","correspondingAuthor":false,"prefix":"","firstName":"Rong","middleName":"","lastName":"Yang","suffix":""},{"id":329246076,"identity":"bd080c0e-808d-40ab-bba8-f5dfd803fc0d","order_by":6,"name":"Yanping Zhu","email":"","orcid":"","institution":"The First Affiliated Hospital of Xinjiang Medical University","correspondingAuthor":false,"prefix":"","firstName":"Yanping","middleName":"","lastName":"Zhu","suffix":""},{"id":329246077,"identity":"a06ba59b-c7e0-474c-92a4-bc518bb6d644","order_by":7,"name":"Ting Zhao","email":"","orcid":"","institution":"The First Affiliated Hospital of Xinjiang Medical University","correspondingAuthor":false,"prefix":"","firstName":"Ting","middleName":"","lastName":"Zhao","suffix":""},{"id":329246078,"identity":"edeb98da-edcd-4e0d-a03e-611fb0b113a6","order_by":8,"name":"Mingxia Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6klEQVRIiWNgGAWjYBACPmYGhgNAmoeBmfnAwQ8VEnLyhLSwwbWwsyU+ljhjYWzYQEgLnMXPY2zA21aRCDYBrxZ27sTDBb8Oy/A3M5hJSM6TSGBsYH746AZeh/FuODyzL41H4jBDmkThNok8dgY2Y+McQlp4e2x4GA4zHJOQ3CZRzNjAwyZNhBYJHvnDjG0SvHMkEhsOEKOF54cNj8FhZmYD3gZitfA2pPEYHmZjfCxxTMLYsJmAX/j5z27+zPPnsL3c+fMfDn6oqZOTZ29++BifFjBgbEPmMRNSDgZ/iFI1CkbBKBgFIxUAALtGRFqnofWtAAAAAElFTkSuQmCC","orcid":"","institution":"The First Affiliated Hospital of Xinjiang Medical University","correspondingAuthor":true,"prefix":"","firstName":"Mingxia","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2024-06-27 11:40:30","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4648257/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4648257/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":60851928,"identity":"09f12d3f-922a-4e8a-bf00-9e5826488536","added_by":"auto","created_at":"2024-07-22 21:05:30","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":78685,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003ePatients flowchart.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"OnlineFig1.png","url":"https://assets-eu.researchsquare.com/files/rs-4648257/v1/670eb2fb1175538b3b1e9d62.png"},{"id":60852880,"identity":"d439b24a-f296-4653-a4cc-598309e3a963","added_by":"auto","created_at":"2024-07-22 21:13:30","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":69047,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003ePerformance of different machine learning models on validation sets of 1st day after birth. A-D The ROC curves of the LR, XGB, RF and GBDT models. Class 0 represents no BPD; class 1 represents mild BPD; class 3 represents msBPD\u003c/strong\u003e.\u003c/p\u003e","description":"","filename":"OnlineFig2.png","url":"https://assets-eu.researchsquare.com/files/rs-4648257/v1/65e95703df431f588806a9f7.png"},{"id":60851932,"identity":"0d777f8f-ba46-4c2a-8ea9-91d67d270f1e","added_by":"auto","created_at":"2024-07-22 21:05:30","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":67091,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003ePerformance of different machine learning models on validation sets of 3rd day after birth. A-D The ROC curves of the LR, XGB, RF and GBDT models. Class 0 represents no BPD; class 1 represents mild BPD; class 2 represents msBPD\u003c/strong\u003e.\u003c/p\u003e","description":"","filename":"OnlineFig3.png","url":"https://assets-eu.researchsquare.com/files/rs-4648257/v1/c46a3f5fb1575ee4587e5356.png"},{"id":60851931,"identity":"d936201c-81df-4c73-8272-f235a978e08a","added_by":"auto","created_at":"2024-07-22 21:05:30","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":70170,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003ePerformance of different machine learning models on validation sets of 7th day after birth. A-D The ROC curves of the LR, XGB, RF and GBDT models. Class 0 represents no BPD; class 1 represents mild BPD; class 2 represents msBPD\u003c/strong\u003e.\u003c/p\u003e","description":"","filename":"OnlineFig4.png","url":"https://assets-eu.researchsquare.com/files/rs-4648257/v1/3688b9e3be71e02f30ee033e.png"},{"id":60851933,"identity":"bf50abe9-7453-4701-b79b-ad48688d95f8","added_by":"auto","created_at":"2024-07-22 21:05:30","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":100834,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003ePerformance of different machine learning models on external validation sets. A-C The ROC curves of the LR, XGB, and XGB models. Class 0 represents no BPD; class 1 represents mild BPD; class 2 represents msBPD.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"OnlineFig5.png","url":"https://assets-eu.researchsquare.com/files/rs-4648257/v1/252a4d44b341207398dd973b.png"},{"id":66368151,"identity":"68669307-3237-4549-a68c-3331c16db7ab","added_by":"auto","created_at":"2024-10-11 03:46:32","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3894,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4648257/v1/6f0fb1f1-4476-4f25-b1af-bad79bb63109.pdf"},{"id":60851930,"identity":"c7e94c6f-1e7e-4baa-9bc5-847f2444da93","added_by":"auto","created_at":"2024-07-22 21:05:30","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":61575,"visible":true,"origin":"","legend":"","description":"","filename":"supplementaryfiles.docx","url":"https://assets-eu.researchsquare.com/files/rs-4648257/v1/d77a34b43cf82f0aa7f0f606.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Construction and Application of Early Stratification Dynamic Prediction Model for Bronchopulmonary Dysplasia in Extremely Premature / Very Low Birth Weight Infants","fulltext":[{"header":"Introduction","content":"\u003cp\u003eBronchopulmonary Dysplasia (BPD) in infants is defined by the need for supplemental oxygen or respiratory support at 36 weeks postmenstrual age (PMA) \u003csup\u003e[\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]\u003c/sup\u003e. BPD is not only the most common complication among preterm infants but also a significant risk factor for other complications and various chronic non-communicable diseases \u003csup\u003e[\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]\u003c/sup\u003e. The advancements in perinatal care have significantly improved the survival rates of very preterm infants (VLBW) and extremely preterm infants (ELBW). Consequently, the incidence of most complications has declined except for BPD, which continues to rise globally \u003csup\u003e[\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e, \u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eBPD is the most prevalent chronic lung disease in preterm infants and a critical factor affecting their quality of life. The etiopathogenesis of BPD involves multiple factors before, during, and after birth \u003csup\u003e[\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e, \u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]\u003c/sup\u003e, although the exact mechanisms remain unknown. Symptomatic and supportive treatments may delay the onset and progression of BPD, but there is no specific treatment once BPD develops, making prevention the primary clinical approach. The diagnostic criteria for BPD are typically met at 28 days postnatally, at which point pulmonary damage is often irreversible, missing the optimal intervention window and increasing the risk of BPD-related complications \u003csup\u003e[\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]\u003c/sup\u003e. Therefore, early prevention is crucial, and the early prediction of BPD remains a significant challenge. Identifying BPD risk factors and establishing predictive models to accurately forecast the onset of BPD can provide clinical \u0026ldquo;windows of opportunity\u0026rdquo; for intervention, a major focus of current research. Existing analyses of predictive models reveal that differences in the included predictive variables result in variable predictive performances. However, a major issue with current models is their limited generalizability and practical clinical utility due to the multitude of variables employed \u003csup\u003e[\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e, \u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]\u003c/sup\u003e. Consequently, enhancing predictive models remains a critical area of research in BPD prevention and treatment.\u003c/p\u003e \u003cp\u003eIndependent predictive factors for BPD may vary by region and ethnicity. Most BPD predictive models in China primarily focus on Han populations, with a notable lack of models tailored to the unique demographic characteristics of Xinjiang populations. Thus, developing a BPD predictive model specific to the Xinjiang area is imperative. In the present study we aimed to delineate independent BPD risk factors at varying postnatal junctures within the inaugural week. Predictive algorithms for BPD at postnatal days 1, 3, and 7 were formulated and subsequently appraised employing prospective, external multicenter data to ascertain their efficacy, thereby laying the groundwork for early BPD intervention, crafting novel individualized prevention methodologies, and mitigating the BPD burden.\u003c/p\u003e"},{"header":"Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003ePatients\u003c/h2\u003e \u003cp\u003eAll premature infants with a gestational age (GA)\u0026thinsp;\u0026lt;\u0026thinsp;32 weeks or birth weight (BW)\u0026thinsp;\u0026lt;\u0026thinsp;1500 g who were admitted to the Neonatology Department of the First Affiliated Hospital of Xinjiang Medical University from Jan 01, 2017 to Dec. 31, 2022, were eligible. After excluding patients with incomplete clinical data and patients were admitted to the hospital after 24 hours of life. 554 patients remained for the final analysis. We also collected prospectively patients admitted to several centers: the First Affiliated Hospital of Xinjiang Medical University, the Friendship Hospital of Xinjiang Yili Kazakh Autonomous Prefecture, the First People\u0026rsquo;s Hospital of the Xinjiang Kashgar Area, the Karamay Central Hospital of Xinjiang, the Hospital of the First Division of Xinjiang Production and Construction Corps, and the Hami Central Hospital of Xinjiang, from Jan. 1, 2023 to Oct. 31, 2023, were eligible. This cohort was used for external validation of the BPD risk prediction model.\u003c/p\u003e \u003cp\u003eAll procedures in this study follow the Declaration of Helsinki. This study was approved by the Ethics Committee of the First Affiliated Hospital of Xinjiang Medical University (Ethics approval number: K202212-12). The patients flowchart is shown in Fig.\u0026nbsp;1.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003ePotential predictor variables\u003c/h2\u003e \u003cp\u003e(1) Maternal clinical details: comprising gestational diseases, conception methods, and incidences of umbilical blood flow interruption. Administration of prenatal corticosteroids was documented.\u003c/p\u003e \u003cp\u003e(2) Neonatal general information: Gestational age (GA), birth weight (BW), gender, and ethnicity (Han, Uighur, other) were recorded.\u003c/p\u003e \u003cp\u003e(3) Fluid intake, nutritional status, respiratory support modalities, and neonatal weight variation on days 1, 3, and 7 postnatal. Serological markers encompassing complete blood counts, inflammatory markers, and blood gas analysis were obtained for days 1, 3, and 7 postnatal.\u003c/p\u003e \u003cp\u003e(4) Derivative indices were calculated based on the laboratory evaluations, including Platelet Mass Index (PMI); Systemic Immune-Inflammation Index (SII); Pan-immune-inflammation Value (PIV); Systemic Inflammation Response Index (SIRI); Prognostic Nutritional Index (PNI); Oxygen Index (OI); and Alveolar-arterial Oxygen Difference (A-aDO2).\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003eDefinition of study outcomes\u003c/h2\u003e \u003cp\u003eDiagnoses and classifications for BPD were based on the criteria set by Jensen in 2019 \u003csup\u003e[\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]\u003c/sup\u003e. Patients were categorized into non-BPD, mild BPD (Grade I), and moderate to severe BPD (msBPD) (Grades II to III).\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003eData analysis\u003c/h2\u003e \u003cp\u003eSPSS version 26.0 was used for date analysis. Numerical variables are expressed as the mean\u0026thinsp;\u0026plusmn;\u0026thinsp;standard deviation (SD) or as the median with percentiles 25\u0026ndash;75 (P25\u0026ndash;P75). Normally distributed variables were analyzed using the analysis of variance, while non-normally distributed variables were analyzed using the Kruskal-Wallis H test. For variables with significant P values on the Kruskal-Wallis \u003cem\u003eH\u003c/em\u003e test, we applied the non-parametric Mann-Whitney \u003cem\u003eU\u003c/em\u003e test for further pairwise comparisons. Categorical data were compared using the chi-square test. We entered factors with a P value\u0026thinsp;\u0026lt;\u0026thinsp;0.10 into the regression test. Ordinal logistic regression was used for univariate and multivariate analyses. All risk factors with statistical significance in multivariate analysis (P value\u0026thinsp;\u0026lt;\u0026thinsp;0.05) were used to develop the prediction model.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003eModel development\u003c/h2\u003e \u003cp\u003eMachine learning modeling was implemented using R 4.2.2 and Python 3.7 software Patients were randomly split into a training set (70%) and validation set (30%). Tenfold cross-validation was used to improve the models. Four types of algorithms were used to determine the optimal strategy and model:gradient boosting decision tree (GBDT), logistic regression (LR), XGBoost (XGB) and random forest (RF). Receiver operating characteristic (ROC) curves were plotted, and the area under the ROC curve (AUC) was used to evaluate the diagnostic value of each model.\u003c/p\u003e \u003c/div\u003e"},{"header":"Results","content":"\u003cdiv id=\"Sec9\" class=\"Section2\"\u003e \u003ch2\u003eBasic Information Analysis\u003c/h2\u003e \u003cp\u003eA total of 554 infants were enrolled. Among all the patients, 286 (51.62%) were no BPD, the mean GA was (30.60\u0026thinsp;\u0026plusmn;\u0026thinsp;1.39) w, and the mean BW was (1410.07\u0026thinsp;\u0026plusmn;\u0026thinsp;230.70) g. 212 (38.26%) were mild, the mean GA was (29.58\u0026thinsp;\u0026plusmn;\u0026thinsp;1.43) w, and the mean BW was (1243.44\u0026thinsp;\u0026plusmn;\u0026thinsp;262.62) g. 56 (10.11%) were msBPD, the mean GA was (27.83\u0026thinsp;\u0026plusmn;\u0026thinsp;1.80) w, and the mean BW was (1019.54\u0026thinsp;\u0026plusmn;\u0026thinsp;222.57) g. Compared to the other groups, infants with msBPD had a higher incidence of asphyxia at birth, a higher proportion of endotracheal intubation resuscitation, and higher resuscitation oxygen concentrations. Mothers of msBPD infants were less likely to have received antenatal corticosteroids compared to those in the other two groups, and were more likely to experience interruption of umbilical blood flow (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001). No significant differences were observed between the groups in terms of gender, mode of delivery, or other maternal gestational diseases (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026gt;\u0026thinsp;0.05), shown in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e.\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\u003eBaseline characteristics among three groups\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eVariable\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eno (N\u0026thinsp;=\u0026thinsp;286)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003emild (N\u0026thinsp;=\u0026thinsp;212)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003emsBPD (N\u0026thinsp;=\u0026thinsp;56)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMale, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e134 (46.85)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e128 (60.38)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e30 (53.57)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.011\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEthnicity n (%)\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\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.067\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHan\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e187 (65.38)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e152 (71.70)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e47 (83.93)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eUyghur\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e42 (14.69)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e28 (13.21)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e3 (5.36)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOther\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e57 (19.93)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e32 (15.09)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e6 (10.71)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGA (w)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e30.60\u0026thinsp;\u0026plusmn;\u0026thinsp;1.39\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e29.58\u0026thinsp;\u0026plusmn;\u0026thinsp;1.43\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e27.83\u0026thinsp;\u0026plusmn;\u0026thinsp;1.80\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\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\u003eBW (g)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1410.07\u0026thinsp;\u0026plusmn;\u0026thinsp;230.70\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1243.44\u0026thinsp;\u0026plusmn;\u0026thinsp;62.62\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e1019.54\u0026thinsp;\u0026plusmn;\u0026thinsp;222.57\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\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\u003eCesarean, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e213 (74.48)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e161 (75.94)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e34 (60.71)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.064\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMultiple Pregnancy n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e71 (24.83)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e57 (26.89)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e19 (33.93)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.366\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eArtificial Conception, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e50 (17.48)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e56 (26.42)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e20 (35.71)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.003\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e1-Apgar Score\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e7.51\u0026thinsp;\u0026plusmn;\u0026thinsp;1.71\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e6.85\u0026thinsp;\u0026plusmn;\u0026thinsp;1.99\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e6.59\u0026thinsp;\u0026plusmn;\u0026thinsp;1.62\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\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\u003e5-Apgar Score\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e9.04\u0026thinsp;\u0026plusmn;\u0026thinsp;0.83\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e8.63\u0026thinsp;\u0026plusmn;\u0026thinsp;1.15\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e8.55\u0026thinsp;\u0026plusmn;\u0026thinsp;0.83\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\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\u003eResuscitation Methods, n (%)\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\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\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\u003eInitial Resuscitation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e162 (56.64)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e85 (40.09)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e11 (19.64)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePositive Pressure Ventilation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e66 (23.08)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e53 (25.00)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e17 (30.36)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEndotracheal Intubation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e58 (20.28)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e74 (34.91)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e28 (50.00)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eResuscitation Oxygen Concentration, n (%)\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\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\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\u003e21%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e162 (56.64)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e85 (40.09)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e10 (17.86)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e40%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e67 (23.43)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e34 (16.04)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e12 (21.43)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e100%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e57 (19.93)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e93 (43.87)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e34 (60.71)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePregnancy-Induced Hypertension, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e59 (20.63)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e39 (18.40)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e7 (12.50)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.353\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePreeclampsia, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e50 (17.48)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e53 (25.00)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e13 (23.21)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.114\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSevere Eclampsia, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1 (0.35)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e8 (3.77)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e1 (1.79)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.013\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGDM, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e51 (17.83)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e47 (22.17)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e12 (21.43)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.464\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAntenatal Infection, n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e8 (2.80)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e19 (8.96)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e3 (5.36)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.011\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAntenatal Steroids n (%)\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\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\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\u003eNot Used\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e40 (13.99)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e88 (41.51)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e24 (42.86)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eInappropriately\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e77 (26.92)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e53 (25.00)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e16 (28.57)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAppropriately\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e169 (59.09)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e71 (33.49)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e16 (28.57)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eUmbilical blood flow interruption n (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e11 (3.85)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e22 (10.38)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e12 (21.43)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"5\"\u003eGA Gestational age, BW Birth weight.\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e: Baseline characteristics among three groups\u003c/p\u003e \u003cp\u003eStatistical significance was observed in differences in invasive respiratory support methods and FIO\u003csub\u003e2\u003c/sub\u003e across the three groups at different postnatal ages (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05). Infants with msBPD had a higher prevalence of non-physiological weight reduction compared to those with no or mild BPD (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001). As the severity of BPD increased, levels of RBC, PNI, OI, and a/APO\u003csub\u003e2\u003c/sub\u003e trended downward (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05), while levels of A-aDO\u003csub\u003e2\u003c/sub\u003e trended upward with worsening conditions (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05). Differences in SII levels were statistically significant across different postnatal ages (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05). Significant differences were noted in levels of CRP, SIRI, RPR, PMI, PIV on postnatal days 1st and 3rd (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05). Differences in PLT levels on day 1, MLR levels on3rd day, and PLR levels on 7th day were significant across the three groups (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05), with no significant differences in other laboratory tests (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026gt;\u0026thinsp;0.05). Shown in supplementary Tables\u0026nbsp;1\u0026ndash;4.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec10\" class=\"Section2\"\u003e \u003ch2\u003eExternal validation\u003c/h2\u003e \u003cp\u003eProspectively, 387 infants treated by six independent neonatal rescue centers across various districts of Xinjiang were collected from Jan. 1, 2023, to October 31, 2023. This includes 146 cases from the First Affiliated Hospital of Xinjiang Medical University, 38 from the Friendship Hospital of Xinjiang Yili Kazakh Autonomous Prefecture, 152 from the First People\u0026rsquo;s Hospital of the Xinjiang Kashgar Area, 23 from the Karamay Central Hospital of Xinjiang, 14 from the Hospital of the First Division of Xinjiang Production and Construction Corps, and 14 from the Hami Central Hospital of Xinjiang. A comparison of clinical characteristics between internal and external datasets indicated certain heterogeneity, which imposes higher requirements on the robustness of the predictive models. Shown in supplementary Table\u0026nbsp;5.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec11\" class=\"Section2\"\u003e \u003ch2\u003eMultivariable analysis\u003c/h2\u003e \u003cp\u003eTen independent predictors that influenced the severity of BPD on postnatal day 1: gender, GA, BW, severe preeclampsia, use of prenatal steroids, interruption of umbilical blood flow, FIO2, RBC, CRP, A-aDO2 (P\u0026thinsp;\u0026lt;\u0026thinsp;0.05), which were incorporated into the model. Eleven variables were identified as independent predictors affecting the severity of BPD on day 3 postnatal: gender, GA, BW, severe preeclampsia, use of prenatal steroids, interruption of umbilical blood flow, FIO2, RBC, SIRI, PNI, A-aDO2 (P\u0026thinsp;\u0026lt;\u0026thinsp;0.05) and incorporated into the model. Ten variables were identified as independent predictors affecting the severity of BPD on postnatal day 7: gender, GA, BW, prenatal infection, use of prenatal steroids, interruption of umbilical blood flow, FIO2, PMI, OI, A-aDO2 (P\u0026thinsp;\u0026lt;\u0026thinsp;0.05), and were included in the model. The results of ordinal logistic regression analysis on the 1st, 3rd and 7th day after birth are shown in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eResults of the ordinal logistic regression model for BPD severity levels at different point\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=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTime\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eCharacteristics\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eOR\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eSE\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eStatistic\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003e95% \u003cem\u003eCI\u003c/em\u003e\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"9\" rowspan=\"10\"\u003e \u003cp\u003e1d\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eGender\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.536\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.196\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e-3.181\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.363ཞ0.785\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eGA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.526\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.130\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e-4.921\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.405ཞ0.676\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eBW\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.465\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.136\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e-5.627\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.354ཞ0.604\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSevere eclampsia\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e4.125\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.645\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e2.197\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1.173\u0026ndash;14.875\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.028\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAntenatal corticosteroids\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.425\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.238\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e-3.602\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.266ཞ0.676\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eUmbilical blood flow interruption\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.440\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.351\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e-2.334\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.220ཞ0.877\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.020\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFIO\u003csub\u003e2\u003c/sub\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2.354\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.222\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e3.858\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1.526ཞ3.646\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eRBC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.801\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.097\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e-2.283\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.661ཞ0.968\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.022\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eCRP\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.342\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.098\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e3.016\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1.110ཞ1.630\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.003\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eA-aDO\u003csub\u003e2\u003c/sub\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.232\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.103\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e2.022\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1.009ཞ1.516\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.043\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"10\" rowspan=\"11\"\u003e \u003cp\u003e3d\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eGender\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.504\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.207\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e-3.318\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.335ཞ0.753\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eGA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.557\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.137\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e-4.285\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.424ཞ0.725\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eBW\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.530\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.132\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e-4.821\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.408ཞ0.684\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSevere eclampsia\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e4.202\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.664\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e2.162\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1.160-15.876\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.031\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAntenatal corticosteroids\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.432\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.240\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e-3.498\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.269ཞ0.690\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eUmbilical blood flow interruption\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.389\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.358\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e-2.636\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.192ཞ0.784\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.008\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFIO\u003csub\u003e2\u003c/sub\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2.502\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.225\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e4.074\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1.613ཞ3.901\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eRBC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.647\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.105\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e-4.134\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.525ཞ0.794\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSIRI\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.579\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.139\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e3.287\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1.219ཞ2.104\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePNI\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.775\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.105\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e-2.421\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.629ཞ0.950\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.015\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eA-aDO\u003csub\u003e2\u003c/sub\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.814\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.117\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e5.094\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1.451ཞ2.300\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" 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\" morerows=\"9\" rowspan=\"10\"\u003e \u003cp\u003e7d\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eGender\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.669\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.203\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e-1.984\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.449ཞ0.994\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.047\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eGA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.491\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.129\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e-5.517\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.379ཞ0.629\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eBW\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.590\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.135\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e-3.902\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.451ཞ0.767\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePrenatal infection\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2.183\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.393\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e1.988\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1.016ཞ4.763\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.047\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAntenatal corticosteroids\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.438\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.242\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e-3.417\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.272ཞ0.702\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eUmbilical blood flow interruption\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.460\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.366\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e-2.120\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.224ཞ0.943\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.034\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFIO\u003csub\u003e2\u003c/sub\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2.459\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.226\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e3.979\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1.582ཞ3.841\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePMI\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.663\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.113\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e-3.645\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.530ཞ0.825\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOI\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.787\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.115\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e-2.078\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.624ཞ0.982\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.038\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eA-aDO\u003csub\u003e2\u003c/sub\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.980\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.150\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e4.559\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1.503ཞ2.692\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"7\"\u003eGA Gestational age, BW Birth weight, FiO\u003csub\u003e2\u003c/sub\u003e fraction of inspiration, RBC red blood cell, CRP C- reactive protein, SIRI Systemic Inflammation Response Index, PNI Prognostic Nutritional Index, PMI Platelet Mass Index, OI Oxygen Index, A-aDO\u003csub\u003e2\u003c/sub\u003e Alveolar-arterial Oxygen Difference,95% CI 95% confidence interval.\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e \u003cb\u003eResults of the ordinal logistic regression model for BPD severity levels at different points\u003c/b\u003e\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec12\" class=\"Section2\"\u003e \u003ch2\u003eModel performance\u003c/h2\u003e \u003cp\u003eAll ten clinical factors with significant differences in multivariate analysis on the first day after birth were entered into the machine learning models. ROC curves were drawn for the validation set (Fig.\u0026nbsp;2). The AUCs of the LR, XGB, RF, and GBDT models were 0.861, 0.844, 0.853, and 0.852., respectively.\u003c/p\u003e \u003cp\u003eAll eleven clinical factors with significant differences in multivariate analysis on the first day after birth were entered into the machine learning models. ROC curves were drawn for the validation set (Fig.\u0026nbsp;3). The AUCs of the LR, XGB, RF, and GBDT models were 0.872, 0.874, 0.873, and 0.871., respectively.\u003c/p\u003e \u003cp\u003eAll ten clinical factors with significant differences in multivariate analysis on the first day after birth were entered into the machine learning models. ROC curves were drawn for the validation set (Fig.\u0026nbsp;4). The AUCs of the LR, XGB, RF, and GBDT models were 0.885, 0.906, 0.884, and 0.865., respectively.\u003c/p\u003e \u003cp\u003eAfter comprehensive evaluation of the four models at different time points after birth, the LR and the XGB models showed better hierarchical prediction performance in identifying BPD high-risk newborns on the 1st, 3rd and 7th days after birth. The prediction performance using external data sets shows that the AUC of the model is 0.810, 0.837 and 0.813, respectively (Fig.\u0026nbsp;5).\u003c/p\u003e \u003cp\u003eThe detailed indexes for the four models are presented in the supplemental material (Supplementary Table\u0026nbsp;6\u0026ndash;11).\u003c/p\u003e "},{"header":"Discussion","content":"\u003cp\u003eAlthough progress has been made in the research of BPD, the pathogenesis and etiology of the disease remain elusive. Stratified risk assessment for BPD in preterm infants is crucial. Through such assessments, we can identify risk factors and stratify BPD risk, giving clinicians a clearer management target for high-risk infants. This enables the formation of differential prevention and intervention strategies, thereby improving the treatment and quality of life for these infants.\u003c/p\u003e \u003cp\u003eCurrently, logistic regression dominates the field of BPD predictive modeling \u003csup\u003e[\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]\u003c/sup\u003e. However, the pathogenesis of BPD is complex, and traditional statistical analysis methods may overlook important information variables. Machine learning algorithms, with their superior handling of complex data, are increasingly favored for BPD prediction studies. Yet, research constructing stratified prediction models for BPD using these algorithms is scarce \u003csup\u003e[\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e, \u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e]\u003c/sup\u003e. This study aims to fill that gap by utilizing machine learning algorithms at different postnatal time points within the first week to construct stratified prediction models for BPD in extremely premature/very low birth weight infants. The optimal models for these specific time points were chosen to provide clinical guidance for early stratified prediction of BPD.\u003c/p\u003e \u003cp\u003eIn this study, the independent risk factors for the severity of BPD at three postnatal time points included gender, GA, BW, use of antenatal steroids, interruption of umbilical blood flow and FIO\u003csub\u003e2\u003c/sub\u003e. GA and BW are widely agreed upon as key factors for the occurrence of BPD \u003csup\u003e[\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e]\u003c/sup\u003e. Previous prediction models \u003csup\u003e[\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e]\u003c/sup\u003e have also identified GA, BW, and gender as critical early predictors for BPD, which is consistent with our findings\u003c/p\u003e \u003cp\u003eThe regulated use of antenatal corticosteroid (ACS) can reduce intrauterine inflammation, promote surfactant synthesis, stabilize alveolar architecture, minimize lung injury, foster pulmonary development, promote the maturation of fetal lungs and significantly reduce the incidence rate of BPD \u003csup\u003e[\u003cspan additionalcitationids=\"CR16 CR17\" citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e]\u003c/sup\u003e. Studies by Greenberg et al \u003csup\u003e[\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]\u003c/sup\u003e, have highlighted the predictive role of ACS on the first postnatal day for BPD, aligning with the NEOCOSUR model \u003csup\u003e[\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]\u003c/sup\u003e, where ACS use is an early predictor for severe BPD or mortality postnatally. Our findings corroborate this. Umbilical blood flow abnormalities can cause various in utero anomalies, leading to fetal hypoxia and inflammatory responses, which through multiple pathways and cytokines, hinder alveolar and pulmonary vascular development, culminating in the development and progression of BPD \u003csup\u003e[\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e, \u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e]\u003c/sup\u003e. FiO\u003csub\u003e2\u003c/sub\u003e was independently associated with BPD severity, consistent with BPD predictive models by Laughon \u003csup\u003e[\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e]\u003c/sup\u003e and Greenberg \u003csup\u003e[\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]\u003c/sup\u003e. The heavier the infant\u0026rsquo;s condition, the higher the required respiratory support mode, oxygen concentration, and consequent lung damage, thus promoting the development and progression of BPD \u003csup\u003e[\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e]\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eAs severe preeclampsia was a significant risk factor for BPD severity on the1st and 3rd postnatal days in the present study, consistent with Shim research model \u003csup\u003e[\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e]\u003c/sup\u003e. Additionally, prenatal infections are identified as independent predictors of BPD severity on the 7th postnatal day. Prenatal infections not only result in a reduction of GA and BW, but also amplify the likelihood of sepsis in infants \u003csup\u003e[\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e]\u003c/sup\u003e. Moreover, prenatal infections activate the fetal immune response, trigger an inflammatory reaction, induce the excessive release of cytokines, provoke inflammatory cascades, worsen lung inflammation, impair lung development \u003csup\u003e[\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e]\u003c/sup\u003e, and elevate the risk of BPD onset and progression \u003csup\u003e[\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e]\u003c/sup\u003e, consistent with the predictive model for BPD developed by Zhang \u003csup\u003e[\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e]\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eUnderdevelopment of the lungs, lung injury, and abnormal repair post-injury represent three pivotal stages in BPD pathogenesis \u003csup\u003e[\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e]\u003c/sup\u003e, involving multiple mechanisms such as oxidative stress, inflammatory damage, immune dysregulation, and nutritional imbalance \u003csup\u003e[\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e, \u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e]\u003c/sup\u003e, and involving various biomarkers. Inflammation affects the generation and maturation of red blood cells (RBC), RBC impacting immune function by inducing vascular dysfunction \u003csup\u003e[\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e]\u003c/sup\u003e. C-reactive protein (CRP) is an established marker of inflammation and has been validated for its value in early prediction of BPD and its severity \u003csup\u003e[\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e]\u003c/sup\u003e. SIRI derived from relevant inflammatory cells in peripheral blood, offers a more stable measure and compensatory function among neutrophils, lymphocytes, and monocytes, thereby providing a comprehensive reflection of the body\u0026rsquo;s inflammatory and immune status. Previous research has identified SIRI as a potential biomarker for predicting BPD \u003csup\u003e[\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e]\u003c/sup\u003e. PMI reflects the body\u0026rsquo;s inflammatory and immune statuses \u003csup\u003e[\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e]\u003c/sup\u003e, consistent with Sati research \u003csup\u003e[\u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e35\u003c/span\u003e]\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eThe PNI amalgamates albumin and peripheral blood lymphocyte levels, providing a cost-effective and utilitarian biomarker reflecting the body\u0026rsquo;s nutritional and immune status. A higher PNI suggests a favorable prognosis, whereas a lower index indicates a poorer outcome \u003csup\u003e[\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e]\u003c/sup\u003e. PNI was inversely proportional to the severity of BPD.The findings may epitomize the collective impact of nutritional and immune imbalances on the onset and progression of BPD \u003csup\u003e[\u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e]\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eBlood gas analysis serves as a critical component of neonatal respiratory management by directly measuring pulmonary ventilation and oxygenation functions. OI is indicative of an infant\u0026rsquo;s alveolar oxygenation efficiency. OI independently affects the severity of BPD, with a negative correlation to the disease\u0026rsquo;s severity, which corroborates previous studies \u003csup\u003e[\u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e]\u003c/sup\u003e. A-aDO2 combines the inhaled oxygen concentration with carbon dioxide and oxygen partial pressures, serving as an index of pulmonary ventilation and alveolar oxygenation ability \u003csup\u003e[\u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e39\u003c/span\u003e]\u003c/sup\u003e. Elevated A-aDO2 levels, suggesting hypercapnia and hypoxic states, reflect impaired pulmonary function and extensive lung injury, suggesting that infants consequently require higher oxygen concentration and respiratory support to maintain normoxic conditions. Such injury may lead to lung damage via oxidative stress pathways, ultimately causing the development and progression of BPD \u003csup\u003e[\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eWith the advent of the big data era and the progression of artificial intelligence technologies, predictive modeling has advanced significantly, utilizing machine learning and other sophisticated data analytics techniques to establish more precise models. Studies employing machine learning algorithms for the prediction and management of BPD have shown substantial advancements \u003csup\u003e[\u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e40\u003c/span\u003e]\u003c/sup\u003e. Nevertheless, there persists contention regarding the performance of machine learning models in predicting BPD, where they haven\u0026rsquo;t conclusively outperformed traditional LR models \u003csup\u003e[\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e, \u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e, \u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e]\u003c/sup\u003e. Our research, by constructing LR, RF, GBDT, and XGB models at various timepoints within the first postnatal week, identified that the LR and XGBoost models in particular perform well on days 1, 3, and 7 for early stratified prediction of infants at high risk for BPD. In contrast with former machine learning models, our models have individually assessed the contribution of risk factors to predictive efficacy at each time point. Hence, the inclusion of different variables at distinct time points tailored to BPD\u0026rsquo;s dynamic nature has achieved effective dynamic stratified prediction within the first week postnatal with considerable predictive performance. This translation into professional academic language suitable for an SCI journal publication should undergo peer review for terminological accuracy and adherence to publication standards.\u003c/p\u003e \u003cp\u003eThe dataset used to construct the models in this study was derived from a single-center, retrospective investigation with an extensive time span, which does not guarantee complete homogeneity of all indicators and presents a multitude of confounding factors that might result in bias. Future multicenter, prospective studies to build models may enhance the performance and predictive power of these models.\u003c/p\u003e \u003cp\u003eIn conclusion, in this study developed various types of machine learning predictive models at different time points within the first postnatal week, which serve as useful tools for early stratified prediction of BPD in clinical practice. These models aid clinicians in the early personalized intervention of high-risk groups, potentially reducing the incidence of BPD.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eAuthor contributions\u0026nbsp;\u003c/strong\u003eNing An: conceptualization, methodology, software, writing\u0026ndash;original draft. Jingwen Yang, Rong Zhang, Wen Han, Xuchen Zhou and Rong Yang: investigation, formal analysis, data curation. Yanping Zhu and Ting Zhao: writing\u0026mdash;review \u0026amp; editing. Mingxia Li: supervision, project administration, writing\u0026mdash;review \u0026amp; editing. All authors discussed, revised, and approved the fnal manuscript as submitted and agreed to be accountable for all aspects of the work.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding No.\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData availability\u003c/strong\u003e The datasets generated during and/or analyzed during the current study are available from the corresponding author on reasonable request.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConflict of interest\u003c/strong\u003e No financial or non-financial benefits have been received or will be received from any party related directly or indirectly to the subject of this article.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthical approval\u0026nbsp;\u003c/strong\u003eStudy approval was granted by the Ethics Committee of the First Affiliated Hospital of Xinjiang Medical University (Ethics approval number: K202212-12). Informed consent to participation has been obtained from their parents.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eCao Y, Jiang S, Sun J, et al. Assessment of Neonatal Intensive Care Unit Practices, Morbidity, and Mortality Among Very Preterm Infants in China [J]. JAMA Netw Open, 2021, 4(8): e2118904.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHoman TD, Nayak RP. Short- and Long-Term Complications of Bronchopulmonary Dysplasia [J]. Respiratory Care, 2021, 66(10): 1618\u0026ndash;1629.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHorbar JD, Greenberg LT, Buzas JS, et al. Trends in Mortality and Morbidities for Infants Born 24 to 28 Weeks in the US: 1997\u0026ndash;2021 [J]. Pediatrics, 2024, 153(1): e2023064153.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBell EF, Hintz SR, Hansen NI, et al. Mortality, In-Hospital Morbidity, Care Practices, and 2-Year Outcomes for Extremely Preterm Infants in the US, 2013\u0026ndash;2018 [J]. Jama, 2022, 327(3): 248\u0026ndash;263.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDankhara N, Holla I, Ramarao S, et al. Bronchopulmonary Dysplasia: Pathogenesis and Pathophysiology [J]. J Clin Med, 2023, 12(13): 4207.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGilfillan M, Bhandari A, Bhandari V. Diagnosis and management of bronchopulmonary dysplasia [J]. Bmj, 2021, 375: n1974.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWang X, Guo J, Wu YY, et al. Comparing the prognostic value of 3 diagnostic criteria of bronchopulmonary dysplasia in preterm infants[J]. Zhonghua Er Ke Za Zhi, 2024, 62(1):36\u0026ndash;42.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRomijn M, Dhiman P, Finken MJJ, et al. Prediction Models for Bronchopulmonary Dysplasia in Preterm Infants: A Systematic Review and Meta-Analysis [J]. J Pediatr, 2023, 258: 113370.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYang Q, Fan X, Cao X, et al. Reporting and risk of bias of prediction models based on machine learning methods in preterm birth: A systematic review [J]. Acta Obstet Gynecol Scand, 2023, 102(1): 7\u0026ndash;14.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJensen EA, Dysart K, Gantz MG, et al. The Diagnosis of Bronchopulmonary Dysplasia in Very Preterm Infants. An Evidence-based Approach [J]. Am J Respir Crit Care Med, 2019, 200(6): 751\u0026ndash;759.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eShah M, Jain D, Prasath S, et al. Artificial intelligence in bronchopulmonary dysplasia- current research and unexplored frontiers [J]. Pediatr Res, 2023, 93(2): 287\u0026ndash;290.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMcadams RM, Kaur R, Sun Y, et al. Predicting clinical outcomes using artificial intelligence and machine learning in neonatal intensive care units: a systematic review [J]. J Perinatol, 2022, 42(12): 1561\u0026ndash;1575.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBonadies L, Cavicchiolo ME, Priante E, et al. Prematurity and BPD: what general pediatricians should know [J]. Eur J Pediatr, 2023, 182(4): 1505\u0026ndash;1516.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLaughon MM, Langer JC, Bose CL, et al. Prediction of bronchopulmonary dysplasia by postnatal age in extremely premature infants [J]. Am J Respir Crit Care Med, 2011, 183(12): 1715\u0026ndash;1722.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMcgoldrick E, Stewart F, Parker R, et al. Antenatal corticosteroids for accelerating fetal lung maturation for women at risk of preterm birth [J]. Cochrane Database Syst Rev, 2020, 12(12): Cd004454.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhu J, Li S, Zhao Y, et al. The role of antenatal corticosteroids in twin pregnancy[J]. Front Pharmacol, 2023, 14:1072578.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePapagianis PC, Pillow JJ, Moss TJ. Bronchopulmonary dysplasia: Pathophysiology and potential anti-inflammatory therapies [J]. Paediatric Respiratory Reviews, 2019, 30: 34\u0026ndash;41.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGairabekova D, Van Rosmalen J, Duvekot JJ. Outcome of early-onset fetal growth restriction with or without abnormal umbilical artery Doppler flow [J]. Acta Obstet Gynecol Scand, 2021, 100(8): 1430\u0026ndash;1438.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGreenberg RG, Mcdonald SA, Laughon MM, et al. Online clinical tool to estimate risk of bronchopulmonary dysplasia in extremely preterm infants [J]. Arch Dis Child Fetal Neonatal Ed, 2022: 323573.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eValenzuela-Stutman D, Marshall G, Tapia JL, et al. Bronchopulmonary dysplasia: risk prediction models for very-low- birth-weight infants [J]. J Perinatol, 2019, 39(9): 1275\u0026ndash;1281.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eO'dwyer V, Burke G, Unterscheider J, et al. Defining the residual risk of adverse perinatal outcome in growth-restricted fetuses with normal umbilical artery blood flow[J]. Am J Obstet Gynecol, 2014, 211(4):420.e1-5.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKimble A, Robbins ME, Perez M. Pathogenesis of Bronchopulmonary Dysplasia: Role of Oxidative Stress from 'Omics' Studies [J]. Antioxidants (Basel), 2022, 11(12): 2380.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eShim SY, Yun JY, Cho SJ, et al. The Prediction of Bronchopulmonary Dysplasia in Very Low Birth Weight Infants through Clinical Indicators within 1 Hour of Delivery [J]. J Korean Med Sci, 2021, 36(11): e81.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJain VG, Willis KA, Jobe A, et al. Chorioamnionitis and neonatal outcomes [J]. Pediatr Res, 2022, 91(2): 289\u0026ndash;296.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePerrone S, Manti S, Buttarelli L, et al. Vascular Endothelial Growth Factor as Molecular Target for Bronchopulmonary Dysplasia Prevention in Very Low Birth Weight Infants [J]. Int J Mol Sci, 2023, 24(3): 2729.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVillamor-Martinez E, \u0026Aacute;lvarez-Fuente M, Ghazi AMT, et al. Association of Chorioamnionitis with Bronchopulmonary Dysplasia Among Preterm Infants: A Systematic Review, Meta-analysis, and Metaregression [J]. JAMA Netw Open, 2019, 2(11): e1914611.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhang R, Xu FL, Li WL, et al. Construction of early risk prediction models fr bronchopulmonary dysplasia in preterm infants [J]. Zhongguo Dang Dai Er Ke Za Zhi, 2021, 23(10): 994\u0026ndash;1001.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHwang JS, Rehan VK. Recent Advances in Bronchopulmonary Dysplasia: Pathophysiology, Prevention, and Treatment [J]. Lung, 2018, 196(2): 129\u0026ndash;138.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSun T, Yu HY, Yang M, et al. Risk of asthma in preterm infants with bronchopulmonary dysplasia: a systematic review and meta-analysis [J]. World J Pediatr, 2023, 19(6): 549\u0026ndash;556.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSchmidt AR, Ramamoorthy C. Bronchopulmonary dysplasia [J]. Pediatric Anesthesia, 2022, 32(2): 174\u0026ndash;180.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDobkin J, Mangalmurti NS. Immunomodulatory roles of red blood cells [J]. Curr Opin Hematol, 2022, 29(6): 306\u0026ndash;309.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYang Y, Li J, Mao J. Early diagnostic value of C-reactive protein as an inflammatory marker for moderate-to-severe bronchopulmonary dysplasia in premature infants with birth weight less than 1500 g [J]. International Immunopharmacology, 2022, 103: 108462.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJiang J, Mao Y, Wu J, et al. Relationship between hematological parameters and bronchopulmonary dysplasia in premature infants [J]. J Int Med Res, 2023, 51(7): 3000605231187802.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCakir U, Tayman C, Tugcu AU, et al. Role of Systemic Inflammatory Indices in the Prediction of Moderate to Severe Bronchopulmonary Dysplasia in Preterm Infants[J]. Arch Bronconeumol, 2023, 59(4):216\u0026ndash;22.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSati SK, Springer C, Kim R, et al. Platelet parameters as biomarker for bronchopulmonary dysplasia in very low birth weight neonates in the first two weeks of life [J]. Minerva Pediatr (Torino), 2023.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDai M, Sun Q. Prognostic and clinicopathological significance of prognostic nutritional index (PNI) in patients with oral cancer: a meta-analysis [J]. Aging (Albany NY), 2023, 15(5): 1615\u0026ndash;1627.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSaenz De Pipaon M, Nelin LD, Gehred A, et al. The role of nutritional interventions in the prevention and treatment of chronic lung disease of prematurity[J]. Pediatr Res, 2024.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChou FS, Leigh RM, Rao SS, et al. Oxygenation index in the first three weeks of life is a predictor of bronchopulmonary dysplasia grade in very preterm infants[J]. BMC Pediatr, 2023, 23(1):18.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eStickland MK, Lindinger MI, Olfert IM, et al. Pulmonary gas exchange and acid-base balance during exercise[J]. Compr Physiol, 2013, 3(2):693\u0026ndash;739.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKeles E, Bagci U. The past, current, and future of neonatal intensive care units with artificial intelligence: a systematic review [J]. NPJ Digit Med, 2023, 6(1): 220.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHe W, Zhang L, Feng R, et al. Risk factors and machine learning prediction models for bronchopulmonary dysplasia severity in the Chinese population [J]. World J Pediatr, 2023, 19(6): 568\u0026ndash;576.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKhurshid F, Coo H, Khalil A, et al. Comparison of Multivariable Logistic Regression and Machine Learning Models for Predicting Bronchopulmonary Dysplasia or Death in Very Preterm Infants [J]. Front Pediatr, 2021, 9: 759776.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Bronchopulmonary Dysplasia, Machine Learning, Dynamic Prediction, Preterm","lastPublishedDoi":"10.21203/rs.3.rs-4648257/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4648257/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eObjective\u003c/h2\u003e \u003cp\u003eTo investigate the independent risk factors for Bronchopulmonary Dysplasia (BPD) at different time points within the first week in extremely premature/very low birth weight infants and to construct an early stratification dynamic prediction model for BPD through machine learning, aiming to achieve dynamic prediction of BPD for the early identification of high-risk groups and preemptive prevention.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eA retrospective collection of clinical data was conducted on premature infants admitted to the Neonatology Department of the First Affiliated Hospital of Xinjiang Medical University from January 2017 to December 2022, with gestational age (GA)\u0026thinsp;\u0026lt;\u0026thinsp;32 weeks or birth weight (BW)\u0026thinsp;\u0026lt;\u0026thinsp;1500g. Eligible subjects were randomly divided into training and validation sets in a 7:3 ratio for model building and internal validation. Prospective clinical data from preterm infants admitted to six neonatal rescue centers in various districts of Xinjiang from January to October 2023 were independently collected to validate the practical application value of each model. Clinical parameters were collected, and study participants were divided into three groups: no BPD, mild BPD, and moderate to severe BPD (msBPD). Machine learning predictive models for BPD stratification employing logistic regression (LR), random forest (RF), XGBoost (XGB), and gradient boosting decision tree (GBDT) were constructed for postnatal days 1, 3, and 7. Comprehensive evaluation was performed to select the optimal model at each time point and proceed to external validation.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eThe study retrospectively gathered data from 554 preterm infants (286 no BPD, 212 mild, and 56 msBPD cases). Prospectively, 387 preterm infants (208 no BPD, 138 mild, and 41 msBPD cases). On ordinal logistic regression, GA, BW, prenatal steroids, interruption of umbilical blood flow, severe preeclampsia, FIO2, CRP, RBC, systemic inflammatory response index (SIRI), prognostic nutritional index, platelet mass index, alveolar-arterial oxygen difference, and oxygenation index were independent risk factors for BPD severity at different times after birth. After comprehensive evaluation, the LR and XGB models were identified as better BPD stratification prediction models for postnatal days 1, 3, and 7 (AUC\u0026thinsp;=\u0026thinsp;0.810,0.837 and 0.813 respectively).\u003c/p\u003e\u003ch2\u003eConclusion\u003c/h2\u003e \u003cp\u003eEarly stratification dynamic prediction machine learning models for BPD have been constructed for postnatal days 1, 3, and 7 in extremely premature/very low birth weight infants. These may serve as effective tools for the screening of high-risk BPD populations.\u003c/p\u003e","manuscriptTitle":"Construction and Application of Early Stratification Dynamic Prediction Model for Bronchopulmonary Dysplasia in Extremely Premature / Very Low Birth Weight Infants","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-07-22 21:05:25","doi":"10.21203/rs.3.rs-4648257/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"07805ae6-2b6b-4b3f-89e3-edf4e93ed51a","owner":[],"postedDate":"July 22nd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":34862268,"name":"Health sciences/Medical research"},{"id":34862269,"name":"Health sciences/Risk factors"}],"tags":[],"updatedAt":"2024-10-11T03:38:23+00:00","versionOfRecord":[],"versionCreatedAt":"2024-07-22 21:05:25","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4648257","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4648257","identity":"rs-4648257","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}