Prediction Models for Bronchopulmonary Dysplasia in Preterm Infants: A Systematic Review

Prediction of bronchopulmonary dysplasia in very preterm infants: competitive risk model nomogram

Objective

To develop predictive clinical models of bronchopulmonary dysplasia (BPD) through competing risk analysis.

Methods

Retrospective observational cohort study, including preterm newborns ≤32 weeks gestational age, conducted between January 1, 2013 and September 30, 2022 in a third-level Neonatal Intensive Care Unit in Spain. A prediction study was carried out using competing risk models, where the event of interest was BPD and the competing event was death. A multivariate competing risk model was developed separately for each postnatal day (days 1, 3, 7 and 14). Nomograms to predict BPD risk were developed from the coefficients of the final models and internally validated.

Results

A total of 306 patients were included in the study, of which 73 (23.9%) developed BPD and 29 (9.5%) died. On day 1, the model with the greatest predictive capacity was that including birth weight, days since rupture of membranes, and surfactant requirement (area under the receiver operating characteristic (ROC) curve (AUC), 0.896; 95% CI, 0.792-0.999). On day 3, the final predictive model was based on the variables birth weight, surfactant requirement, and Fraction of Inspired Oxygen (FiO2) (AUC, 0.891; 95% CI, 0.792-0.989).

Conclusions

Competing risk analysis allowed accurate prediction of BPD, avoiding the potential bias resulting from the exclusion of deceased newborns or the use of combined outcomes. The resulting models are based on clinical variables measured at bedside during the first 3 days of life, can be easily implemented in clinical practice, and can enable earlier identification of patients at high risk of BPD.

A clinical informatics approach to bronchopulmonary dysplasia: current barriers and future possibilities

Bronchopulmonary dysplasia (BPD) is a complex, multifactorial lung disease affecting preterm neonates that can result in long-term pulmonary and non-pulmonary complications. Current therapies mainly focus on symptom management after the development of BPD, indicating a need for innovative approaches to predict and identify neonates who would benefit most from targeted or earlier interventions. Clinical informatics, a subfield of biomedical informatics, is transforming healthcare by integrating computational methods with patient data to improve patient outcomes. The application of clinical informatics to develop and enhance clinical therapies for BPD presents opportunities by leveraging electronic health record data, applying machine learning algorithms, and implementing clinical decision support systems. This review highlights the current barriers and the future potential of clinical informatics in identifying clinically relevant BPD phenotypes and developing clinical decision support tools to improve the management of extremely preterm neonates developing or with established BPD. However, the full potential of clinical informatics in advancing our understanding of BPD with the goal of improving patient outcomes cannot be achieved unless we address current challenges such as data collection, storage, privacy, and inherent data bias.

Combined gestational age and serum fucose for early prediction of risk for bronchopulmonary dysplasia in premature infants

OBJECTIVE

As the predominant complication in preterm infants, Bronchopulmonary Dysplasia (BPD) necessitates accurate identification of infants at risk and expedited therapeutic interventions for an improved prognosis. This study evaluates the potential of Monosaccharide Composite (MC) enriched with environmental information from circulating glycans as a diagnostic biomarker for early-onset BPD, and, concurrently, appraises BPD risk in premature neonates.

MATERIALS AND METHODS

The study incorporated 234 neonates of ≤32 weeks gestational age. Clinical data and serum samples, collected one week post-birth, were meticulously assessed. The quantification of serum-free monosaccharides and their degraded counterparts was accomplished via High-performance Liquid Chromatography (HPLC). Logistic regression analysis facilitated the construction of models for early BPD diagnosis. The diagnostic potential of various monosaccharides for BPD was determined using Receiver Operating Characteristic (ROC) curves, integrating clinical data for enhanced diagnostic precision, and evaluated by the Area Under the Curve (AUC).

RESULTS

Among the 234 neonates deemed eligible, BPD development was noted in 68 (29.06%), with 70.59% mild (48/68) and 29.41% moderate-severe (20/68) cases. Multivariate analysis delineated several significant risk factors for BPD, including gestational age, birth weight, duration of both invasive mechanical and non-invasive ventilation, Patent Ductus Arteriosus (PDA), pregnancy-induced hypertension, and concentrations of two free monosaccharides (Glc-F and Man-F) and five degraded monosaccharides (Fuc-D, GalN-D, Glc-D, and Man-D). Notably, the concentrations of Glc-D and Fuc-D in the moderate-to-severe BPD group were significantly diminished relative to the mild BPD group. A potent predictive capability for BPD development was exhibited by the conjunction of gestational age and Fuc-D, with an AUC of 0.96.

CONCLUSION

A predictive model harnessing the power of gestational age and Fuc-D demonstrates promising efficacy in foretelling BPD development with high sensitivity (95.0%) and specificity (94.81%), potentially enabling timely intervention and improved neonatal outcomes.

Variables related to bronchopulmonary dysplasia severity: a Six-Year retrospective study

OBJECTIVES

This was a retrospective observational study conducted in a tertiary neonatal intensive care unit, in order to investigate factors which influenced the severity of bronchopulmonary dysplasia under NICHD new classification.

METHODS

Six years of clinical data with different grades of bronchopulmonary dysplasia patients were collected and analyzed, bivariate ordinal logistic regression model and multivariable ordinal logistic regression model were used with sensitivity analyses.

RESULTS

We identified seven variables were associated with the severity of BPD via a bivariate ordinal logistic regression model, including the level of referral hospital (OR 0.273；95% CI 0.117, 0.636), method of caffeine administration (OR 00.418；95% CI 0.177, 0.991), more than two occurrences of reintubation (OR 4.925；95% CI 1.878, 12.915), CPAP reapplication (OR 2.255；95% CI 1.059, 4.802), presence of positive sputum cultures (OR 2.574；95% CI 1.200, 5.519), the cumulative duration of invasive ventilation (OR 1.047；95% CI 1.017, 1.078), and postmenstrual age at the discontinuation of oxygen supplementation (OR 1.190；95% CI 1.027, 1.38). These seven variables were further analyzed via all multivariable ordinal logistic regression models, and we found that tertiary hospital birth and early administration of caffeine could reduce the severity of BPD by approximately 70% (OR 0.263；95% CI 0.090, 0.770) and 60% (OR 0.371；95% CI 0.138, 0.995), respectively. In contrast, multiple reintubations were related to higher BPD severity with an OR of 3.358 (95% CI 1.002, 11.252).

CONCLUSION

Improving perinatal care in level II hospitals, standardized caffeine administration, and optimized extubation strategy could potentially decrease the severity of BPD.

An Early Prediction Model for Estimating Bronchopulmonary Dysplasia in Preterm Infants

INTRODUCTION

Accurate assessment of the risk for bronchopulmonary dysplasia (BPD) is critical to determine the prognosis and identify infants who will benefit from preventive therapies. Clinical prediction models can support the identification of high-risk patients. In this study, we investigated the potential risk factors for BPD and compared machine learning models for predicting the outcome of BPD/death on days 1, 7, 14, and 28 in preterm infants. We also developed a local BPD estimator.

METHODS

This study involved 124 infants. We evaluated the composite outcome of BPD/death at a postmenstrual age of 36 weeks and identified risk factors that would improve BPD/death prediction. SPSS for Windows Version 11.5 and Weka 3.9 software were used for the data analysis.

RESULTS

To evaluate the combined effect of all variables, all risk factors were taken into consideration. Gestational age, birth weight, mode of respiratory support, intraventricular hemorrhage, necrotizing enterocolitis, surfactant requirement, and late-onset sepsis were risk factors on postnatal days 7, 14, and 28. In a comparison of four different time points (postnatal days 1, 7, 14, and 28), the day 7 model provided the best prediction. According to this model, when a patient was diagnosed with BPD/death, the accuracy rate was 89.5%.

CONCLUSION

The postnatal day 7 model was the best predictor of BPD or death. Future validation studies will help identify infants who may benefit from preventive therapies and develop individualized care.

Two-stage learning-based prediction of bronchopulmonary dysplasia in very low birth weight infants: a nationwide cohort study

Introduction

The aim of this study is to develop an enhanced machine learning-based prediction models for bronchopulmonary dysplasia (BPD) and its severity through a two-stage approach integrated with the duration of respiratory support (RSd) using prenatal and early postnatal variables from a nationwide very low birth weight (VLBW) infant cohort.

Methods

We included 16,384 VLBW infants admitted to the neonatal intensive care unit (NICU) of the Korean Neonatal Network (KNN), a nationwide VLBW infant registry (2013-2020). Overall, 45 prenatal and early perinatal clinical variables were selected. A multilayer perceptron (MLP)-based network analysis, which was recently introduced to predict diseases in preterm infants, was used for modeling and a stepwise approach. Additionally, we applied a complementary MLP network and established new BPD prediction models (PMbpd). The performances of the models were compared using the area under the receiver operating characteristic curve (AUROC) values. The Shapley method was used to determine the contribution of each variable.

Results

We included 11,177 VLBW infants (3,724 without BPD (BPD 0), 3,383 with mild BPD (BPD 1), 1,375 with moderate BPD (BPD 2), and 2,695 with severe BPD (BPD 3) cases). Compared to conventional machine learning (ML) models, our PMbpd and two-stage PMbpd with RSd (TS-PMbpd) model outperformed both binary (0 vs. 1,2,3; 0,1 vs. 2,3; 0,1,2 vs. 3) and each severity (0 vs. 1 vs. 2 vs. 3) prediction (AUROC = 0.895 and 0.897, 0.824 and 0.825, 0.828 and 0.823, 0.783, and 0.786, respectively). GA, birth weight, and patent ductus arteriosus (PDA) treatment were significant variables for the occurrence of BPD. Birth weight, low blood pressure, and intraventricular hemorrhage were significant for BPD ≥2, birth weight, low blood pressure, and PDA ligation for BPD ≥3. GA, birth weight, and pulmonary hypertension were the principal variables that predicted BPD severity in VLBW infants.

Conclusions

We developed a new two-stage ML model reflecting crucial BPD indicators (RSd) and found significant clinical variables for the early prediction of BPD and its severity with high predictive accuracy. Our model can be used as an adjunctive predictive model in the practical NICU field.

A prediction nomogram for moderate-to-severe bronchopulmonary dysplasia in preterm infants < 32 weeks of gestation: A multicenter retrospective study

Background

Moderate-to-severe bronchopulmonary dysplasia (msBPD) is a serious complication in preterm infants. We aimed to develop a dynamic nomogram for early prediction of msBPD using perinatal factors in preterm infants born at <32 weeks' gestation.

Methods

This multicenter retrospective study conducted at three hospitals in China between January 2017 and December 2021 included data on preterm infants with gestational age (GA) < 32 weeks. All infants were randomly divided into training and validation cohorts (3:1 ratio). Variables were selected by Lasso regression. Multivariate logistic regression was used to build a dynamic nomogram to predict msBPD. The discrimination was verified by receiver operating characteristic curves. Hosmer-Lemeshow test and decision curve analysis (DCA) were used for evaluating calibration and clinical applicability.

Results

A total of 2,067 preterm infants. GA, Apgar 5-min score, small for gestational age (SGA), early onset sepsis, and duration of invasive ventilation were predictors for msBPD by Lasso regression. The area under the curve was 0.894 (95% CI 0.869-0.919) and 0.893 (95% CI 0.855-0.931) in training and validation cohorts. The Hosmer-Lemeshow test calculated P value of 0.059 showing a good fit of the nomogram. The DCA demonstrated significantly clinical benefit of the model in both cohorts. A dynamic nomogram predicting msBPD by perinatal days within postnatal day 7 is available at https://sdxxbxzz.shinyapps.io/BPDpredict/.

Conclusion

We assessed the perinatal predictors of msBPD in preterm infants with GA < 32 weeks and built a dynamic nomogram for early risk prediction, providing clinicians a visual tool for early identification of msBPD.

Development of a peripheral blood transcriptomic gene signature to predict bronchopulmonary dysplasia

Bronchopulmonary dysplasia (BPD) is the most common lung disease of extreme prematurity, yet mechanisms that associate with or identify neonates with increased susceptibility for BPD are largely unknown. Combining artificial intelligence with gene expression data is a novel approach that may assist in better understanding mechanisms underpinning chronic lung disease and in stratifying patients at greater risk for BPD. The objective of this study is to develop an early peripheral blood transcriptomic signature that can predict preterm neonates at risk for developing BPD. Secondary analysis of whole blood microarray data from 97 very low birth weight neonates on day of life 5 was performed. BPD was defined as positive pressure ventilation or oxygen requirement at 28 days of age. Participants were randomly assigned to a training (70%) and testing cohort (30%). Four gene-centric machine learning models were built, and their discriminatory abilities were compared with gestational age or birth weight. This study adheres to the transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD) statement. Neonates with BPD (n = 62 subjects) exhibited a lower median gestational age (26.0 wk vs. 30.0 wk, P < 0.01) and birth weight (800 g vs. 1,280 g, P < 0.01) compared with non-BPD neonates. From an initial pool (33,252 genes/patient), 4,523 genes exhibited a false discovery rate (FDR) <1%. The area under the receiver operating characteristic curve (AUC) for predicting BPD utilizing gestational age or birth weight was 87.8% and 87.2%, respectively. The machine learning models, using a combination of five genes, revealed AUCs ranging between 85.8% and 96.1%. Pathways integral to T cell development and differentiation were associated with BPD. A derived five-gene whole blood signature can accurately predict BPD in the first week of life.