Development and Validation of a Nomogram for Predicting Bronchopulmonary Dysplasia in Very-Low-Birth-Weight Infants

Improving early diagnosis of bronchopulmonary dysplasia

INTRODUCTION

Bronchopulmonary disease (BPD) is associated with long-term neurodevelopmental and cardiorespiratory complications, often requiring significant use of resources. To reduce this healthcare burden, it is essential that those at high risk of BPD are identified early so that strategies are introduced to prevent disease progression. Our aim was to discuss potential methods for improving early diagnosis in the first week after birth.

AREAS COVERED

A narrative review was undertaken. The search strategy involved searching PubMed, Embase and Cochrane databases from 1967 to 2024. The results of potential biomarkers and imaging modes are discussed. Furthermore, the value of scoring systems is explored.

EXPERT OPINION

BPD occurs as a result of disruption to pulmonary vascular and alveolar development, thus abnormal levels of factors regulating those processes are promising avenues to explore with regard to early detection of high-risk infants. Data from twin studies suggests genetic factors can be attributed to 82% of the observed difference in moderate to severe BPD, but large genome-wide studies have yielded conflicting results. Comparative studies are required to determine which biomarker or imaging mode may most accurately diagnose early BPD development. Models which include the most predictive factors should be evaluated going forward.

Machine learning predictive models for grading bronchopulmonary dysplasia: umbilical cord blood IL-6 as a biomarker

Objectives

This study aimed to analyze the predictive value of umbilical cord blood Interleukin-6 (UCB IL-6) for the severity-graded BPD and to establish machine learning (ML) predictive models in a Chinese population based on the 2019 NRN evidence-based guidelines.

Methods

In this retrospective analysis, we included infants born with gestational age <32 weeks, who underwent UCB IL-6 testing within 24 h of admission to our NICU between 2020 and 2022. We collected their medical information encompassing the maternal, perinatal, and early neonatal phases. Furthermore, we classified the grade of BPD according to the 2019 NRN evidence-based guidelines. The correlation between UCB IL-6 and the grades of BPD was analyzed. Univariate analysis and ordinal logistic regression were employed to identify risk factors, followed by the development of ML predictive models based on XGBoost, CatBoost, LightGBM, and Random Forest. The AUROC was used to evaluate the diagnostic value of each model. Besides, we generated feature importance distribution plots based on SHAP values to emphasize the significance of UCB IL-6 in the models.

Results

The study ultimately enrolled 414 preterm infants, with No BPD group (n = 309), Grade 1 BPD group (n = 73), and Grade 2-3 BPD group (n = 32). The levels of UCB IL-6 increased with the grades of BPD. UCB IL-6 demonstrated clinical significance in predicting various grades of BPD, particularly in distinguishing Grade 2-3 BPD patients, with an AUROC of 0.815 (95% CI: 0.753-0.877). All four ML models, XGBoost, CatBoost, LightGBM, and Random Forest, exhibited Micro-average AUROC values of 0.841, 0.870, 0.851, and 0.878, respectively. Notably, UCB IL-6 consistently appeared as the most prominent feature across the feature importance distribution plots in all four models.

Conclusion

UCB IL-6 significantly contributes to predicting severity-graded BPD, especially in grade 2-3 BPD. Through the development of four ML predictive models, we highlighted UCB IL-6's importance.

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.

Urinary NT-proBNP: A Useful Biomarker for the Diagnosis of Respiratory Distress in the Neonatal Population

OBJECTIVE

To determine the diagnostic accuracy of urinary NT-proBNP levels in the detection and classification of the severity of respiratory distress in neonates after birth.

METHODS

We compared the urinary NT- proBNP levels between the respiratory distress (RD) group and the control group on the 1st, 3rd, and 5th day of life (DOL).

RESULTS

The RD group (55 neonates) showed higher levels of NT-proBNP compared to the control group (63 neonates) on DOL1 (585.4 pg/ml vs 396.1 pg/ml (p=0.014)), DOL3 (805.1 pg/ml vs 271.9 pg/ml (p<0.001)) and DOL5 (409.7 pg/ml vs 94.4 pg/ml (p<0.001)). Especially, on DOL5, the area under the ROC curve was 0.884 and the NT-proBNP cut-off value (221.8 pg/ml) showed a sensitivity of 71% and specificity of 79%. The RD group was subclassified into neonates with mild (21 neonates), moderate (19 neonates), and severe (15 neonates) disease. NT-proBNP cut-off point of 668 pg/ml for DOL5 can safely differentiate neonates with severe disease from those with mild and moderate disease (combined subgroups) since the sensitivity was 80% and specificity was 77.5% for DOL5.

CONCLUSION

Urinary NT-proBNP levels are a useful biomarker in detecting clinical signs of respiratory distress in neonates that are born within the first week of life; they can also detect neonates that are vulnerable to severe forms of the disease.

Risk prediction of bronchopulmonary dysplasia in preterm infants by the nomogram model

Backgrounds and Aims

Bronchopulmonary dysplasia (BPD) has serious immediate and long-term sequelae as well as morbidity and mortality. The objective of this study is to develop a predictive model of BPD for premature infants using clinical maternal and neonatal parameters.

Methods

This single-center retrospective study enrolled 237 cases of premature infants with gestational age less than 32 weeks. The research collected demographic, clinical and laboratory parameters. Univariate logistic regression analysis was carried out to screen the potential risk factors of BPD. Multivariate and LASSO logistic regression analysis was performed to further select variables for the establishment of nomogram models. The discrimination of the model was assessed by C-index. The Hosmer-Lemeshow test was used to assess the calibration of the model.

Results

Multivariate analysis identified maternal age, delivery option, neonatal weight and age, invasive ventilation, and hemoglobin as risk predictors. LASSO analysis selected delivery option, neonatal weight and age, invasive ventilation, hemoglobin and albumin as the risk predictors. Both multivariate (AUC = 0.9051; HL P = 0.6920; C-index = 0.910) and LASSO (AUC = 0.8935; HL P = 0.7796; C-index = 0.899) - based nomograms exhibited ideal discrimination and calibration as confirmed by validation dataset.

Conclusions

The probability of BPD in a premature infant could be effectively predicted by the nomogram model based on the clinical maternal and neonatal parameters. However, the model required external validation using larger samples from multiple medical centers.

A nomogram for predicting lung-related diseases among construction workers in Wuhan, China

Objective

To develop a prediction nomogram for the risk of lung-related diseases (LRD) in construction workers.

Methods

Seven hundred and fifty-two construction workers were recruited. A self- designed questionnaire was performed to collected relevant information. Chest X-ray was taken to judge builders' lung health. The potential predictors subsets of the risk of LRD were screened by the least absolute shrinkage and selection operator regression and univariate analysis, and determined by using multivariate logistic regression analysis, then were used for developing a prediction nomogram for the risk of LRD. C-index, calibration curve, receiver operating characteristic curve, decision curve analysis (DCA) and clinical impact curve analysis (CICA) were used to evaluation the identification, calibration, predictive ability and clinical effectiveness of the nomogram.

Results

Five hundred and twenty-six construction workers were allocated to training group and 226 to validation group. The predictors included in the nomogram were symptoms, years of dust exposure, work in shifts and labor intensity. Our model showed good discrimination ability, with a bootstrap-corrected C index of 0.931 (95% CI = 0.906-0.956), and had well-fitted calibration curves. The area under the curve (AUC) of the nomogram were (95% CI = 0.906-0.956) and 0.945 (95% CI = 0.891-0.999) in the training and validation groups, respectively. The results of DCA and CICA indicated that the nomogram may have clinical usefulness.

Conclusion

We established and validated a novel nomogram that can provide individual prediction of LRD for construction workers. This practical prediction model may help occupational physicians in decision making and design of occupational health examination.

Lung ultrasound score has better diagnostic ability than NT-proBNP to predict moderate-severe bronchopulmonary dysplasia

The N-terminal end of B-type natriuretic peptide (NT-proBNP) and lung ultrasound (LUS) score have been proven to be adequate early biomarkers of bronchopulmonary dysplasia (BPD) in preterm infants. Our aim was to study if the predictive capacity of each one is increased by analyzing them together. We included infants born before 32 weeks with NT-proBNP and LUS scores on the first day of life (DOL) and on the 3rd, 7th, and 14th DOL and compared the diagnostic ability for moderate-severe BPD (msBPD) of each biomarker and in combination. We also compared them with a multivariate model of msBPD using only clinical variables. The sample size was 133 patients, and twenty-seven (20%) developed msBPD. The LUS score on the 7th DOL had better performance than NT-proBNP at the same moment: area under the receiver operating characteristic curve (AUC) 0.83 (0.75-0.89) versus 0.66 (0.56-0.75), p = 0.003, without differences in the rest of the times studied. These values did not increase when using the combination of both. A multivariate regression model that included only clinical variables (birth weight and invasive mechanical ventilation (IMV) at the 7th DOL) predicted msBPD with the same AUC as after the addition of any of these biomarkers, neither together.

CONCLUSION

The LUS score is a better predictor of msBPD on the 7th DOL than NT-proBNP in preterm infants born before 32 weeks, although they have similar diagnostic accuracy on the 1st, 3rd, and 14th DOL. Neither of them, nor together, have a better AUC for msBPD than a clinical model with birthweight and the need for IMV at the 7th DOL.

WHAT IS KNOWN

• NT-proBNP and LUS score are early predictors of moderate-severe bronchopulmonary dysplasia (msBPD).

WHAT IS NEW

• The combination of both NT-proBNP and LUS score does not increase the predictive ability of each separately.

Development and Validation of a Nomogram for Predicting the Risk of Bell's Stage II/III Necrotizing Enterocolitis in Neonates Compared to Bell's Stage I

BACKGROUND

Patients with Bell's Stage II/III necrotizing enterocolitis (NEC) may have more severe presentations, higher rates of death, and more long-term complications than those with Bell's Stage I NEC, so the purpose of this article was to construct a nomogram model to distinguish Bell's stage II/III NEC early from Bell's Stage I NEC, which is critical in the clinical management of NEC.

PATIENTS AND METHODS

A total of 730 NEC newborns diagnosed from January 2015 to January 2021 were retrospectively studied. They were randomly divided into training and validation groups at the ratio of 7:3. A nomogram model for predicting NEC was developed based on all the independent risk factors by multivariate regression analysis. The model's performance was mainly evaluated through three aspects: the area under the curve (AUC) to verify discrimination, the Hosmer-Lemeshow test and calibration curve to validate the consistency, and decision curve analysis (DCA) to determine the clinical effectiveness.

RESULTS

Predictors included in the prediction model were gestational age (GA), birth weight (BW), asphyxia, septicemia, hypoglycemia, and patent ductus arteriosus (PDA). This nomogram model containing the above-mentioned six risk factors had good discrimination ability in both groups, and the AUCs were 0.853 (95% CI, 0.82-0.89) and 0.846 (95% CI, 0.79-0.90), respectively. The calibration curve and DCA confirmed that the nomogram had good consistency and clinical usefulness.

CONCLUSIONS

This individual prediction nomogram based on GA, BW, asphyxia, septicemia, hypoglycemia, and PDA served as a useful tool to risk-stratify patients with NEC, and can help neonatologists early distinguish Bell's stage II/III NEC early from Bell's Stage I NEC.

Utility of umbilical cord blood 25-hydroxyvitamin D levels for predicting bronchopulmonary dysplasia in preterm infants with very low and extremely low birth weight

BACKGROUND AND OBJECTIVE

There remains controversy regarding vitamin D deficiency and bronchopulmonary dysplasia (BPD) in very low birth weight (VLBW) and extremely low birth weight (ELBW) preterm infants. This study aimed to determine the prevalence of vitamin D deficiency assessed by umbilical cord blood 25-hydroxyvitamin D [25(OH)D] in preterm infants in northeast China and to evaluate the ability and optimal threshold of 25(OH)D for predicting BPD.

METHODS

The clinical data of VLBW and ELBW preterm infants with known cord-blood 25(OH)D levels were analyzed retrospectively. Infants were divided into groups based on their cord-blood 25(OH)D levels and BPD diagnosis. Logistic regression was performed to assess the risk factors for BPD and a nomogram was established. Receiver operating characteristic (ROC) curve analysis was used to evaluate the optimal threshold of cord-blood 25(OH)D concentration for predicting BPD.

RESULTS

A total of 267 preterm infants were included, of which 225 (84.3%) exhibited vitamin D deficiency and 134 (50.2%) were diagnosed with BPD. The incidence of BPD was lower in the group with a 25(OH)D level of >20 ng/ml than in the other groups (P = 0.024). Infants with BPD had lower cord-blood 25(OH)D levels than those without BPD (11.6 vs. 13.6 ng/ml, P = 0.016). The multivariate logistic regression model revealed that 25(OH)D levels (odds ratio [OR] = 0.933, 95% confidence interval [95% CI]: 0.891-0.977), gestational age (OR = 0.561, 95% CI: 0.425-0.740), respiratory distress syndrome (OR = 2.989, 95% CI: 1.455-6.142), and pneumonia (OR = 2.546, 95% CI: 1.398-4.639) were independent risk factors for BPD. A predictive nomogram containing these four risk factors was established, which had a C-index of 0.814. ROC curve analysis revealed that the optimal cutoff value of 25(OH)D for predicting BPD was 15.7 ng/ml (area under the curve = 0.585, 95% CI: 0.523-0.645, P = 0.016), with a sensitivity of 75.4% and a specificity of 42.9%.

CONCLUSIONS

A cord-blood 25(OH)D level of <15.7 ng/ml was predictively valuable for the development of BPD. The nomogram established in this study can help pediatricians predict the risk of BPD more effectively and easily.

The Intertemporal Role of Respiratory Support in Improving Neonatal Outcomes: A Narrative Review

Defining improvements in healthcare can be challenging due to the need to assess multiple outcomes and measures. In neonates, although progress in respiratory support has been a key factor in improving survival, the same degree of improvement has not been documented in certain outcomes, such as bronchopulmonary dysplasia. By exploring the evolution of neonatal respiratory care over the last 60 years, this review highlights not only the scientific advances that occurred with the application of invasive mechanical ventilation but also the weakness of the existing knowledge. The contributing role of non-invasive ventilation and less-invasive surfactant administration methods as well as of certain pharmacological therapies is also discussed. Moreover, we analyze the cost-benefit of neonatal care-respiratory support and present future challenges and perspectives.

Development of a Nomogram for Moderate-to-Severe Bronchopulmonary Dysplasia or Death: Role of N-Terminal Pro-brain Natriuretic Peptide as a Biomarker

Objectives: This study aimed to explore the clinical value of N-terminal pro-brain natriuretic peptide (NT-proBNP) in predicting moderate-to-severe bronchopulmonary dysplasia (BPD)/death, and to establish an effective clinical predictive nomogram. Methods: We retrospectively analyzed very low birth weight infants (VLBWs) with gestational age ≤ 32 weeks. The NT-proBNP values were determined on the 1st, 3rd, 7th, 14th, 21st, and 28th days after birth. The correlation between NT-proBNP level and moderate-to-severe BPD/death was evaluated. Receiver operating characteristic (ROC) curve analysis was used to evaluate the prediction ability. Then, we used multivariable logistic regression to build the prediction model and nomogram, and calibration of the model was assessed by calibration curve. Results: In total, 556 VLBWs were involved, among whom 229 developed BPD (mild: n = 109; moderate: n = 68; severe: n = 52) and 18 died. The NT-proBNP level in the moderate-to-severe BPD/death group was significantly higher than that in the no-to-mild BPD group from the 3rd to 28th day (P < 0.001). When the natural logarithm of the serum NT-ProBNP level increased by 1 unit at day 7 (±2 days) of life, the risk of moderate and severe BPD/death was the highest (OR = 3.753; 95% CI: 2.984~4.720), and ROC analysis identified an optimal cutoff point of 3360 ng/L (sensitivity: 80.0%; specificity: 86.2%; AUC: 0.861). After adjusting for confounding factors, the level of NT-proBNP at day 7 (±2 days) of life still had important predictive value for the development of moderate-to-severe BPD/death, significantly improving the predictive ability of the model. Conclusion: The level of NT-proBNP at day 7 (±2 days) of life can be used as an early promising biomarker for VLBWs to develop moderate-to-severe BPD/death. We constructed an early predictive nomogram to help clinicians identify high-risk populations.

Association Between NT-proBNP and Prolonged Length of Stay in Hospital Among Preterm Infants Born at 28-31 Weeks' Gestation

OBJECTIVE

In the early life of preterm infants, the relationship between heart function and length of hospitalization is unclear. This study aims to examine the association between serum NT-proBNP level on the 7th day (NT-proBNP7) after birth and length of hospitalization among preterm infants.

METHODS

A retrospective cohort study was conducted. Patients included 709 preterm infants born at 28-31 weeks' gestational age (GA) admitted to the NICU of the First Affiliated Hospital of Zhengzhou University between December 20, 2016, to April 31, 2021. Main outcome: Late discharge (postmenstrual age at discharge was in the fourth quartile (highest) among infants born at the same GA). Exposure factor: NT-proBNP7.

RESULTS

We observed increased prevalence ratios for late discharge among the tertile of logarithm of NT-proBNP7 level (LnNT-proBNP7) which was positive. Compared with the lowest tertile, infants in the highest tertile of LnNT-proBNP7 had an 8.4-fold increased probability of late discharge, and the results were consistent for the subgroups. Next, a non-linear (S-shaped) relationship between LnNT-proBNP7 and late discharge was observed, whose turning points were 7.5 and 9. The effect sizes and the confidence intervals on the left of the first turning point, between two turning points and on the right of the second turning point, were 0.6 (95% CI, 0.2-1.6), 5.0 (95% CI, 2.4-10.6), and 1.1 (95% CI, 0.2-6.1), respectively. In addition, the prevalence of BPD, NEC, nosocomial infection, or any of them was highest in the group of LnNT-proBNP7 ≥ 9, lowest in the group of LnNT-proBNP7 < 7.5.

CONCLUSION

Higher NT-proBNP7 levels were associated with longer hospitalization. The relationship between LnNT-proBNP7 and late discharge was S-shaped. LnNT-proBNP7 was positively related with late discharge when LnNT-proBNP7 was between 7.5 and 9.