Dataset Information

Development and verification of a risk prediction model for bronchopulmonary dysplasia in very low birth weight infants.

ABSTRACT:

Background

To analyze the risk factors of bronchopulmonary dysplasia (BPD) of very low birth weight infants (VLBWIs), and to develop and verify a risk prediction model of BPD.

Methods

The data of 611 VLBWIs from the neonatal intensive care unit (NICU) of a tertiary grade A hospital in Suzhou from January 2017 to September 2019 were collected. The data was randomly divided into the modeling set (451 cases) and the validation set (160 cases). Binary logistic regression was used to analyze the data, and the model was examined by a receiver operating characteristic (ROC) curve. The grouped data was used to verify the sensitivity and specificity of the model.

Results

The study found that neonatal asphyxia, the positive rate of sputum culture, neonatal sepsis, neonatal respiratory distress syndrome (NRDS), blood transfusions (≥3), patent ductus arteriosus (PDA), the time of invasive mechanical ventilation, the duration of oxygen therapy, and the time of parenteral nutrition were the independent risk factors of BPD, while 1 min Apgar score was a protective factor. The model formula was Z=neonatal asphyxia * 1.229 + the positive rate of sputum culture * 1.265 + neonatal sepsis * 1.677 + NRDS * 1.848 + blood transfusions (≥3) * 1.455 + PDA * 1.835 - 1 min Apgar score * 0.25 + the time of invasive mechanical ventilation * 0.123 + the duration of oxygen therapy * 0.09 + the time of parenteral nutrition * 0.057 - 8.077. The area under the ROC curve of this model was 0.965 (95% CI: 0.946-0.983), with a sensitivity of 93.7% and a specificity of 91.3%. Verification of this prediction model showed a sensitivity of 92.9% and a specificity of 76%, demonstrating that the effects of this model were satisfactory.

Conclusions

The risk prediction model had a good predictive effect for the risk of BPD in VLBWIs, and can provide a reference for preventive treatment and nursing intervention.

SUBMITTER: Cai H

PROVIDER: S-EPMC8578781 | biostudies-literature | 2021 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Development and verification of a risk prediction model for bronchopulmonary dysplasia in very low birth weight infants.

Cai Huiwen H Jiang Ling L Liu Yongshu Y Shen Ting T Yang Zuming Z Wang Sannan S Ma Yuelan Y

Translational pediatrics 20211001 10

<h4>Background</h4>To analyze the risk factors of bronchopulmonary dysplasia (BPD) of very low birth weight infants (VLBWIs), and to develop and verify a risk prediction model of BPD.<h4>Methods</h4>The data of 611 VLBWIs from the neonatal intensive care unit (NICU) of a tertiary grade A hospital in Suzhou from January 2017 to September 2019 were collected. The data was randomly divided into the modeling set (451 cases) and the validation set (160 cases). Binary logistic regression was used to a ...[more]

PMID: 34765477

Similar Datasets

Project description:ObjectiveThis study aimed to determine the influence of fluid overload on bronchopulmonary dysplasia (BPD) in very low-birth-weight infants (VLBWI) within 1 week after birth.MethodsThis was a retrospective case control study conducted in the Jingzhou Central Hospital. The clinical data of VLBWI (with a birth weight [BW] < 1,500 g and 26 weeks ≤ gestational age [GA] < 32 weeks) who were admitted to the neonatal intensive care unit of this hospital from January 2016 to December 2021 were analyzed retrospectively. A total of 157 cases were enrolled and divided into a BPD group (n = 60) and a non-BPD group (n = 97) according to whether BPD was present. The general condition, fluid intake, and fluid overload of the two groups of neonates within 1 week after birth were compared. The logistic regression was used to assess the association between infant characteristics and BPD. The ROC curve was used to assess how well the 7 day cumulative fluid overload predicted BPD, and to identify an optimal cut off for prediction.ResultsThe comparison of the patients' general condition revealed that the neonates in the BPD group had a younger GA, lower BW, lower 5-min Apgar score, longer duration of invasive mechanical ventilation, and higher incidence of intrauterine infections and administration of surfactants (P < 0.05). The differences in the other indicators were not statistically significant between the two groups. The logistic regression analysis revealed that a younger GA, the presence of intrauterine infection, and a 7-day cumulative fluid overload were the risk factors for the development of BPD. A ROC curve was plotted with the 7-day cumulative fluid overload as the test variable and BPD as the status variable. The area under the curve was 0.75 (95% confidence interval: 0.664-0.826, P = 0.042), with a sensitivity of 76.7% and a specificity of 70.1%, corresponding to a 7-day cumulative fluid overload of 36.2%.ConclusionA younger GA, the presence of intrauterine infection, and a 7-day cumulative fluid overload were risk factors for the development of BPD. A 7 day cumulative fluid overload threshold of 36.2% best predicted the development of BPD.

Project description:IntroductionThe 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.MethodsWe 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.ResultsWe 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.ConclusionsWe 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.

Project description:Background and aimHuman milk has potential protective effects against bronchopulmonary dysplasia (BPD). However, studies on the association between the dose of human milk and BPD in China are limited. This study aimed to evaluate the dose-dependent effects of human milk on BPD and other neonatal morbidities in very low birth weight (VLBW) infants.MethodsThis retrospective cohort study of preterm infants was conducted on preterm infants of gestational age ≤ 34 weeks and birth weight < 1500 g admitted to the multicenter clinical research database for breastfeeding quality improvement in Jiangsu province. The multivariate analysis was performed to compare the effect outcomes of daily graded doses [1-24 mL/(kg · day), 25-49 mL/(kg · day), and ≥ 50 mL/(kg · day) of body weight] of human milk on neonatal outcomes throughout the first 4 weeks of life versus a reference group receiving no human milk. The models were adjusted for potential confounding variables.ResultsOf 964 included infants, 279 (28.9%) received exclusive preterm formula, 128 (13.3%) received 1-24 ml/(kg · day), 139 (14.4%) received 25-49 ml/(kg · day), and 418 (43.4%) received ≥50 ml/(kg · day) human milk for the first 4 weeks of life. Compared with infants receiving exclusive formula, those receiving the highest volume of human milk daily [≥50 mL/(kg · day)] had lower incidences of BPD [27.5% in ≥50 mL/(kg · day) vs 40.1% in 0 mL/(kg · day) human milk, P = 0.001)], moderate and severe BPD [8.9% in ≥50 mL/(kg · day) vs 16.1% in 0 mL/(kg · day), P = 0.004], necrotizing enterocolitis [NEC; 3.8% in ≥50 mL/(kg · day) vs 10.8% in 0 mL/(kg · day), P = 0.001], late-onset sepsis [LOS; 9.3% in ≥50 mL/(kg · day) vs 19.7% in 0 mL/(kg · day), P <0.01], and extrauterine growth retardation [EUGR; 38.5% in ≥50 mL/(kg · day) vs 57.6% in 0 mL/(kg · day), P <0.01)]. The logistic regression indicated that those receiving ≥50 ml/kg · day human milk had lower odds of BPD [adjusted odds ratio (AOR) 0.453; 95% confidence interval (CI): 0.309, 0.666], moderate and severe BPD (AOR 0.430; 95% CI: 0.249, 0.742), NEC (AOR 0.314; 95% CI: 0.162, 0. 607), LOS (AOR 0.420; 95% CI: 0.263, 0.673), and EUGR (AOR 0.685; 95% CI: 0.479, 0.979).ConclusionsA daily threshold amount of ≥50 ml/(kg · day) human milk in the first 4 weeks of life was associated with lower incidence of BPD as well as NEC, LOS, and EUGR in VLBW infants.Trial registrationClinicalTrials.gov Identifier: NCT03453502 . Registration date: March 5, 2018. This study was retrospectively registered.

Project description:BackgroundA meta-analysis was performed to study the effect of steroid intervention on the neurodevelopment of extremely low birth weight preterm infants complicated with bronchopulmonary dysplasia, and to provide a theoretical basis for clinical treatment.MethodsThe Wanfang database, Chinese Biomedical Literature database, VIP database, Baidu Academic, CNKI database, The Cochrane Library, Medline, Embase, and PubMed database were searched by computer from establishment to 2021. Randomized controlled trials on the effect of steroids on neurodevelopment in very low birth weight preterm infants with bronchial dysplasia published from January 10, 2007 were retrieved. The included literature was evaluated for bias risk, then analyzed using RevMan 5.3 software.ResultsA total of 9 studies were included, with a total of 2,453 patients. The funnel plot showed that the circles and the midline of some studies were basically symmetrical, and there was no bias in the publications. The conclusions obtained were relatively reliable. Cerebral palsy, neurodevelopmental indicators, and MRI findings of preterm infants were analyzed. The cognitive impairment of very low birth weight preterm infants complicated with bronchial dysplasia (RR =0.83, 95% CI: 0.72-0.96, P=0.01) in the treatment group was significantly different from that in the control group, while cerebral palsy (RR =0.99, 95% CI: 0.75-1.29, P=0.93), speech impairment (RR =0.75, 95% CI: 0.46-1.21, P=0.24), hearing loss requiring amplification (RR =0.60, 95% CI: 0.35-1.03, P=0.06), bilateral blindness RR =0.81, 95% CI: 0.52-1.24, P=0.32), severe intraventricular hemorrhage (IVH) (RR =0.71, 95% CI: 0.33-1.50, P=0.37), and cystic periventricular leukomalacia (RR =0.82, 95% CI: 0.43-1.57, P=0.56) had no significant differences compared with the control group.DiscussionIn this meta-analysis, we found that the use of steroids in very low birth weight preterm infants complicated with bronchial dysplasia had significant effects on cognition, but no significant effects on hearing, vision, or language function.

Dataset Information

Development and verification of a risk prediction model for bronchopulmonary dysplasia in very low birth weight infants.

Background

Methods

Results

Conclusions

Publications

Development and verification of a risk prediction model for bronchopulmonary dysplasia in very low birth weight infants.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets