Invasive mechanical ventilation and biomarkers as predictors of bronchopulmonary dysplasia in preterm infants

Predictive value of serum MED1 and PGC-1α for bronchopulmonary dysplasia in preterm infants

OBJECTIVE

This study aimed to predict the bronchopulmonary dysplasia (BPD) in preterm infants with a gestational age(GA) < 32 weeks utilizing clinical data, serum mediator complex subunit 1 (MED1), and serum peroxisome proliferator-activated receptor gamma coactivator-1alpha (PGC-1α).

METHODS

This prospective observational study enrolled 70 preterm infants with GA < 32 weeks. The infants were categorized into two groups: non-BPD group(N = 35) and BPD group(N = 35), including 25 cases with mild BPD and 10 patients with moderate/severe subgroups. We performed multifactorial regression analysis to investigate the postnatal risk factors for BPD. Furthermore, we compared serum levels of biomarkers, including MED1 and PGC-1α, among infants with and without BPD at postnatal days 1, 7, 14, 28, and PMA 36 weeks. A logistic regression model was constructed to predict BPD's likelihood using clinical risk factors and serum biomarkers.

RESULTS

Serum levels of MED1 on the first postnatal day, PGC-1α on the 1st, 7th, and 28th days, and PMA at 36 weeks were significantly lower in the BPD group than in the non-BPD group (P < 0.05). Furthermore, the predictive model for BPD was created by combing serum levels of MED1 and PGC-1α on postnatal day 1 along with clinical risk factors such as frequent apnea, mechanical ventilation time > 7 d, and time to reach total enteral nutrition. Our predictive model had a high predictive accuracy(C statistics of 0.989) .

CONCLUSION

MED1and PGC-1α could potentially serve as valuable biomarkers, combined with clinical factors, to aid clinicians in the early diagnosis of BPD.

Predictors of Bronchopulmonary Dysplasia in Infants With Birth Weight Less Than 1500 g

Bronchopulmonary dysplasia (BPD) is a complication of preterm and low birth weight infants. The incidence of BPD has not decreased over the past 20 years. Complications of BPD include rehospitalization, chronic lung disease, cardiovascular disease, and impaired growth and development which will affect the patient's quality of life. There are unfortunately limited data available regarding BPD in Indonesia. This study is expected to be a reference in taking preventive measures to reduce mortality and morbidity in preterm and low birth infants. This study aims to determine predictors of BPD in infants with birth weight less than 1500 g. We conducted a retrospective cohort study that included 116 infants with birth weight <1500 g. Twenty-two (19%) infants had BPD with the highest proportion (63.6%) in the 28 to 31 weeks of gestational age. Multivariate analysis showed mechanical ventilation in more than first 2 days of life (P = .008; HR = 7.7), hematocrit <39% (P = .001; HR = 12), and hemodynamically significant patent ductus arteriosus (hsPDA; P = .041; HR = 3.5) were significant predictors of BPD in infants with birth weight <1500 g.

Duration of mechanical ventilation and clinical outcomes in very low birth weight infants: A single center 10-years cohort study

BACKGROUND

Despite the important role of MV in reducing mortality in very preterm infants, its use is often associated with complications. The study was aimed to determine the duration of mechanical ventilation (MV), which significantly increased the risk of adverse outcomes in very low birth weight (VLBW) infants.

METHODS

Data obtained from a prospectively created computer database were used in a retrospective cohort study. The database included information about 1980 VLBW infants <32 weeks of gestation who were cared for at the tertiary care center between January 2010 and December 2020.

RESULTS

Out of 1980 VLBW infants, 1086 (55%) were ventilated sometime during the hospital stay. 678 (62.43%) of ventilated babies survived until discharge. With ROC analysis, it was identified that MV duration of 60.5 hours had 79.3% sensitivity and 64.6% specificity for the prediction of BPD with the AUC of 0.784 (95% CI 0.733-0.827; p < 0.0001). The duration of MV above 60.5 hours was a significant risk factor for bronchopulmonary dysplasia (aOR 6.005, 95% CI 3.626-9.946), death (aOR 3.610, 95% CI 2.470-5.276), bronchopulmonary dysplasia/death (aOR 4.561, 95% CI 3.328-6.252), sepsis (aOR 1.634, 95% CI 1.168-2.286), necrotizing enterocolitis (aOR 2.606, 95% CI 1.364-4.980), and periventricular leukomalacia (aOR 2.191, 95% CI 1.241-3.867).

CONCLUSIONS

Duration of MV longer than 60.5 hours is an independent risk factor for adverse outcomes in VLBW infants. It is essential to increase and optimize efforts to avoid MV or extubate very preterm infants as soon as possible, before reaching the established threshold duration of invasive respiratory support.

Early severity prediction of BPD for premature infants from chest X-ray images using deep learning: A study at the 28th day of oxygen inhalation

BACKGROUND AND OBJECTIVE

Bronchopulmonary dysplasia is a common respiratory disease in premature infants. The severity is diagnosed at the 56th day after birth or discharge by analyzing the clinical indicators, which may cause the delay of the best treatment opportunity. Thus, we proposed a deep learning-based method using chest X-ray images of the 28th day of oxygen inhalation for the early severity prediction of bronchopulmonary dysplasia in clinic.

METHODS

We first adopted a two-step lung field extraction method by combining digital image processing and human-computer interaction to form the one-to-one corresponding image and label. The designed XSEG-Net model was then trained for segmenting the chest X-ray images, with the results being used for the analysis of heart development and clinical severity. Therein, Six-Point cardiothoracic ratio measurement algorithm based on corner detection was designed for the analysis of heart development; and the transfer learning of deep convolutional neural network models were used for the early prediction of clinical severities.

RESULTS

The dice and cross-entropy loss value of the training of XSEG-Net network reached 0.9794 and 0.0146. The dice, volumetric overlap error, relative volume difference, precision, and recall were used to evaluate the trained model in testing set with the result being 98.43 ± 0.39%, 0.49 ± 0.35%, 0.49 ± 0.35%, 98.67 ± 0.40%, and 98.20 ± 0.47%, respectively. The errors between the Six-Point cardiothoracic ratio measurement method and the gold standard were 0.0122 ± 0.0084. The deep convolutional neural network model based on VGGNet had the promising prediction performance, with the accuracy, precision, sensitivity, specificity, and F1 score reaching 95.58 ± 0.48%, 95.61 ± 0.55%, 95.67 ± 0.44%, 96.98 ± 0.42%, and 95.61±0.48%, respectively.

CONCLUSIONS

These experimental results of the proposed methods in lung field segmentation, cardiothoracic ratio measurement and clinic severity prediction were better than previous methods, which proved that this method had great potential for clinical application.