[A clinical analysis of neurobehavioral development within one year after birth in preterm infants with bronchopulmonary dysplasia]

A prediction model for short-term neurodevelopmental impairment in preterm infants with gestational age less than 32 weeks

Introduction

Early identification and intervention of neurodevelopmental impairment in preterm infants may significantly improve their outcomes. This study aimed to build a prediction model for short-term neurodevelopmental impairment in preterm infants using machine learning method.

Methods

Preterm infants with gestational age  < 32 weeks who were hospitalized in The Maternal and Child Health Hospital of Guangxi Zhuang Autonomous Region, and were followed-up to 18 months corrected age were included to build the prediction model. The training set and test set are divided according to 8:2 randomly by Microsoft Excel. We firstly established a logistic regression model to screen out the indicators that have a significant effect on predicting neurodevelopmental impairment. The normalized weights of each indicator were obtained by building a Support Vector Machine, in order to measure the importance of each predictor, then the dimension of the indicators was further reduced by principal component analysis methods. Both discrimination and calibration were assessed with a bootstrap of 505 resamples.

Results

In total, 387 eligible cases were collected, 78 were randomly selected for external validation. Multivariate logistic regression demonstrated that gestational age(p = 0.0004), extrauterine growth restriction (p = 0.0367), vaginal delivery (p = 0.0009), and hyperbilirubinemia (0.0015) were more important to predict the occurrence of neurodevelopmental impairment in preterm infants. The Support Vector Machine had an area under the curve of 0.9800 on the training set. The results of the model were exported based on 10-fold cross-validation. In addition, the area under the curve on the test set is 0.70. The external validation proves the reliability of the prediction model.

Conclusion

A support vector machine based on perinatal factors was developed to predict the occurrence of neurodevelopmental impairment in preterm infants with gestational age  < 32 weeks. The prediction model provides clinicians with an accurate and effective tool for the prevention and early intervention of neurodevelopmental impairment in this population.

[Clinical significance of amplitude-integrated electroencephalography in preterm infants with bronchopulmonary dysplasia]

OBJECTIVE

To study the changes and clinical significance of amplitude-integrated electroencephalography (aEEG) in preterm infants with bronchopulmonary dysplasia (BPD).

METHODS

A total of 156 preterm infants with a gestational age of ≤ 32+6 weeks who were diagnosed with BPD were enrolled as the BPD group, and 156 preterm infants without BPD who were hospitalized during the same period of time were enrolled as the control group. The aEEG scoring system for preterm infants was used to compare aEEG results between the two groups during hospitalization. A stratified analysis was conducted based on the examination time (at the corrected gestational age of ≤ 28+6 weeks, 29-30+6 weeks, 31-32+6 weeks, 33-34+6 weeks, 35-36+6 weeks, and 37-38+6 weeks).

RESULTS

Compared with the non-BPD group, the BPD group had a significantly lower total aEEG score at the corrected gestational age of 33-34+6 weeks (P < 0.001). The mild BPD group had a significantly lower total aEEG score than the non-BPD group at the corrected gestational age of 33-34+6 weeks (P < 0.05); the moderate BPD group had a significantly lower total aEEG score than the non-BPD group at the corrected gestational ages of 31-32+6 weeks, 33-34+6 weeks, and 35-36+6 weeks (P < 0.05); the severe BPD group had a significantly lower total aEEG score than the non-BPD group at all corrected gestational ages except ≤ 28+6 weeks and 29-30+6 weeks (P < 0.05).

CONCLUSIONS

Preterm infants with BPD (especially moderate to severe BPD) have a lower aEEG score than those without BPD, suggesting that their nervous system development may lag behind that of non-BPD preterm infants with the same gestational age. Therefore, early nervous system evaluation and intervention are necessary for preterm infants with BPD.