Jo HS, et al. J Korean Med Sci. 2015 Oct;30(Suppl 1):S81-S87. https://doi.org/10.3346/jkms.2015.30.S1.S81

Kim JK, et al. Ann Dermatol. 2011 Sep;23(Suppl 1):S127-S130. http://dx.doi.org/10.5021/ad.2011.23.S1.S127

Respiratory distress syndrome (RDS) among preterm infants is typically due to a quantitative deficiency of pulmonary surfactant. Aside from the degree of prematurity, diverse environmental and genetic factors can affect the development of RDS. The variance of the risk of RDS in various races/ethnicities or monozygotic/dizygotic twins has suggested genetic influences on this disorder. So far, several specific mutations in genes encoding surfactant-associated molecules have confirmed this. Specific genetic variants contributing to the regulation of pulmonary development, its structure and function, or the inflammatory response could be candidate risk factors for the development of RDS. This review summarizes the background that suggests the genetic predisposition of RDS, the identified mutations, and candidate genetic polymorphisms of pulmonary surfactant proteins associated with RDS.

Cho KH, et al. J Korean Med Sci. 2021 Nov;36(47):e320. https://doi.org/10.3346/jkms.2021.36.e320

Introduction: Preterm birth is a leading cause of infant mortality and morbidity. Despite the improvement in the overall mortality in premature infants, the intact survival of these infants remains a significant challenge. Screening the physical growth of infants is fundamental to potentially reducing the escalation of this disorder. Recently, machine learning models have been used to predict the growth restrictions of infants; however, they frequently rely on conventional risk factors and cross-sectional data and do not leverage the longitudinal database associated with medical data from laboratory tests.Methods: This study aimed to present an automated interpretable ML-based approach for the prediction and classification of short-term growth outcomes in preterm infants. We prepared four datasets based on weight and length including weight baseline, length baseline, weight follow-up, and length follow-up. The CHA Bundang Medical Center Neonatal Intensive Care Unit dataset was classified using two well-known supervised machine learning algorithms, namely support vector machine (SVM) and logistic regression (LR). A five-fold cross-validation, and several performance measures, including accuracy, precision, recall and F1-score were used to compare classifier performances. We further illustrated the models’ trustworthiness using calibration and cumulative curves. The visualized global interpretations using Shapley additive explanation (SHAP) is provided for analyzing variables’ contribution to final prediction.Results: Based on the experimental results with area under the curve, the discrimination ability of the SVM algorithm was found to better than that of the LR model on three of the four datasets with 81%, 76% and 72% in weight follow-up, length baseline and length follow-up dataset respectively. The LR classifier achieved a better ROC score only on the weight baseline dataset with 83%. The global interpretability results revealed that pregnancy-induced hypertension, gestational age, twin birth, birth weight, antenatal corticosteroid use, premature rupture of membranes, sex, and birth length were consistently ranked as important variables in both the baseline and follow-up datasets.Discussion: The application of machine learning models to the early detection and automated classification of short-term growth outcomes in preterm infants achieved high accuracy and may provide an efficient framework for clinical decision systems enabling more effective monitoring and facilitating timely intervention.

The aim of this study was to evaluate the results of sleep-wake cycle monitoring using amplitude-integrated EEG (aEEG) and neuroimaging in newborn infants with a possible perinatal hypoxic insult, investigate the correlation between the findings, and determine the relevance of the findings to reasonably predict neurological outcome. aEEG was recorded among newborn infants suspected of perinatal asphyxia between November, 2014 and June, 2015 in one neonatal intensive care unit facility. Brain imaging with serial ultrasonography and MRI when available were performed, and the infants were divided into two groups according to findings and potential neurological outcome: Group I (favorable findings) and Group II (severe findings such as high grade intraventricular hemorrhage, cerebral infarction or white matter injury). Established sleep-wake cycle times after birth was compared between the two groups. Among 107 newborn infants, 85 subjects were classified as Group I and the remaining 22 subjects as Group II. The total number of aEEG sessions was 207 and recording time was 2,796 h with a mean of 14.43 ± 13.40 h per study. Estimated times of cyclicity were earlier in Group I (113.34 h, 95 % CI 82.31–144.37) as compared to Group II (504.39 h, 95 % CI 319.91–688.88; p < 0.001). Delayed cyclicity on aEEG has a strong correlation with unfavorable brain neuroimages in newborns with possible perinatal asphyxia. If sleep-wake cycles do not appear during initial period after birth, follow-up brain imaging studies are recommended. Retrospectively registered Registration number: BD 2015–148 Name of registry: amplitude integrated EEG in neonate Date of registration: September 9, 2015