Ji Yoo Kim

The impact of metabolic acidosis on short-term outcomes and mortality in very low birth weight infants (VLBWIs) has not been well studied. To investigate the potential association between metabolic acidosis and the clinical outcomes of VLBWIs in South Korea. Between 2013 and 2019, data were collected from the Korean Neonatal Network, which covers a multicenter birth cohort spanning 75 hospitals. Our study cohort included 14,519 infants with a birth weight of less than 1,500 g who were admitted to the neonatal intensive care unit. Blood gas measurements taken within 1 hour of birth were used to evaluate the clinical outcomes, which were categorized into 5 groups according to base excess (BE) levels. We assessed respiratory outcomes, neurological morbidities, and infection-related and gastrointestinal outcomes along with mortality rates. We analyzed 10,394 VLBWIs based on the inclusion criteria. A BE level below -9 suggested a significantly high risk of various respiratory outcomes, including air leak syndrome (adjusted odds ratio [aOR], 2.071; 95% confidence interval [CI], 1.305-3.285), massive pulmonary hemorrhage (aOR, 2.317; 95% CI, 1.502-3.575), pulmonary hypertension (aOR, 2.296; 95% CI, 1.667-3.161), and neonatal respiratory distress syndrome (aOR, 2.219; 95% CI, 1.778-2.769). These infants also exhibited an elevated risk of neurological (aOR, 2.797; 95% CI, 2.314-3.380), infection-related (aOR, 2.082; 95% CI, 1.653-2.623), gastrointestinal (aOR, 1.979; 95% CI, 1.408-2.783), and mortality (aOR, 2.683; 95% CI, 2.076-3.466) outcomes. Our findings highlight the potential effect of metabolic acidosis at birth on the clinical outcomes of VLBWIs. A strong correlation was observed between metabolic acidosis and neurological morbidity. These findings offer important insights for managing VLBWIs with metabolic acidosis and suggest the need.

Hepatocyte nuclear factor 1-beta (HNF1B), located on chromosome 17q12, plays a critical role in the embryonic development of the kidneys, pancreas, liver, and genital tract. HNF1B has a heterozygous mutation that is also associated with neurodevelopmental diseases. Here, we describe the case of a female infant with bilateral renal enlargement and multiple cysts detected on prenatal ultrasonography. Postnatal imaging confirmed these findings and laboratory evaluation revealed transient hyperuricemia without hypomagnesemia or elevated liver enzyme levels. Targeted next-generation sequencing identified a novel heterozygous nonsense variant in the Pit-Oct-Unc-specific domain of HNF1B (c.316C>T; p.Gln106Ter), which was predicted to introduce a premature stop codon at amino acid position 106. As the patient grew older, the risk of developmental delays increased. This case illustrates the broad phenotypic spectrum of HNF1B-associated nephropathy and emphasizes the importance of HNF1B analysis in neonates presenting with renal and extra-renal manifestations. Early identification of HNF1B mutations facilitates the appropriate monitoring and management of symptoms, including neurodevelopmental outcomes. Further studies are needed to elucidate genotype-phenotype correlations and expand our understanding of HNF1B-related disorders.

Background: Respiratory distress syndrome (RDS) is a disease that commonly affects premature infants whose lungs are not fully developed. RDS results from a lack of surfactant in the lungs. The more premature the infant is, the greater is the likelihood of having RDS. However, even though not all premature infants have RDS, preemptive treatment with artificial pulmonary surfactant is administered in most cases. Objective: We aimed to develop an artificial intelligence model to predict RDS in premature infants to avoid unnecessary treatment. Methods: In this study, 13,087 very low birth weight infants who were newborns weighing less than 1500 grams were assessed in 76 hospitals of the Korean Neonatal Network. To predict RDS in very low birth weight infants, we used basic infant information, maternity history, pregnancy/birth process, family history, resuscitation procedure, and test results at birth such as blood gas analysis and Apgar score. The prediction performances of 7 different machine learning models were compared, and a 5-layer deep neural network was proposed in order to enhance the prediction performance from the selected features. An ensemble approach combining multiple models from the 5-fold cross-validation was subsequently developed. Results: Our proposed ensemble 5-layer deep neural network consisting of the top 20 features provided high sensitivity (83.03%), specificity (87.50%), accuracy (84.07%), balanced accuracy (85.26%), and area under the curve (0.9187). Based on the model that we developed, a public web application that enables easy access for the prediction of RDS in premature infants was deployed. Conclusions: Our artificial intelligence model may be useful for preparations for neonatal resuscitation, particularly in cases involving the delivery of very low birth weight infants, as it can aid in predicting the likelihood of RDS and inform decisions regarding the administration of surfactant.

BACKGROUND Respiratory distress syndrome (RDS) is a disease that commonly affects premature infants whose lungs are not fully developed. RDS results from a lack of surfactant in the lungs. The more premature the infant is, the greater is the likelihood of having RDS. However, even though not all premature infants have RDS, preemptive treatment with artificial pulmonary surfactant is administered in most cases. OBJECTIVE We aimed to develop an artificial intelligence model to predict RDS in premature infants to avoid unnecessary treatment. METHODS In this study, 13,087 very low birth weight infants who were newborns weighing less than 1500 grams were assessed in 76 hospitals of the Korean Neonatal Network. To predict RDS in very low birth weight infants, we used basic infant information, maternity history, pregnancy/birth process, family history, resuscitation procedure, and test results at birth such as blood gas analysis and Apgar score. The prediction performances of 7 different machine learning models were compared, and a 5-layer deep neural network was proposed in order to enhance the prediction performance from the selected features. An ensemble approach combining multiple models from the 5-fold cross-validation was subsequently developed. RESULTS Our proposed ensemble 5-layer deep neural network consisting of the top 20 features provided high sensitivity (83.03%), specificity (87.50%), accuracy (84.07%), balanced accuracy (85.26%), and area under the curve (0.9187). Based on the model that we developed, a public web application that enables easy access for the prediction of RDS in premature infants was deployed. CONCLUSIONS Our artificial intelligence model may be useful for preparations for neonatal resuscitation, particularly in cases involving the delivery of very low birth weight infants, as it can aid in predicting the likelihood of RDS and inform decisions regarding the administration of surfactant.