Background: Neonatal morbidities are major determinants of clinical outcomes and healthcare utilization in preterm infants. However, population-level evidence quantifying the cumulative contribution of neonatal morbidities to neonatal intensive care unit (NICU) length of stay (LOS) and medical costs remains limited. Methods: We conducted a nationwide retrospective cohort study using the Korean Health Insurance Review and Assessment Service database. Preterm infants admitted to NICUs between 2020 and 2023 were identified. After exclusions, 30,034 infants with complete birth weight data and 31,240 with complete gestational age data were included. Major neonatal morbidities—including bronchopulmonary dysplasia (BPD), patent ductus arteriosus (PDA), sepsis, intraventricular hemorrhage (IVH), retinopathy of prematurity (ROP), necrotizing enterocolitis (NEC), and periventricular leukomalacia (PVL)—were identified using ICD-10 odes. Associations of individual morbidities and cumulative morbidity burden with NICU LOS and medical costs were evaluated using multivariable regression and generalized linear mixed models. Results: Mean NICU LOS was 26.5 days, and mean total medical cost was 41.9 million KRW. All major morbidities were associated with prolonged LOS and increased costs. BPD showed the strongest association with LOS, whereas NEC and sepsis were associated with the highest costs. NICU LOS and medical costs increased in a stepwise manner with increasing numbers of morbidities; each additional morbidity was associated with an 8.0-day increase in LOS and a 32.5 million KRW increase in medical costs (both p < 0.001). Conclusions: Greater cumulative morbidity burden was associated with prolonged hospitalization and increased healthcare costs in preterm infants.

Cha T, et al. Perinatology. 2023 Dec;34(4):157-164. https://doi.org/10.14734/PN.2023.34.4.157

Background/Objectives: Early detection of postnatal growth failure (PGF) is essential for optimizing nutritional management in preterm infants, as PGF is associated with adverse neurodevelopmental outcomes. Early prediction remains difficult because postnatal growth is influenced by multiple clinical factors including gestation age, birth weight, nutritional status, and comorbidities. Machine-learning approaches have been proposed to predict complex neonatal outcomes. This study compared the predictive performance of neonatologists with that of a machine-learning model for predicting PGF. Methods: PGF was defined as a decrease in weight z-score greater than 1.28 at discharge compared with birth. A machine-learning model based on extreme gradient boosting (XGBoost) was trained using a dataset of 7954 very low birth weight (VLBW) infants. Nine neonatologists independently assessed 100 clinical cases through a questionnaire-based evaluation, including 50 patients with PGF. Predictive performance was evaluated using seven metrics: area under the receiver operating characteristic curve (AUROC), accuracy, error rate, positive predictive value (PPV), sensitivity, specificity, and F1 score. Results: The neonatologists had a median of 5 years (range: 4–10 years) of clinical experience. The median prediction score among the neonatologists was 52/100 (range, 44–60), whereas the XGBoost model achieved 79/100. The XGBoost model achieved an AUROC of 0.79, accuracy of 0.79, error rate of 0.21, sensitivity of 0.82, and an F1 score of 0.80, demonstrating superior overall performance compared to the neonatologists. In addition, the XGBoost model had a lower error rate than the neonatologists (0.21 vs. 0.49), whereas specificity (0.76 vs. 0.86) and PPV (0.77 vs. 0.53) did not differ significantly. Conclusions: The machine-learning model demonstrated superior or comparable predictive performance to that of neonatologists in detecting PGF. Machine-learning-based prediction models may support early risk stratification and targeted nutritional management in VLBW infants.

The pathophysiology of patent ductus arteriosus (PDA) is conventionally attributed to increased pulmonary blood flow and reduced systemic organ perfusion caused by left-to-right ductal shunting. Although PDA has been associated with major complications of prematurity and neurodevelopmental impairment, establishing direct causality remains challenging due to multiple confounders, including interactions among risk factors inherent to prematurity, variability in PDA severity and exposure duration, and the effects of interventions themselves. Accumulating evidence supports interpreting PDA in preterm infants as a biomarker of physiological vulnerability and comorbidity severity rather than as a primary causative condition. Prophylactic or early routine pharmacological closure has not demonstrated consistent benefits over conservative management with expectant closure in terms of mortality, short-term morbidity, or long-term neurodevelopmental outcomes. Prospective studies have confirmed that conservative management is a viable treatment strategy even in extremely preterm infants born before 28 weeks of gestation. Major international guidelines recommend that closure be considered only when echocardiographic evidence of hemodynamic compromise is accompanied by clinical symptoms, with pharmacological therapy as the first-line treatment. When pharmacological treatment fails or is contraindicated, the choice and timing of transcatheter ductal occlusion or surgical ligation should be determined based on the patient’s cardiorespiratory status, comorbidities, institutional availability, and anticipated risks. PDA management should be guided by the clinical judgment of experienced neonatologists with comprehensive knowledge of each patient rather than by adherence to uniform protocols. In the domestic neonatal care setting, individualized management strategies developed through multidisciplinary collaboration should be given appropriate consideration.