Search

BackgroundNeonatal sepsis is associated with most cases of mortalities and morbidities in the neonatal intensive care unit (NICU). Many studies have developed prediction models for the early diagnosis of bloodstream infections in newborns, but there are limitations to data collection and management because these models are based on high-resolution waveform data. ObjectiveThe aim of this study was to examine the feasibility of a prediction model by using noninvasive vital sign data and machine learning technology. MethodsWe used electronic medical record data in intensive care units published in the Medical Information Mart for Intensive Care III clinical database. The late-onset neonatal sepsis (LONS) prediction algorithm using our proposed forward feature selection technique was based on NICU inpatient data and was designed to detect clinical sepsis 48 hours before occurrence. The performance of this prediction model was evaluated using various feature selection algorithms and machine learning models. ResultsThe performance of the LONS prediction model was found to be comparable to that of the prediction models that use invasive data such as high-resolution vital sign data, blood gas estimations, blood cell counts, and pH levels. The area under the receiver operating characteristic curve of the 48-hour prediction model was 0.861 and that of the onset detection model was 0.868. The main features that could be vital candidate markers for clinical neonatal sepsis were blood pressure, oxygen saturation, and body temperature. Feature generation using kurtosis and skewness of the features showed the highest performance. ConclusionsThe findings of our study confirmed that the LONS prediction model based on machine learning can be developed using vital sign data that are regularly measured in clinical settings. Future studies should conduct external validation by using different types of data sets and actual clinical verification of the developed model.

Author(s): Seh Hyun Kim [sup.1] , Yo Han Ahn [sup.1] [sup.2] , Jeongmin Shin [sup.1] , Young Hwa Jung [sup.1] , Ji Young Kim [sup.4] , Chang Won Choi [sup.1] [...]

Purpose: Bronchopulmonary dysplasia (BPD) is a chronic lung disease that primarily affects premature infants receiving mechanical ventilation and oxygen therapy. Severe BPD leads to long-term respiratory complications, including lung tissue damage, vascular abnormalities, and airway diseases. This study aimed to investigate bronchoscopy findings and characteristics in patients with moderate-to-severe BPD, and to investigate BPD-associated airway diseases. Methods: A retrospective study of preterm infants diagnosed with moderate-to-severe BPD who underwent bronchoscopic evaluation in the neonatal intensive care unit at Seoul National University Bundang Hospital between 2004 and December 2022 was conducted. Results: Nineteen patients with a mean gestational age of 28.0±1.6 weeks and mean birth weight of 960.5±271.0 g were included in the study. Among these 19 patients, 18 were diagnosed with severe BPD. Tracheobronchomalacia, laryngomalacia, and subglottic stenosis were observed in 63.2%, 52.6%, and 36.8% of patients, respectively. Tracheostomy was performed in nine of the 19 patients (47.4%); five were discharged without requiring tracheostomy following surgical or medical interventions. Conclusion: Tracheobronchomalacia, laryngomalacia, and subglottic stenosis were common in patients with moderate or severe BPD who underwent bronchoscopic evaluations, of which 50% required tracheostomy. Our study findings provide valuable insights into the pathophysiology of BPD-associated airway diseases and may inform future clinical management strategies for patients with BPD. [ABSTRACT FROM AUTHOR]

To compare the frequency of Ureaplasma-positive gastric fluid (GF) cultures based on the cause and mode of delivery in preterm newborns. This retrospective cohort study included women with a singleton pregnancy who delivered prematurely (between 23+0 and 32+0 weeks of gestation, n=464) at a single university hospital in South Korea. The newborns' GF was obtained on the day of birth via nasogastric intubation. The frequency of Ureaplasma spp. in GF cultures was measured and compared according to the cause and mode of delivery. Ureaplasma spp. was detected in 20.3 % of the GF samples. The presence of Ureaplasma spp. was significantly higher in the spontaneous preterm birth group than in the indicated preterm birth group (30.2 vs. 3.0 %; p<0.001). Additionally, Ureaplasma spp. was more frequently found in the vaginal delivery group than in the cesarean delivery group, irrespective of the cause of preterm delivery [indicated preterm birth group (22.2 vs. 1.9 %, p=0.023); spontaneous preterm birth group (37.7 vs. 24.2 %, p=0.015)]. Ureaplasma spp. were found in 20.3 % of the GFs. However, only 1.9 % of newborns in the indicated preterm birth group with cesarean delivery had a Ureaplasma-positive GF culture. [ABSTRACT FROM AUTHOR]