Search

Abstract Accurate assessment of pediatric vital signs is critical for detecting abnormalities and guiding medical interventions, but interpretation is challenging due to age-dependent physiological variations. Therefore, this study aimed to develop age-specific centile curves for blood pressure, heart rate, and respiratory rate in pediatric patients and create a user-friendly web-based application for easy access to these data. We conducted a retrospective cross-sectional observational study analyzing 3,779,482 records from the National Emergency Department Information System of Korea, focusing on patients under 15 years old admitted between January 2016 and December 2017. After applying exclusion criteria to minimize the impact of patients’ symptoms on vital signs, 1,369,608 records were used for final analysis. The box–cox power exponential distribution and Lambda–Mu–Sigma (LMS) method were used to generate blood pressure centile charts, while heart rate and respiratory rate values were drawn from previously collected LMS values. We developed comprehensive age-specific centile curves for systolic, diastolic, and mean blood pressure, heart rate, and respiratory rate. These were integrated into a web-based application ( http://centile.research.or.kr ), allowing users to input patient data and promptly obtain centile and z-score information for vital signs. Our study provides an accessible system for pediatric vital sign evaluation, addressing previous limitations and offering a practical solution for clinical assessment. Future research should validate these centile curves in diverse populations.

Abstract Early detection of deteriorating patients is important to prevent life-threatening events and improve clinical outcomes. Efforts have been made to detect or prevent major events such as cardiopulmonary resuscitation, but previously developed tools are often complicated and time-consuming, rendering them impractical. To overcome this problem, we designed this study to create a deep learning prediction model that predicts critical events with simplified variables. This retrospective observational study included patients under the age of 18 who were admitted to the general ward of a tertiary children’s hospital between 2020 and 2022. A critical event was defined as cardiopulmonary resuscitation, unplanned transfer to the intensive care unit, or mortality. The vital signs measured during hospitalization, their measurement intervals, sex, and age were used to train a critical event prediction model. Age-specific z-scores were used to normalize the variability of the normal range by age. The entire dataset was classified into a training dataset and a test dataset at an 8:2 ratio, and model learning and testing were performed on each dataset. The predictive performance of the developed model showed excellent results, with an area under the receiver operating characteristics curve of 0.986 and an area under the precision-recall curve of 0.896. We developed a deep learning model with outstanding predictive power using simplified variables to effectively predict critical events while reducing the workload of medical staff. Nevertheless, because this was a single-center trial, no external validation was carried out, prompting further investigation.

Abstract The aim of this study was to develop a predictive model of pediatric mortality in the early stages of intensive care unit (ICU) admission using machine learning. Patients less than 18 years old who were admitted to ICUs at four tertiary referral hospitals were enrolled. Three hospitals were designated as the derivation cohort for machine learning model development and internal validation, and the other hospital was designated as the validation cohort for external validation. We developed a random forest (RF) model that predicts pediatric mortality within 72 h of ICU admission, evaluated its performance, and compared it with the Pediatric Index of Mortality 3 (PIM 3). The area under the receiver operating characteristic curve (AUROC) of RF model was 0.942 (95% confidence interval [CI] = 0.912–0.972) in the derivation cohort and 0.906 (95% CI = 0.900–0.912) in the validation cohort. In contrast, the AUROC of PIM 3 was 0.892 (95% CI = 0.878–0.906) in the derivation cohort and 0.845 (95% CI = 0.817–0.873) in the validation cohort. The RF model in our study showed improved predictive performance in terms of both internal and external validation and was superior even when compared to PIM 3.