Yunseob Shin, Kyung-Jae Cho, Yeha Lee, Yu Hyeon Choi, Jae Hwa Jung, Soo Yeon Kim, Yeo Hyang Kim, Young A Kim, Joongbum Cho, Seong Jong Park, Won Kyoung Jhang
Acute Crit Care. 2022;37(4):654-666. Published online October 26, 2022
Background Early recognition of deterioration events is crucial to improve clinical outcomes. For this purpose, we developed a deep-learning-based pediatric early-warning system (pDEWS) and aimed to validate its clinical performance. Methods: This is a retrospective multicenter cohort study including five tertiary-care academic children’s hospitals. All pediatric patients younger than 19 years admitted to the general ward from January 2019 to December 2019 were included. Using patient electronic medical records, we evaluated the clinical performance of the pDEWS for identifying deterioration events defined as in-hospital cardiac arrest (IHCA) and unexpected general ward-to-pediatric intensive care unit transfer (UIT) within 24 hours before event occurrence. We also compared pDEWS performance to those of the modified pediatric early-warning score (PEWS) and prediction models using logistic regression (LR) and random forest (RF). Results: The study population consisted of 28,758 patients with 34 cases of IHCA and 291 cases of UIT. pDEWS showed better performance for predicting deterioration events with a larger area under the receiver operating characteristic curve, fewer false alarms, a lower mean alarm count per day, and a smaller number of cases needed to examine than the modified PEWS, LR, or RF models regardless of site, event occurrence time, age group, or sex. Conclusions: The pDEWS outperformed modified PEWS, LR, and RF models for early and accurate prediction of deterioration events regardless of clinical situation. This study demonstrated the potential of pDEWS as an efficient screening tool for efferent operation of rapid response teams.
Citations
Citations to this article as recorded by
Predicting cardiac arrest after neonatal cardiac surgery Alexis L. Benscoter, Mark A. Law, Santiago Borasino, A. K. M. Fazlur Rahman, Jeffrey A. Alten, Mihir R. Atreya Intensive Care Medicine – Paediatric and Neonatal.2024;[Epub] CrossRef
Volumetric regional MRI and neuropsychological predictors of motor task variability in cognitively unimpaired, Mild Cognitive Impairment, and probable Alzheimer's disease older adults Michael Malek-Ahmadi, Kevin Duff, Kewei Chen, Yi Su, Jace B. King, Vincent Koppelmans, Sydney Y. Schaefer Experimental Gerontology.2023; 173: 112087. CrossRef
Predicting sepsis using deep learning across international sites: a retrospective development and validation study Michael Moor, Nicolas Bennett, Drago Plečko, Max Horn, Bastian Rieck, Nicolai Meinshausen, Peter Bühlmann, Karsten Borgwardt eClinicalMedicine.2023; 62: 102124. CrossRef
A model study for the classification of high-risk groups for cardiac arrest in general ward patients using simulation techniques Seok Young Song, Won-Kee Choi, Sanggyu Kwak Medicine.2023; 102(37): e35057. CrossRef
An advanced pediatric early warning system: a reliable sentinel, not annoying extra work Young Joo Han Acute and Critical Care.2022; 37(4): 667. CrossRef
Direct hemoperfusion therapy with a polymyxin B-immobilized fiber column (PMX-HP) has been introduced as a therapeutic option for gram negative bacterial septic shock in adults. However, its use in neonates and children has not yet been established. We successfully performed hemoperfusion therapy using an adult polymyxin B-immobilized fiber column in a neonate with carbapenem resistant Acinetobacter baumannii septic shock. The application was technically feasible because the neonate was on extracorporeal membrane oxygenation (ECMO). Although it did not rescue the patient, there was significant short-lasting improvement in pulmonary oxygenation and hemodynamics, leading to wean the patient from ECMO. PMX-HP could be used as an adjunctive treatment for selected neonatal and pediatric patients with gram negative bacterial septic shock.
Citations
Citations to this article as recorded by
Polymyxin B Hemoperfusion in Pediatric Septic Shock: Single-Center Observational Case Series Patcharin Saetang, Rujipat Samransamruajkit, Kanokwan Singjam, Tawatchai Deekajorndech Pediatric Critical Care Medicine.2022; 23(8): e386. CrossRef
Controlling an Outbreak of Multidrug-resistant Acinetobacter baumannii in a Pediatric Intensive Care Unit: a Retrospective Analysis Joung-Hee Byun, Su Eun Park, Minhae Seo, Jeungmi Jang, Mi Sun Hwang, Ju Yeoun Song, Chulhun L. Chang, Young A Kim Journal of Korean Medical Science.2021;[Epub] CrossRef
Effects of continuous renal replacement therapy with the AN69ST membrane for septic shock and sepsis-induced AKI in an infant: a case report with literature review of cytokine/mediator removal therapy in children Naoto Nishizaki, Riko Ueno, Yuki Nagayama, Hanako Abe, Akina Matsuda, Akira Mizutani, Kaoru Obinata, Tadaharu Okazaki, Toshiaki Shimizu Renal Replacement Therapy.2020;[Epub] CrossRef
Suggestions and tips regarding polymyxin B-immobilized fiber column direct hemoperfusion of neonates with sepsis Naoto Nishizaki Acute and Critical Care.2020; 35(3): 226. CrossRef
Case Report: Successful Use of Extracorporeal Therapies After ECMO Resuscitation in a Pediatric Kidney Transplant Recipient Andrey Rybalko, Anna Pytal, Mikhail Kaabak, Nadejda Rappoport, Anuar Bidzhiev, Vasilii Lastovka Frontiers in Pediatrics.2020;[Epub] CrossRef
BACKGROUND Selenium is an essential trace-element with antioxidant and immunological function. We studied the relationship between blood selenium concentrations, systemic inflammatory response syndrome (SIRS) and organ dysfunctions in critically ill children. METHODS This was a retrospective, observational study of the blood selenium concentrations of critically ill children at the time of a pediatric intensive care unit admission. RESULTS A total of 62 patients with a median age of 18 (5-180) months were included in this study. The mean of blood selenium concentration (microg/dl) was 8.49 +/- 2.42.
The platelet count (r = -0.378) and PaCO2 (r = -0.403) showed negative correlations with blood selenium concentration, while PaO2/FiO2 (r = 0.359) and PaO2 (r = 0.355) showed positive correlations (p < 0.05, for all variables). Blood selenium concentrations were significantly lower in patients with SIRS than in those patients without SIRS (8.08 +/- 2.42 vs. 9.45 +/- 2.02, p = 0.011). Patients with severe sepsis and septic shock had showed significantly lower blood selenium concentrations than those without SIRS (7.03 +/- 2.73 vs. 9.45 +/- 2.02, p = 0.042). Patients with PaO2/FiO2 < or = 300 had lower blood selenium concentrations than those with PaO2/FiO2 > 300 (7.90 +/- 2.43 vs. 9.54 +/- 2.17, p = 0.018). Blood selenium concentrations were significantly lower in patient with PaO2/FiO2 < or = 200 than in those with PaO2/FiO2 > 300 (7.64 +/- 2.76 vs. 9.54 +/- 2.17, p = 0.018). CONCLUSIONS Patients with systemic inflammatory response syndrome or respiratory dysfunction showed significantly low blood selenium concentrations.