Dataset Information

Predicting cardiac arrests in pediatric intensive care units.

ABSTRACT: BACKGROUND:Early identification of children at risk for cardiac arrest would allow for skill training associated with improved outcomes and provides a prevention opportunity. OBJECTIVE:Develop and assess a predictive model for cardiopulmonary arrest using data available in the first 4?h. METHODS:Data from PICU patients from 8 institutions included descriptive, severity of illness, cardiac arrest, and outcomes. RESULTS:Of the 10074 patients, 120 satisfying inclusion criteria sustained a cardiac arrest and 67 (55.9%) died. In univariate analysis, patients with cardiac arrest prior to admission were over 6 times and those with cardiac arrests during the first 4?h were over 50 times more likely to have a subsequent arrest. The multivariate logistic regression model performance was excellent (area under the ROC curve?=?0.85 and Hosmer-Lemeshow statistic, p?=?0.35). The variables with the highest odds ratio's for sustaining a cardiac arrest in the multivariable model were admission from an inpatient unit (8.23 (CI: 4.35-15.54)), and cardiac arrest in the first 4?h (6.48 (CI: 2.07-20.36). The average risk predicted by the model was highest (11.6%) among children sustaining an arrest during hours >4-12 and continued to be high even for days after the risk assessment period; the average predicted risk was 9.5% for arrests that occurred after 8 PICU days. CONCLUSIONS:Patients at high risk of cardiac arrest can be identified with routinely available data after 4?h. The cardiac arrest may occur relatively close to the risk assessment period or days later.

SUBMITTER: Pollack MM

PROVIDER: S-EPMC6258339 | biostudies-literature | 2018 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting cardiac arrests in pediatric intensive care units.

Pollack Murray M MM Holubkov Richard R Berg Robert A RA Newth Christopher J L CJL Meert Kathleen L KL Harrison Rick E RE Carcillo Joseph J Dalton Heidi H Wessel David L DL Dean J Michael JM

Resuscitation 20180925

<h4>Background</h4>Early identification of children at risk for cardiac arrest would allow for skill training associated with improved outcomes and provides a prevention opportunity.<h4>Objective</h4>Develop and assess a predictive model for cardiopulmonary arrest using data available in the first 4 h.<h4>Methods</h4>Data from PICU patients from 8 institutions included descriptive, severity of illness, cardiac arrest, and outcomes.<h4>Results</h4>Of the 10074 patients, 120 satisfying inclusion c ...[more]

PMID: 30261219

Similar Datasets

Project description:BACKGROUND:Healthcare-associated infections (HAIs) represent serious complications for patients within pediatric cardiac intensive care units (CICU). HAIs are associated with increased morbidity, mortality and resource utilization. There are few studies describing the epidemiology of HAIs across the entire spectrum of patients (surgical and nonsurgical) receiving care in dedicated pediatric CICUs. METHODS:Retrospective analyses of 22,839 CICU encounters from October 2013 to September 2016 across 22 North American CICUs contributing data to the Pediatric Cardiac Critical Care Consortium clinical registry. RESULTS:HAIs occurred in 2.4% of CICU encounters at a rate of 3.3 HAIs/1000 CICU days, with 73% of HAIs occurring in children <1 year. Eighty encounters (14%) had ?2 HAIs. Aggregate rates for the 4 primary HAIs are as follows: central line-associated blood stream infection, 1.1/1000 line days; catheter-associated urinary tract infections, 1.5/1000 catheter days; ventilator-associated pneumonia, 1.9/1000 ventilator days; surgical site infections, 0.81/100 operations. Surgical and nonsurgical patients had similar HAIs rates/1000 CICU days. Incidence was twice as high in surgical encounters and increased with surgical complexity; postoperative infection occurred in 2.8% of encounters. Prematurity, younger age, presence of congenital anomaly, Society of Thoracic Surgeons-European Association for Cardio-Thoracic Surgery Congenital Heart Surgery Mortality Categories (STAT) 4-5 surgery, admission with an active medical condition, open sternum and extracorporeal membrane oxygenation were independently associated with HAIs. In univariable analysis, HAI was associated with longer hospital length of stay and durations of urinary catheter, central venous catheter and ventilation. Mortality was 24.4% in patients with HAIs versus 3.4% in those without, P < 0.0001. CONCLUSIONS:We provide comprehensive multicenter benchmark data regarding rates of HAIs within dedicated pediatric CICUs. We confirm that although rare, HAIs of all types are associated with significant resource utilization and mortality.

Project description:Develop and compare separate prediction models for ICU and non-ICU care for hospitalized children in four future time periods (6-12, 12-18, 18-24, and 24-30 hr) and assess these models in an independent cohort and simulated children's hospital.DesignPredictive modeling used cohorts from the Health Facts database (Cerner Corporation, Kansas City, MO).SettingChildren hospitalized in ICUs.PatientsChildren with greater than or equal to one ICU admission (n = 20,014) and randomly selected routine care children without ICU admission (n = 20,130) from 2009 to 2016 were used for model development and validation. An independent 2017-2018 cohort consisted of 80,089 children.InterventionsNone.Measurement and main resultsInitially, we undersampled non-ICU patients for development and comparison of the models. We randomly assigned 64% of patients for training, 8% for validation, and 28% for testing in both clinical groups. Two additional validation cohorts were tested: a simulated children's hospitals and the 2017-2018 cohort. The main outcome was ICU care or non-ICU care in four future time periods based on physiology, therapy, and care intensity. Four independent, sequential, and fully connected neural networks were calibrated to risk of ICU care at each time period. Performance for all models in the test sample were comparable including sensitivity greater than or equal to 0.727, specificity greater than or equal to 0.885, accuracy greater than 0.850, area under the receiver operating characteristic curves greater than or equal to 0.917, and all had excellent calibration (all R2 s > 0.98). Model performance in the 2017-2018 cohort was sensitivity greater than or equal to 0.545, specificity greater than or equal to 0.972, accuracy greater than or equal to 0.921, area under the receiver operating characteristic curves greater than or equal to 0.946, and R2 s greater than or equal to 0.979. Performance metrics were comparable for the simulated children's hospital and for hospitals stratified by teaching status, bed numbers, and geographic location.ConclusionsMachine learning models using physiology, therapy, and care intensity predicting future care needs had promising performance metrics. Notably, performance metrics were similar as the prediction time periods increased from 6-12 hours to 24-30 hours.

Dataset Information

Predicting cardiac arrests in pediatric intensive care units.

Publications

Predicting cardiac arrests in pediatric intensive care units.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure