Predicting cardiac arrests in pediatric intensive care units
Related Experiment Video
Updated: Feb 4, 2026
Author Spotlight: Simulating Pediatric Cardiac Surgery Using a Neonatal Piglet Model
Published on: May 26, 2023
Murray M Pollack1, Richard Holubkov2, Robert A Berg3
1Department of Pediatrics, Children's National Health System and the George Washington University School of Medicine and Health Sciences, Washington DC, United States.
Insights
Early identification of pediatric cardiac arrest risk is possible using data within the first 4 hours. This allows for timely interventions and improved patient outcomes in pediatric intensive care units.
Area of Science:
- Pediatric critical care medicine
- Clinical prediction modeling
- Cardiopulmonary arrest research
Background:
- Early identification of children at risk for cardiac arrest is crucial for timely intervention.
- Skill training and preventative measures can improve outcomes for at-risk pediatric patients.
Purpose of the Study:
- To develop and validate a predictive model for cardiopulmonary arrest in pediatric intensive care unit (PICU) patients.
- To utilize data available within the initial 4 hours of PICU admission for risk prediction.
Main Methods:
- Analysis of data from 10,074 PICU patients across 8 institutions.
- Inclusion of descriptive, severity of illness, cardiac arrest, and outcome data.
- Development of a multivariate logistic regression model to predict cardiac arrest.
Main Results:
- A predictive model demonstrated excellent performance (AUC=0.85).
- Key predictors for cardiac arrest included admission from an inpatient unit and prior arrest within 4 hours.
- High-risk predictions persisted even days after the initial assessment period.
Conclusions:
- Routinely available data within 4 hours can identify pediatric patients at high risk for cardiac arrest.
- Cardiac arrest events can occur shortly after risk assessment or days later.
- The developed model offers a valuable tool for proactive patient management in PICUs.
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.
Related Concept Videos
03:02Measurement: Derived Units
03:38Measurement: Standard Units
02:27Predicting Molecular Geometry
00:58Sound Intensity
01:03Prediction Intervals
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
01:27Units of Measurement
There are various well-known historical measurement systems, such as the Babylonian system, the Roman system, the Egyptian system, the Olympian system, the British system, and the Indus...