Related Experiment Video
Updated: May 30, 2025
A Modified Sonographic Algorithm for Image Acquisition in Life-Threatening Emergencies in the Critically Ill Newborn
Published on: April 7, 2023
Incidence of cardiac arrest following implementation of a predictive analytics display in a pediatric intensive care
Michael C Spaeder1,2, Laura Lee1, Chelsea Miller1
1Department of Pediatrics, University of Virginia School of Medicine, Box 800386, Charlottesville, VA 22908, USA.
Insights
Displaying cardiovascular and respiratory instability risk scores in pediatric ICUs did not significantly reduce cardiac arrest events. However, it did increase the rate of successful resuscitation (ROSC) and decrease fatal events.
Area of Science:
- Pediatric Critical Care Medicine
- Clinical Informatics
- Predictive Analytics in Healthcare
Background:
- Pediatric in-hospital cardiac arrests (IHCA) predominantly occur in intensive care units (ICUs), with low survival rates.
- Understanding and mitigating risks for pediatric cardiac arrest is a critical challenge in critical care.
Purpose of the Study:
- To evaluate the impact of displaying real-time cardiovascular and respiratory instability risk scores on the incidence of cardiac arrest in a pediatric ICU.
- To assess the association between predictive analytics for clinical deterioration and patient outcomes.
Main Methods:
- Developed supervised machine learning models to predict cardiovascular and respiratory instability within 12 hours.
- Implemented a system displaying risk scores on monitors throughout the ICU.
- Compared cardiac arrest event rates in the 18 months before and after implementation.
Main Results:
- Cardiac arrest incidence decreased from 3.0 to 2.4 events per 1000 patient days.
- Cardiac arrest events without return of spontaneous circulation (ROSC) significantly decreased (1.4 to 0.4 events per 1000 patient days).
- The rate of cardiac arrest events with ROSC significantly increased by 50% (p=0.025).
Conclusions:
- Implementation of predictive analytics displaying risk scores showed a non-significant trend towards decreasing overall cardiac arrest events.
- The system significantly increased the rate of achieving ROSC, indicating improved resuscitation success.
- Predictive analytics may enhance early recognition and intervention, improving outcomes for pediatric critical care patients.
Background:
More than 90% of in-hospital cardiac arrests involving children occur in an intensive care unit (ICU) with less than half surviving to discharge. We sought to assess the association of the display of risk scores of cardiovascular and respiratory instability with the incidence of cardiac arrest in a pediatric ICU.
Methods:
Employing supervised machine learning, we previously developed predictive models of cardiovascular and respiratory instability, incorporating real-time physiologic and laboratory data, to display risk scores for potentially catastrophic clinical events in the subsequent 12 h. Clinical implementation with risk scores displayed on large screen monitors in multiple areas throughout the ICU was finalized in July 2022. We compared the incidence of cardiac arrest events in the 18-months pre- and post-implementation.
Results:
The cardiac arrest incidence rate dropped from 3.0 events (95% CI 2.0-4.4) to 2.4 events (95% CI 1.6-3.5) per 1000 patient days following implementation. We observed a 50% increase in the rate of cardiac arrest events where return of spontaneous circulation (ROSC) was achieved (p = 0.025). The incidence rate of cardiac arrest without ROSC dropped from 1.4 events (95% CI 0.7-2.4) to 0.4 events (95% CI 0.1-0.9) per 1000 patient days (incidence rate difference = 1.0 (95% CI 0.13-1.87), p = 0.01).
Conclusions:
We observed a non-significant decrease in the rates of cardiac arrest events and an increase in the rate of cardiac arrests events where ROSC was achieved following the implementation of a predictive analytics display of risk scores.
