Related Experiment Video
Updated: Aug 3, 2025
Analyzing Long-Term Electrocardiography Recordings to Detect Arrhythmias in Mice
Published on: May 23, 2021
Predicting Cardiac Arrest in Children with Heart Disease: A Novel Machine Learning Algorithm
Priscilla Yu1, Michael Skinner2,3, Ivie Esangbedo4
1Division of Critical Care, Department of Pediatrics, University of Texas Southwestern Medical Center, Dallas, TX 75235, USA.
Insights
A machine learning algorithm can predict cardiac arrest in children with heart disease up to an hour before it occurs. This tool shows promise for cardiac arrest prevention in pediatric intensive care units.
Area of Science:
- Pediatric Cardiology
- Biomedical Informatics
- Machine Learning in Healthcare
Background:
- Children with heart disease face a higher risk of cardiac arrest.
- Despite advancements in resuscitation, survival rates remain low for this population.
- Predictive algorithms using machine learning offer potential for cardiac arrest prevention.
Purpose of the Study:
- To evaluate a novel machine learning algorithm for predicting cardiac arrest in pediatric patients with heart disease.
- To compare the performance of machine learning against traditional logistic regression for cardiac arrest prediction.
Main Methods:
- Retrospective analysis of electronic health records (EHR) from a pediatric cardiac intensive care unit (CICU) (2010-2019).
- Collected demographic, laboratory, and vital sign data for patients who experienced cardiac arrest and a control group.
- Compared a functional gradient boosting machine learning algorithm with time series data against logistic regression.
Main Results:
- The machine learning algorithm achieved a peak performance (AUROC 0.85) one hour prior to cardiac arrest.
- The algorithm utilized 11 variables from EHR data (vital signs and lab values).
- Performance was comparable to a previously developed multivariable logistic regression model.
Conclusions:
- A novel machine learning algorithm can predict cardiac arrest in pediatric CICU patients with performance similar to traditional models.
- The algorithm, developed on retrospective EHR data, shows promise for real-time clinical decision support.
- Further prospective, multicenter validation is necessary before clinical implementation.
Background:
Children with congenital and acquired heart disease are at a higher risk of cardiac arrest compared to those without heart disease. Although the monitoring of cardiopulmonary resuscitation quality and extracorporeal resuscitation technologies have advanced, survival after cardiac arrest in this population has not improved. Cardiac arrest prevention, using predictive algorithms with machine learning, has the potential to reduce cardiac arrest rates. However, few studies have evaluated the use of these algorithms in predicting cardiac arrest in children with heart disease.
Methods:
We collected demographic, laboratory, and vital sign information from the electronic health records (EHR) of all the patients that were admitted to a single-center pediatric cardiac intensive care unit (CICU), between 2010 and 2019, who had a cardiac arrest during their CICU admission, as well as a comparator group of randomly selected non-cardiac-arrest controls. We compared traditional logistic regression modeling against a novel adaptation of a machine learning algorithm (functional gradient boosting), using time series data to predict the risk of cardiac arrest.
Results:
A total of 160 unique cardiac arrest events were matched to non-cardiac-arrest time periods. Using 11 different variables (vital signs and laboratory values) from the EHR, our algorithm's peak performance for the prediction of cardiac arrest was at one hour prior to the cardiac arrest (AUROC of 0.85 [0.79,0.90]), a performance that was similar to our previously published multivariable logistic regression model.
Conclusions:
Our novel machine learning predictive algorithm, which was developed using retrospective data that were collected from the EHR and predicted cardiac arrest in the children that were admitted to a single-center pediatric cardiac intensive care unit, demonstrated a performance that was similar to that of a traditional logistic regression model. While these results are encouraging, future research, including prospective validations with multicenter data, is warranted prior to the implementation of this algorithm as a real-time clinical decision support tool.
Related Concept Videos
01:23Cardiopulmonary Resuscitation III: AED Use
01:25Cardiopulmonary Resuscitation IV: Pharmacological Management