Related Experiment Video
Updated: Jan 25, 2026
Author Spotlight: Simulating Pediatric Cardiac Surgery Using a Neonatal Piglet Model
Published on: May 26, 2023
Prediction of survival after pediatric cardiac arrest using heart rate variability and machine learning
Daishi Xu1, Eris van Twist2, Marit Verboom3
1Department of Cardiology, Erasmus MC, University Medical Center, Rotterdam, the Netherlands.
Insights
Heart rate variability (HRV) measured 24 hours after pediatric cardiac arrest (CA) can predict 12-month survival. Lower HRV values, particularly total power and VLF power, indicate a higher mortality risk in these young patients.
Area of Science:
- Pediatric Critical Care Medicine
- Cardiology
- Biomedical Engineering
Background:
- Early prognostication is vital for pediatric cardiac arrest (CA) patients.
- Heart rate variability (HRV) shows promise in predicting adult CA outcomes.
- This study explores HRV for predicting survival in pediatric CA using machine learning.
Purpose of the Study:
- To investigate the utility of HRV in predicting 12-month survival outcomes in pediatric CA patients.
- To apply machine learning techniques for analyzing HRV data post-cardiac arrest.
- To identify key HRV parameters predictive of mortality in children.
Main Methods:
- Retrospective analysis of pediatric CA patients (2012-2021) achieving return of spontaneous circulation (ROSC).
- Calculation of time-, frequency-, and non-linear HRV parameters from a 5-minute ECG at 24 hours post-CA.
- Development and evaluation of a random forest model using HRV parameters, assessed via ROC analysis and Shapley values.
Main Results:
- The study included 76 pediatric patients; 42 died within 12 months.
- The random forest model achieved 77.6% accuracy and 0.879 positive predictive value for mortality.
- Frequency-domain HRV parameters, specifically total power and very-low frequency (VLF) power, were the most influential predictors, with lower values linked to increased mortality.
Conclusions:
- HRV analysis 24 hours after ROSC is a strong predictor of 12-month survival in pediatric CA.
- Machine learning models can effectively utilize HRV for prognostication in pediatric critical care.
- This non-invasive method offers potential for improved clinical decision-making in pediatric CA management.
Background:
Early prognostication of the outcome in pediatric cardiac arrest (CA) patients is crucial for clinical decision-making. Heart rate variability (HRV) has shown potential in predicting outcomes after CA in adult patients. This study investigates whether HRV can be used to predict survival outcomes after pediatric CA using machine learning techniques.
Methods:
This retrospective study included children with CA, who achieved return of spontaneous circulation (ROSC), and were admitted to the pediatric intensive care unit (PICU) of a tertiary hospital between 2012 and 2021. A 5-min electrocardiogram (ECG) segment acquired at 24 h after CA was used to calculate HRV parameters (time-, frequency-, and non-linear domains). These parameters were used to train a random forest model. The primary outcome was 12-month survival or death. Model performance was evaluated using receiver-operating characteristics (ROC) analysis and predictive values. Feature importance was assessed using Shapley values.
Results:
A total of 76 patients (male: 63.2%, median age: 2.5 [IQR: 0.4-8.0] years) were divided into survival (34) or death (42) groups based on 12-month outcomes. The machine learning model achieved an accuracy of 77.6% and a positive predictive value of 0.879 for mortality prediction. The most influential features for model predictions were the frequency-domain parameters total power and very-low frequency (VLF) power, with lower values associated with an increased probability of death.
Conclusions:
Analysis of HRV at 24 h after ROSC may serve as a strong predictor of 12-month survival after pediatric CA.
More Related Videos
07:13Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
Published on: April 18, 2025
05:48Autonomic Function Following Concussion in Youth Athletes: An Exploration of Heart Rate Variability Using 24-hour Recording Methodology
Published on: September 21, 2018
Related Concept Videos
01:19Cardiac Output I:Effect of Heart Rate on Cardiac Output
Cardiac output (CO) refers to the total amount of blood ejected by one of the ventricles in liters per minute (L/min). In a resting adult, CO ranges from 5 to 6 L/min, adjusting according to the body's metabolic requirements.
Effect of Heart Rate on Cardiac Output
Cardiac output adapts to metabolic demands during stress, physical activity, or illness. The autonomic nervous system regulates heart rate via the sinoatrial node. The parasympathetic nervous system decreases heart...
01:31Regulation of Heart Rates
The SNS increases heart rate through the release of norepinephrine and epinephrine, which act on beta-1 adrenergic receptors in the heart. This action increases the rate of depolarization in the sinoatrial (SA) node, the heart's...
01:30Factors Influencing Heart Rate
Let us explore the significant factors affecting heart rate, including age, body temperature, posture, acute pain, chemical influences,...
01:18Physiology of the Heart: The Cardiac Cycle
Diastole: The Relaxation Phase
During diastole, all four heart chambers relax. The atrioventricular (AV) valves open, and the semilunar valves close. This phase sees the lowest chamber pressures, promoting ventricular filling. Venous blood enters the heart through the...
01:21Cardiac Catheterization II: Right Heart Catheterization
01:24Cardiac Catheterization III: Left Heart Catheterization