Related Experiment Video
Updated: Jun 11, 2025
Polar Histogram Visualization of Acute Stress Disorder Scale Scores for Comprehensive Clinical Assessment
Published on: December 6, 2024
Predicting Parental Post-Traumatic Stress Symptoms Following their Child's Stay in a Pediatric Intensive Care Unit,
Mekela M Whyte-Nesfield1, Eduardo A Trujillo Rivera1,2,3, Daniel Kaplan4
1Department of Pediatrics, Division of Pediatric Critical Care, Children's National Hospital, Washington, DC, USA.
Insights
A machine learning model can predict parental post-traumatic stress (PTS) after a child
Area of Science:
- Psychology and Psychiatry
- Pediatric Critical Care Medicine
- Machine Learning in Healthcare
Background:
- Parental experience in the Pediatric Intensive Care Unit (PICU) can lead to significant psychological distress, including post-traumatic stress (PTS).
- Identifying at-risk parents early is crucial for timely intervention and support.
- Existing methods for predicting PTS may not fully capture the complexity of parental experiences in the PICU.
Purpose of the Study:
- To develop and validate an inpatient predictive model for parental PTS following pediatric intensive care.
- To identify key pre-admission and admission risk factors associated with the development of PTS in parents.
- To assess the accuracy and utility of a machine learning model for predicting parental PTS.
Main Methods:
- A prospective observational cohort study was conducted with 169 parents of children admitted to two tertiary care PICUs.
- Data on pre-admission and admission factors were collected, and parental PTS symptoms were assessed 3-9 months post-discharge using the Post-traumatic Stress Disorder Symptom Scale-Interview.
- A machine learning model (XGBoost) was developed to predict parental PTS, with variable importance analyzed using Local Interpretable Model-Agnostic Explanation (LIME).
Main Results:
- 35% of parents met criteria for PTS (score >9) at 3-9 months post-PICU discharge.
- The XGBoost model achieved 76.7% accuracy in predicting parental PTS, with a sensitivity of 0.83 and specificity of 0.72.
- The most significant predictors identified were composite variables of parental history of mental illness and traumatic experiences.
Conclusions:
- A machine learning model effectively predicts parental PTS following pediatric intensive care with sufficient accuracy for clinical application.
- The model's performance (76.7% accuracy, number needed to evaluate 1.47) supports its use in identifying at-risk parents during hospitalization.
- Early identification enables timely inpatient and post-discharge interventions to mitigate the impact of PTS on parents.
Abstract:
Objective: Develop an inpatient predictive model of parental post-traumatic stress (PTS) following their child's care in the Pediatric Intensive Care Unit (PICU). Design: Prospective observational cohort. Setting: Two tertiary care children's hospitals with mixed medical/surgical/cardiac PICUs. Subjects: Parents of patients admitted to the PICU. Interventions: None. Measurements and Main Results: Preadmission and admission data from 169 parents of 129 children who completed follow up screening for parental post-traumatic stress symptoms at 3-9 months post PICU discharge were utilized to develop a predictive model estimating the risk of parental PTS 3-9 months after hospital discharge. The parent cohort was predominantly female (63%), partnered (75%), and working (70%). Child median age was 3 years (IQR 0.36-9.04), and more than half had chronic illnesses (56%) or previous ICU admissions (64%). Thirty-five percent (60/169) of parents met criteria for PTS (>9 on the Post-traumatic Stress Disorder Symptom Scale-Interview). The machine learning model (XGBoost) predicted subjects with parental PTS with 76.7% accuracy, had a sensitivity of 0.83 (95% CI 0.586, 0.964), a specificity of 0.72 (95% CI 0.506, 0.879), a precision of 0.682 (95% CI 0.451, 0.861) and number needed to evaluate of 1.47 (95% CI 1.16, 1.98). The area under the receiver operating curve was 0.78 (95% CI 0.64, 0.92). The most important predictive pre-admission and admission variables were determined using the Local Interpretable Model-Agnostic Explanation, which identified seven variables used 100% of the time. Composite variables of parental history of mental illness and traumatic experiences were most important. Conclusion: A machine learning model using parent risk factors predicted subsequent PTS at 3-9 months following their child's PICU discharge with an accuracy of 76.7% and number needed to evaluate of 1.47. This performance is sufficient to identify parents who are at risk during hospitalization, making inpatient and acute post admission mitigation initiatives possible.
More Related Videos
19:15Assessment and Evaluation of the High Risk Neonate: The NICU Network Neurobehavioral Scale
Published on: August 25, 2014
05:48Autonomic Function Following Concussion in Youth Athletes: An Exploration of Heart Rate Variability Using 24-hour Recording Methodology
Published on: September 21, 2018
