Related Experiment Video
Updated: Jun 12, 2025
A Novel Rescue Technique for Difficult Intubation and Difficult Ventilation
Published on: January 17, 2011
Development and Validation of a Bayesian Network Predicting Intubation Following Hospital Arrival Among Injured
Travis M Sullivan1, Mary S Kim1, Genevieve J Sippel1
1Division of Trauma and Burn Surgery, Children's National Hospital, Washington, DC, USA.
Insights
A new Bayesian network, TITAN, predicts the need for intubation in pediatric trauma patients using readily available data. This tool aids in timely airway management for injured children and adolescents.
Area of Science:
- Pediatric Trauma Care
- Machine Learning in Medicine
- Airway Management
Background:
- Inadequate airway management is a significant cause of preventable trauma deaths.
- Existing machine learning tools for trauma intubation prediction are limited to adults and use non-immediate data.
- There is a need for predictive tools applicable to pediatric populations upon arrival.
Purpose of the Study:
- To develop and validate a Bayesian network for predicting emergent intubation in pediatric trauma patients.
- To utilize observable data available early in the resuscitation process.
- To improve airway management strategies in pediatric trauma care.
Main Methods:
- Utilized trauma registry data from four Level 1 pediatric trauma centers (2010-2021).
- Trained and validated a Bayesian network model incorporating demographic, injury, resuscitation, and transportation characteristics.
- Evaluated model performance using area under the receiver operating characteristic (ROC) and calibration curves.
Main Results:
- The TITAN (Timing of Intubation in Trauma Analysis Network) model includes Glasgow Coma Scale, mechanism of injury, injury type, systolic blood pressure, and age.
- Achieved an area under the ROC curve of 0.83 (95% CI 0.80, 0.85).
- Demonstrated high specificity (98%), negative predictive value (97%), and accuracy (96%) at a 22.6% probability threshold.
Conclusions:
- The TITAN Bayesian network effectively predicts intubation risk in pediatric trauma patients using early-observable factors.
- Further prospective validation is required to assess the real-world clinical benefits and risks.
- This model can support timely and informed airway management decisions in pediatric trauma resuscitation.
Background:
Inadequate airway management can contribute to preventable trauma deaths. Current machine learning tools for predicting intubation in trauma are limited to adult populations and include predictors not readily available at the time of patient arrival. We developed a Bayesian network to predict intubation in injured children and adolescents using observable data available upon or immediately after patient arrival.
Methods:
We obtained patient demographic, injury, resuscitation, and transportation characteristics from trauma registries from four American College of Surgeons-verified level 1 pediatric trauma centers from January 2010 through December 2021. We trained and validated a Bayesian network to predict emergent intubation after pediatric injury. We evaluated model performance using the area under the receiver operating and calibration curves.
Results:
The final model, TITAN (Timing of Intubation in Trauma Analysis Network), incorporated five factors: Glasgow Coma Scale, mechanism of injury, injury type (e.g., penetrating, blunt), systolic blood pressure, and age. The model achieved an area under the receiver operating characteristic curve of 0.83 (95% CI 0.80, 0.85) and had a calibration curve slope of 0.98 (95% CI 0.67, 1.29). TITAN had high specificity (98%), negative predictive value (97%), and accuracy (96%) at a binary probability threshold of 22.6%.
Conclusion:
The TITAN Bayesian network predicts the risk of intubation in pediatric trauma patients using five factors that are observable early in trauma resuscitation. Prospective validation of the model performance with patient outcomes is needed to assess real-life application benefits and risks.
Level Of Evidence:
Prognostic and Epidemiological, Level III.
Related Concept Videos
01:17Endotracheal Intubation II: Nursing Management
1. Nursing Care of Patients Before Intubation
Before the endotracheal intubation procedure, nurses play an essential role in ensuring the process goes smoothly. The nurses must be familiar with intubation...
01:15Endotracheal Intubation I: Procedure
The ET tube comprises various components, including a standard adaptor to attach a bag-valve-mask (BVM) or ventilator, a cuff, a pilot balloon, and radiopaque markings along its length to measure the insertion distance. The tube sizes...