⚡ Quick Summary
A recent study developed a prehospital triage model utilizing machine learning to enhance the National Field Triage Guidelines for predicting severe trauma. The model demonstrated a sensitivity of 79.9% and an undertriage rate of 8.0%, showcasing its potential to improve patient outcomes in emergency settings. 🚑
🔍 Key Details
- 📊 Dataset: 1,469,146 patients from the National Trauma Data Bank (2017-2019)
- 🧩 Features used: Age, 7 vital signs, and 8 injury patterns
- ⚙️ Technology: Extreme Gradient Boosting model
- 🏆 Performance: Sensitivity 79.9%, Undertriage rate 8.0%
🔑 Key Takeaways
- 🚑 Enhanced triage: The model significantly improves the identification of severe trauma cases.
- 💡 Machine learning: Utilized to refine existing triage guidelines, demonstrating its applicability in emergency medicine.
- 📈 Consistent performance: The model’s effectiveness was validated across multiple datasets.
- 🔍 Better than traditional methods: Outperformed Glasgow Coma Score and other established triage tools.
- 🌍 Potential for broader use: Could be adapted for various emergency medical services beyond trauma.
- 🗓️ Study duration: Data collected over a two-year period, ensuring a robust sample size.
- 📉 Low undertriage rate: Achieved an undertriage rate of less than 10%, a critical metric for emergency care.
📚 Background
Prehospital trauma triage is crucial for ensuring that patients receive appropriate care at the right facilities. However, the existing National Field Triage Guidelines have been criticized for their insensitivity in identifying severe trauma cases. This study addresses this gap by leveraging machine learning techniques to develop a more accurate triage model.
🗒️ Study
Conducted as a multisite prediction study, researchers extracted data from the National Trauma Data Bank, focusing on patients aged 16 and older who were transported by ambulance. The study aimed to create a model that could predict severe trauma and critical resource use, utilizing a comprehensive set of variables recommended by the national guidelines.
📈 Results
The developed model achieved a sensitivity of 79.9% for predicting severe trauma, with an undertriage rate of 8.0% and an overtriage rate of 74.3%. For predicting critical resource use, the sensitivity was 77.4%, with an undertriage rate of 15.8%. The model’s areas under the curve were 0.755 for severe trauma and 0.736 for critical resource use, indicating strong predictive capabilities.
🌍 Impact and Implications
The implications of this study are significant for emergency medical services. By integrating machine learning into triage protocols, healthcare providers can enhance their ability to identify patients who require immediate and specialized care. This advancement not only improves patient outcomes but also optimizes resource allocation in emergency departments, ultimately leading to a more efficient healthcare system.
🔮 Conclusion
This study highlights the transformative potential of machine learning in prehospital trauma triage. The promising results of the developed model suggest that it can significantly enhance the performance of existing guidelines, reducing undertriage rates and improving patient care. Continued research and implementation of such technologies could pave the way for a new standard in emergency medical services.
💬 Your comments
What are your thoughts on the integration of machine learning in trauma triage? We would love to hear your insights! 💬 Share your comments below or connect with us on social media:
Enhancing Performance of the National Field Triage Guidelines Using Machine Learning: Development of a Prehospital Triage Model to Predict Severe Trauma.
Abstract
BACKGROUND: Prehospital trauma triage is essential to get the right patient to the right hospital. However, the national field triage guidelines proposed by the American College of Surgeons have proven to be relatively insensitive when identifying severe traumas.
OBJECTIVE: This study aimed to build a prehospital triage model to predict severe trauma and enhance the performance of the national field triage guidelines.
METHODS: This was a multisite prediction study, and the data were extracted from the National Trauma Data Bank between 2017 and 2019. All patients with injury, aged 16 years of age or older, and transported by ambulance from the injury scene to any trauma center were potentially eligible. The data were divided into training, internal, and external validation sets of 672,309; 288,134; and 508,703 patients, respectively. As the national field triage guidelines recommended, age, 7 vital signs, and 8 injury patterns at the prehospital stage were included as candidate variables for model development. Outcomes were severe trauma with an Injured Severity Score ≥16 (primary) and critical resource use within 24 hours of emergency department arrival (secondary). The triage model was developed using an extreme gradient boosting model and Shapley additive explanation analysis. The model’s accuracy regarding discrimination, calibration, and clinical benefit was assessed.
RESULTS: At a fixed specificity of 0.5, the model showed a sensitivity of 0.799 (95% CI 0.797-0.801), an undertriage rate of 0.080 (95% CI 0.079-0.081), and an overtriage rate of 0.743 (95% CI 0.742-0.743) for predicting severe trauma. The model showed a sensitivity of 0.774 (95% CI 0.772-0.776), an undertriage rate of 0.158 (95% CI 0.157-0.159), and an overtriage rate of 0.609 (95% CI 0.608-0.609) when predicting critical resource use, fixed at 0.5 specificity. The triage model’s areas under the curve were 0.755 (95% CI 0.753-0.757) for severe trauma prediction and 0.736 (95% CI 0.734-0.737) for critical resource use prediction. The triage model’s performance was better than those of the Glasgow Coma Score, Prehospital Index, revised trauma score, and the 2011 national field triage guidelines RED criteria. The model’s performance was consistent in the 2 validation sets.
CONCLUSIONS: The prehospital triage model is promising for predicting severe trauma and achieving an undertriage rate of <10%. Moreover, machine learning enhances the performance of field triage guidelines.
Author: [‘Chen Q’, ‘Qin Y’, ‘Jin Z’, ‘Zhao X’, ‘He J’, ‘Wu C’, ‘Tang B’]
Journal: J Med Internet Res
Citation: Chen Q, et al. Enhancing Performance of the National Field Triage Guidelines Using Machine Learning: Development of a Prehospital Triage Model to Predict Severe Trauma. Enhancing Performance of the National Field Triage Guidelines Using Machine Learning: Development of a Prehospital Triage Model to Predict Severe Trauma. 2024; 26:e58740. doi: 10.2196/58740