Automated stratification of trauma injury severity across multiple body regions using multi-modal, multi-class machine learning models
Presenter
Statement of Purpose
The timely stratification of trauma injury severity can enhance the quality of trauma care but it requires intense manual annotation from certified trauma coders. The objective of this study is to develop machine learning models for the stratification of trauma injury severity across various body regions using clinical text and structured electronic health records (EHR) data. Our study utilized clinical documents and structured EHR variables linked with the trauma registry data to create two machine learning models with different approaches to representing text. The first one fuses concept unique identifiers (CUIs) extracted from free text with structured EHR variables, while the second one integrates free text with structured EHR variables. Both models can provide accurate stratification of trauma injury severity and clinically relevant interpretations. The CUI-based model achieves comparable performance, if not higher, compared to the free-text-based model, with reduced complexity. Furthermore, integrating structured EHR data improves performance, particularly when the text modalities are insufficiently indicative. To the best of our knowledge, this is the first work that identifies trauma injury severity across multiple body regions beyond binary classification. Our models have great potential to be implemented in health systems and potentially automate trauma data capture in registries, particularly in lower-resourced settings for quality improvement.
Learning Outcomes
Participants will be able to:
- Analyze the importance of automatic trauma injury severity stratification
- Construct machine learning models for trauma care
- Integrate varied clinical text forms into machine learning
- Evaluate the advantages of integrating structured EHR data
- Investigate variable importance analysis