Automated stratification of trauma injury severity across multiple body regions using multi-modal, multi-class machine learning models

Jifan Gao; Guanhua Chen; Ann P O'Rourke; John Caskey; Kyle A Carey; Madeline Oguss; Anne Stey; Dmitriy Dligach; Timothy Miller; Anoop Mayampurath; Matthew M Churpek; Majid Afshar

doi:10.1093/jamia/ocae071

Automated stratification of trauma injury severity across multiple body regions using multi-modal, multi-class machine learning models

J Am Med Inform Assoc. 2024 Apr 8:ocae071. doi: 10.1093/jamia/ocae071. Online ahead of print.

Authors

Jifan Gao¹, Guanhua Chen¹, Ann P O'Rourke², John Caskey³, Kyle A Carey³, Madeline Oguss³, Anne Stey^{4

5}, Dmitriy Dligach⁶, Timothy Miller^{7

8}, Anoop Mayampurath^{1

3}, Matthew M Churpek^{1

3}, Majid Afshar^{1

3}

Affiliations

¹ Department of Biostatistics and Medical Informatics, University of Wisconsin-Madison, Madison, WI 53726, United States.
² Department of Surgery, University of Wisconsin-Madison, Madison, WI 53792, United States.
³ Department of Medicine, University of Wisconsin-Madison, Madison, WI 53705, United States.
⁴ Department of Surgery, Northwestern University Feinberg School of Medicine, Chicago, IL 60611, United States.
⁵ Center of Health Services and Outcomes Research, Institute for Public Health and Medicine, Chicago, IL 60611, United States.
⁶ Department of Computer Science, Loyola University Chicago, Chicago, IL 60660, United States.
⁷ Computational Health Informatics Program, Boston Children's Hospital, Boston, MA 02115, United States.
⁸ Department of Pediatrics, Harvard Medical School, Boston, MA 02115, United States.

PMID: 38587875
DOI: 10.1093/jamia/ocae071

Abstract

Objective: 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 (EHRs) data.

Materials and methods: Our study utilized clinical documents and structured EHR variables linked with the trauma registry data to create 2 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. Temporal validation was undertaken to ensure the models' temporal generalizability. Additionally, analyses to assess the variable importance were conducted.

Results: Both models demonstrated impressive performance in categorizing leg injuries, achieving high accuracy with macro-F1 scores of over 0.8. Additionally, they showed considerable accuracy, with macro-F1 scores exceeding or near 0.7, in assessing injuries in the areas of the chest and head. We showed in our variable importance analysis that the most important features in the model have strong face validity in determining clinically relevant trauma injuries.

Discussion: 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.

Conclusions: Our multi-modal, multiclass models can provide accurate stratification of trauma injury severity and clinically relevant interpretations.

Keywords: artificial intelligence; multimodality deep learning; trauma.

Abstract

Grants and funding