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

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.

Puberty Blocker, Leuprolide, Reduces Sex Differences in Rough-and-Tumble Play and Anxiety-like Behavior in Juvenile Rats

We examined the effect of the puberty blocker, leuprolide acetate, on sex differences in juvenile rough-and-tumble play behavior and anxiety-like behavior in adolescent male and female rats. We also evaluated leuprolide treatment on gonadal and pituitary hormone levels and activity-regulated cytoskeleton-protein messenger RNA levels within the adolescent amygdala, a region important both for rough-and-tumble play and anxiety-like behavior. Our findings suggest that leuprolide treatment lowered anxiety-like behavior during adolescent development, suggesting that the maturation of gonadotropin-releasing hormone systems may be linked to increased anxiety. These data provide a potential new model to understand the emergence of increased anxiety triggered around puberty. Leuprolide also reduced masculinized levels of rough-and-tumble play behavior, lowered follicle-stimulating hormone, and produced a consistent pattern of reducing or halting sex differences of hormone levels, including testosterone, growth hormone, thyrotropin, and corticosterone levels. Therefore, leuprolide treatment not only pauses sexual development of peripheral tissues, but also reduces sex differences in hormones, brain, and behavior, allowing for better harmonization of these systems following gender-affirming hormone treatment. These data contribute to the intended use of puberty blockers in stopping sex differences from developing further with the potential benefit of lowering anxiety-like behavior.