Objective: The Florida Adult Trauma Triage Criteria (FATTC) define specific parameters concerning injury mechanism and physiologic data that prompt paramedics to initiate a trauma alert and necessitate transport to a trauma center. In the state of Florida, paramedics are also given discretion to bring patients to the trauma center who do not meet those criteria. Our aim was to compare the injury characteristics and outcomes of adult patients who were evaluated in our trauma center after activation due to FATTC criteria vs. paramedic discretion (PD) and to identify predictors of PD. Methods: This retrospective study included all patients 18 years and older evaluated in our trauma center from January 1, 2007, to December 31, 2014. Descriptive statistics were computed for all variables. Bivariate and multivariate analyses were performed to compare demographic, injury severity, and outcome differences between groups. Results: A total of 13,963 patients met FATTC during the study period, and 1,811 were brought in by PD. PD patients had lower injury severity and crude mortality. Regression modeling of demographic and injury variables found that only the combination of older age and higher heart rate predicted PD when both were lower than FATTC alone. Conclusions: While PD patients were less seriously injured and had lower mortality, they experienced similar lengths of stay and resource utilization after presentation. Paramedics may be able to identify patients at risk for poor outcomes who would otherwise not be captured by FATTC.

Disease subtyping has been a critical aim of precision and personalized medicine. With the potential to improve patient outcomes, unsupervised and semi-supervised methods for determining phenotypes of subtypes have emerged with a recent focus on matrix and tensor factorization. However, interpretability of proposed models is debatable. Principal component analysis (PCA), a traditional method of dimensionality reduction, does not impose non-negativity constraints. Thus coefficients of the principal components are, in cases, difficult to translate to real physical units. Non-negative matrix factorization (NMF) constrains the factorization to positive numbers such that representative types resulting from the factorization are additive. Archetypal analysis (AA) extends this idea and seeks to identify pure types, archetypes, at the extremes of the data from which all other data can be expressed as a convex combination, or by proportion, of the archetypes. Using AA, this study sought to evaluate the sufficiency of AKI staging criteria through unsupervised subtyping. Archetype analysis failed to find a direct 1:1 mapping of archetypes to physician staging and also did not provide additional insight into patient outcomes. Several factors of the analysis such as quality of the data source and the difficulty in selecting features contributed to the outcome. Additionally, after performing feature selection with lasso across data subsets, it was determined that current staging criteria is sufficient to determine patient phenotype with serum creatinine at time of diagnosis to be a necessary factor.