Using the National Trauma Data Bank (NTDB) and machine learning to predict trauma patient mortality at admission

doi:10.1371/journal.pone.0242166

Using the National Trauma Data Bank (NTDB) and machine learning to predict trauma patient mortality at admission

Fig 6

SHAP feature importance metrics for 4 patients that were incorrectly predicted as deceased.

Output values (bold), expressed as log odds ratio of probability of survival to probability of deceased (i.e. log()), that are < 0 represent deceased patients. Blue bars indicate that the feature value is increasing the probability of survival while red bars indicate that the feature is decreasing it. In all 4 cases, there was one feature that dominated the model prediction.

doi: https://doi.org/10.1371/journal.pone.0242166.g006