Table 1.
Admission characteristics of patients from internal validation cohort by outcome.
Table 2.
Admission laboratory findings of patients from internal validation cohort by outcome.
Fig 1.
Receiver operating characteristic curves of the machine-learning model for the different classification algorithms.
Panel A shows the internal crossvalidation results and panel B shows the external testing results. The results of a risk classification only based on age are also shown for comparison.
Table 3.
Admission demographic and clinical characteristics of patients from external testing cohort by outcome.
Table 4.
Relative importance of each variable according to mean decrease accuracy, scaled to the most important one.