Summary of the dataset features.

In this table the 63 features analyzed in this work, reported in the second column, are grouped into 6 classes, listed in the first column. The third and fourth columns show the feature occurrence in the dataset in dead and recovered subjects, respectively. The last column reports a description of the feature values: for continuous variables the 5th and the 95th percentiles indicated as [P5, P95] are reported, while for categorical variables their values are reported within curly brackets.