Fig. 1From: Development and evaluation of regression tree models for predicting in-hospital mortality of a national registry of COVID-19 patients over six pandemic surgesRegression tree for survival (#ch.com is the number of chronic comorbidities) based on patient data available at admission. Each node shows the survival probabilities in that group as well as the number of patients in that group. Survival probabilities include a 95% confidence interval based on the percentile bootstrap method on 200 samplesBack to article page