Fig. 5

Median density measurement of Hounsfield units reveals the best working model to predict moderate-to-severe anemia. Analysis of prediction performance for moderate-to-severe anemia with 2 variant feature subsets applying random forest (RF) machine learning algorithms (a–c). Monte Carlo cross-validation with 100 random splits (colored lines represent each single measurement) receiver operating characteristics (ROC) curve analysis of the validation cohort with mean ROC curve (blue) and ± 1 standard deviation (grey area) are shown for Median and Minimum (a) or Median only (b). RF maximum depth was 2 (a) and 1 (b). c The Box-Whisker Plots with 5–95% percentile for both cross-validated prediction models with the respective accuracy, area under the curve (AUC) and precision. Two-tailed, unpaired student’s t-test was applied for model comparison (c, p-values). d A decision tree with a depth of 1 for firstorder-Median. The gini value measures the impurity of the group. The decision tree minimizes the measure of impurity by a bisection of the group of 100 patients into two groups, one with 21 patients and a second with 79. The so-called gini gain, i.e., the sum of gini values of the child nodes weighted by the number of their members, becomes optimal for a selection threshold 36.5 of the firstorder-Median