Skip to main content
Fig. 2 | BMC Infectious Diseases

Fig. 2

From: Projecting COVID-19 disease severity in cancer patients using purposefully-designed machine learning

Fig. 2

Individual clinical variables weakly correlate with patient outcomes. a-f Each panel shows a variable (y-axis) grouped by patients in each of the three outcomes (x-axis). The number of patients (n) for which the variable was measured is shown for each group. For example, there were 206 non-severe patients, and their average age was 60.3 years old. Each bar shows average; error bars show standard deviation. a Age, b) C-reactive protein, c) D-dimer, d) Albumin, e) Lactate dehydrogenase, f) BMI. g-i Each panel shows an interaction between two variables (x and y axes). Each patient is represented by a colored dot (red = non-severe, blue = severe-early, green = severe-late). * = P < 0.01, ** = P < 0.001, *** = P < 0.0001, Welch’s two-sample T-test

Back to article page