Skip to main content
Fig. 2 | Critical Care

Fig. 2

From: Machine learning identifies ICU outcome predictors in a multicenter COVID-19 cohort

Fig. 2

EBM prediction model showing importance of risk factors predicting “survival” in COVID-19 ICU patients including admission data. Top A significant risk factors for outcome after analysis of admission data and weighed according to their importance for outcome. bottom) B importance of age for outcome and distribution of age data C platelet/neutrophil ratio and distribution of data on admission D initial D-dimer serum values and distribution of data determined on admission E importance of Horovitz quotient (PaO2/FiO2) for outcome and distribution of data on admission F initial hemoglobin values and distribution of data on admission G initial procalcitonin (PCT) serum values and distribution of data on admission. Grey indicates patients that did not survive ICU therapy, orange indicates patients that did survive ICU therapy

Back to article page