Figure 4
From: Budget constrained machine learning for early prediction of adverse outcomes for COVID-19 patients
Feature importance of a trained XGBoost model. The higher the absolute SHAP value, the greater the contribution of the feature to the predicted outcome. The SHAP values are averaged over 5 folds of test splits that span the whole dataset. (A) The top three most important features for predicting ventilation are Procalcitonin, Lymphocytes Absolute and Pulse Oximetry. (B) The top three most important features for predicting mortality are Age, BUN and Potassium.
