Interpretable Machine Learning to Optimize Early In-Hospital Mortality Prediction for Elderly Patients with Sepsis: A Discovery Study

<div>(a) Feature significance ranking for the feature representation methods of the XGBoost and (b) top 20 features ranking of importance using the SHAP values.</div>

Computational and Mathematical Methods in Medicine

fig3

Figure 3

Figure 3: Interpretable Machine Learning to Optimize Early In-Hospital Mortality Prediction for Elderly Patients with Sepsis: A Discovery Study 