Table 3.

Detailed results of machine learning classifiers for prediction of mortality and post-surgery prolonged LOS.

Model	Precision	Recall	F-Score	Accuracy	AUROC
Mortality Prediction
Deep Neural Network	0.94 ± 0.03	0.86 ± 0.04	0.89 ± 0.03	0.89 ± 0.04	0.95 ± 0.02
Gradient Boosting	0.87 ± 0.03	0.78 ± 0.04	0.83 ± 0.04	0.84 ± 0.04	0.90 ± 0.04
Random Forest	0.71 ± 0.04	0.27 ± 0.03	0.43 ± 0.03	0.75 ± 0.05	0.84 ± 0.03
Decision Tree	0.43 ± 0.04	0.14 ± 0.05	0.29 ± 0.06	0.65 ± 0.04	0.58 ± 0.04
Ridge Regression	0.43 ± 0.04	0.10 ± 0.04	0.28 ± 0.03	0.61 ± 0.04	0.55 ± 0.03
Prolonged LOS Prediction
Deep Neural Network	0.85 ± 0.04	0.91 ± 0.04	0.89 ± 0.04	0.85 ± 0.03	0.94 ± 0.04
Gradient Boosting	0.87 ± 0.04	0.82 ± 0.05	0.83 ± 0.03	0.82 ± 0.03	0.88 ± 0.03
Random Forest	0.62 ± 0.03	0.51 ± 0.05	0.55 ± 0.04	0.61 ± 0.03	0.67 ± 0.03
Decision Tree	0.56 ± 0.04	0.49 ± 0.04	0.52 ± 0.05	0.53 ± 0.04	0.59 ± 0.05
Ridge Regression	0.59 ± 0.05	0.32 ± 0.04	0.35 ± 0.04	0.63 ± 0.06	0.54 ± 0.07