Table 2.

Performance Comparison of Machine Learning Models for Death Prediction

Variables	AUC (95% CI)	SE (95% CI)	SP (95% CI)	PPV (95% CI)	NPV (95% CI)	ACC (95% CI)
Logistic regression - all variables (LO-A)	0.49 (0.46, 0.51)	1.00 (0.98, 1.00)	0.00 (NA, 0.01)	0.28 (0.00, 1.00)	NA (0.00, 1.00)	0.28 (0.25, 0.32)
Logistic regression - selected variables (LO-S)	0.68 (0.62, 0.73)	0.53 (0.45, 0.61)	0.75 (0.70, 0.79)	0.43 (0.38, 0.52)	0.81 (0.76, 0.85)	0.69 (0.65, 0.73)
Support Vector Machine (SVM)	0.68 (0.63, 0.74)	0.58 (0.50, 0.66)	0.70 (0.66, 0.75)	0.42 (0.37, 0.50)	0.82 (0.77, 0.85)	0.68 (0.64, 0.71)
Naïve Bayes (NB)	0.70 (0.65, 0.75)	0.60 (0.51, 0.68)	0.73 (0.69, 0.78)	0.45 (0.40, 0.54)	0.83 (0.78, 0.86)	0.70 (0.66, 0.73)
Neural Network (NN)	0.48 (0.43, 0.54)	0.19 (0.13, 0.27)	0.86 (0.82, 0.89)	0.33 (0.27, 0.43)	0.75 (0.65, 0.80)	0.68 (0.64, 0.72)
Decision Tree (DT)	0.60 (0.56, 0.64)	0.27 (0.20, 0.35)	0.91 (0.88, 0.94)	0.53 (0.44, 0.62)	0.77 (0.70, 0.83)	0.75 (0.71, 0.78)
Light GBM (LGBM)	0.70 (0.65, 0.75)	0.75 (0.67, 0.82)	0.56 (0.51, 0.61)	0.39 (0.34, 0.48)	0.86 (0.80, 0.88)	0.61 (0.57, 0.65)

This table presents the area under the curve (AUC), sensitivity (SE), specificity (SP), positive predictive value (PPV), negative predictive value (NPV), and accuracy (ACC) of various machine learning models applied to outcome prediction. The models include logistic regression with all variables (LO), logistic regression with selected variables (LO), Support Vector Machine (SVM), Naïve Bayes (NB), Neural Network (NN), Decision Tree (DT), and Light GBM (LGBM). Each model's performance is quantified with corresponding 95% confidence intervals (CI) for the presented metrics.