Table 2 Comparison of performance metrics for six models (internal validation).
Model | AUC (95% CI) | Accuracy (95% CI) | F1 Score (95% CI) | Sensitivity (95% CI) | Specificity (95% CI) |
|---|---|---|---|---|---|
Random Forest | 0.79 [0.68, 0.88] | 0.65 [0.53, 0.75] | 0.64 [0.52, 0.77] | 0.76 [0.61, 0.91] | 0.55 [0.40, 0.70] |
DNN | 0.78 [0.67, 0.87] | 0.69 [0.59, 0.79] | 0.67 [0.54, 0.79] | 0.72 [0.56, 0.86] | 0.67 [0.54, 0.81] |
SVM | 0.76 [0.64, 0.86] | 0.69 [0.58, 0.79] | 0.56 [0.37, 0.71] | 0.45 [0.30, 0.62] | 0.88 [0.78, 0.98] |
LightGBM | 0.71 [0.58, 0.82] | 0.66 [0.55, 0.75] | 0.63 [0.50, 0.77] | 0.70 [0.53, 0.86] | 0.62 [0.48, 0.77] |
CatBoost | 0.77 [0.66, 0.87] | 0.66 [0.55, 0.76] | 0.65 [0.50, 0.76] | 0.73 [0.57, 0.88] | 0.60 [0.45, 0.75] |
Logistic | 0.86 [0.77, 0.93] | 0.76 [0.66, 0.84] | 0.73 [0.59, 0.84] | 0.73 [0.57, 0.87] | 0.79 [0.66, 0.91] |
