Skip to main content

Table 4 Performance of the different algorithms

From: Machine learning approaches for the prediction of postoperative complication risk in liver resection patients

Type of ML

Accuracy

(95% CI)

Sensitivity

Specificity

AUC

(95% CI)

Logistic Regression (LR)

0.83 [0.77,0.89]

0.72

0.60

0.82 [0.66,0.98]

T-wise Regression (TR)

0.79 [0.73,0.84]

0.70

0.59

0.79 [0.66,0.92]

Decision Tree: C5.0 (C5.0)

0.92 [0.83,1]

0.87

0.94

0.91 [0.77,1]

Decision Tree: CART (CART)

0.87 [0.80,0.94]

0.69

0.91

0.82 [0.70,0.94]

Support Vector Machine (SVM)

0.81 [0.75,0.87]

0.50

0.94

0.72 [0.59,0.85]

Random Forest (RF)

0.77 [0.71,0.84]

0.56

0.86

0.7 [0.60,0.81]