Table 2 Subtype predictive accuracy and area under the receiver operating characteristic curve of unilateral subtype of primary aldosteronism for each classifier in the test cohort (n = 46).

From: Machine learning based models for prediction of subtype diagnosis of primary aldosteronism using blood test

Classifiers

Accuracy (%)

Sensitivity (%)

Specificity (%)

AUC (95% confidence interval)

LR

89.1

83.3

92.9

0.948 (0.89–1.000)

SVM

84.8

66.7

96.4

0.966 (0.925–1.000)

RF

95.7

94.4

96.4

0.990 (0.971–1.000)

GBDT

87.0

72.2

96.4

0.976 (0.941–1.000)

  1. AUC indicates area under the receiver operating characteristic curve; LR, logistic regression; SVM, support vector machines; RF, random forests; GBDT, and gradient boosting decision trees.
Back to article page