Skip to main content

Table 3 Prediction efficacy of KBD among adolescents by different machine learning methods

From: Identifying discriminative features for diagnosis of Kashin-Beck disease among adolescents

Diagnostic Model

Sensitivity (%)

Specificity (%)

Accuracy (%)

AUC

RFA

100.00

99.22

99.63

1.00

ANNs

99.86

99.66

99.76

1.00

SVM

88.64

98.51

93.63

0.94

LR

96.20

96.89

96.50

0.97

  1. Sensitivity = Predictive Positive/True Positive × 100%; Specificity = Predictive Negative/True Negative × 100%; Accuracy = (Predictive Positive + Predictive Negative)/(True Positive + True Negative) × 100%; AUC = Area under the receiver operating characteristic curve (ROC)
  2. RFA Random forest algorithm, ANNs Artificial neural networks, SVM Support vector machine, LR Logistic regression
Back to article page

BMC Musculoskeletal Disorders

ISSN: 1471-2474

Contact us