Skip to main content

Table 3 Comparisons of predictive capability of the three algorithm models

From: Blood oxygen level dependent magnetic resonance imaging for detecting pathological patterns in lupus nephritis patients: a preliminary study using a decision tree model

Diagnosis Test Parameters

Decision Tree Model

Line Discriminant Model

Logistic Regression Model

Sensitivity

0.718a,b

0.595c

0.787

Specificity

0.639b

0.637c

0.380

Accuracy

0.685a,b

0.613

0.618

AUROCC

0.765a b

0.629c

0.662

  1. AUROCC area under the ROC curve
  2. a Decision tree model vs Line discriminant model, p < 0.001
  3. b Decision tree model vs Logistic regression model, p < 0.001
  4. c Line discriminant model vs Logistic regression model, p < 0.001
Back to article page

BMC Nephrology

ISSN: 1471-2369

Contact us