Skip to main content
Insights into Imaging

Table 3 Comparison of different machine learning classifiers in the training and validation cohorts

From: Development of a simplified model and nomogram in preoperative diagnosis of pediatric chronic cholangitis with pancreaticobiliary maljunction using clinical variables and MRI radiomics

Classifiers

Training cohort (N = 100)

    

Validation cohort (N = 44)

    
 

AUC (95% CI)

ACC

SEN

SPE

Delong

AUC (95% CI)

ACC

SEN

SPE

Delong

LR

0.896 (0.826–0.967)

0.876

0.846

0.885

0.019#

0.878 (0.771–0.985)

0.841

0.852

0.824

0.556#

SVM

0.937 (0.877–0.997)

0.920

0.897

0.984

0.001##

0.847 (0.732–0.963)

0.818

0.941

0.741

0.106##

DT

0.817 (0.731–0.902)

0.810

0.615

0.934

0.025###

0.719 (0.516–0.972)

0.750

0.412

1.000

0.025###

  1. LR logistic regression; SVM support vector machine; DT decision tree; SEN sensitivity; SPE specificity; ACC accuracy; AUC area under the curve; CI confidence interval
  2. #LR versus SVM
  3. ##SVM versus DT
  4. ###DT versus LR
Back to article page