Skip to main content

Table 2 Prediction of ultrasomics features analyzed by 9 machine learning algorithms for CALs progression in children with KD

From: Progression prediction of coronary artery lesions by echocardiography-based ultrasomics analysis in Kawasaki disease

Algorithms

ACC 

AUROC

Decision tree

0.80

0.49

SVM

0.83

0.67

RF

0.83

0.52

KNN

0.84

0.48

GBM

0.80

0.54

XGBM

0.78

0.46

LGBM

0.82

0.56

mLP

0.84

0.37

bNB

0.84

0.52

  1. Abbreviations: ACC, accuracy; AUROC, area under the receiver operating characteristic curve; SVM, support vector machine; RF, random forest; KNN, K-nearest neighbor; GBM, Gradient boosting machine; XGBM, Extreme gradient boosting machine; LGBM, Light gradient boosting machine; mLP, multi-Layer perceptron; bNB, Bernoulli naive Bayes
Back to article page

Italian Journal of Pediatrics

ISSN: 1824-7288

Contact us