Skip to main content

Table 6 Evaluation criteria for comparison performance of machine learning models (LR, RF, SVM and k-NN)

From: The efficacy of machine learning models in forecasting treatment failure in thoracolumbar burst fractures treated with short-segment posterior spinal fixation

Evaluation criteria

Model

variables

RF

LR

SVM

K-NN

Accuracy

0.948

0.917

0.933

0.927

Sensitivity

0.863

0.697

0.724

0.811

Specificity

0.959

0.945

0.943

0.950

Positive predictive value

0.748

0.773

0.691

0.698

Negative predictive value

0.901

0.857

0.763

0.722

AUC

0.911

0.823

0.844

0.877

  1. RF:Random forest; LR:Logistic regression; SVM:Support vector machine; k-NN: k- nearest neighbor; AUC: area under the curve of mean receiver operating characteristics
Back to article page

Journal of Orthopaedic Surgery and Research

ISSN: 1749-799X