Skip to main content

Table 2 Predictive performance comparison of the five types of machine learning algorithms in the validation sets

From: Application of machine learning model to predict osteoporosis based on abdominal computed tomography images of the psoas muscle: a retrospective study

Model

AUROC

Sensitivity

Specificity

Accuracy

LR

0.85

0.73

0.86

0.80

XGBoost

0.82

0.70

0.75

0.72

GNB

0.80

0.73

0.86

0.80

GBM

0.86

0.70

0.92

0.81

RF

0.87

0.73

0.86

0.80

SVM

0.81

0.86

0.55

0.71

  1. Abbreviations: LR Logistic regression, GBM Gradient boosting machine, RF Random forest, GNB Gaussian naïve Bayes, XGBoost Extreme gradient boosting, SVM Support vector machines, AUROC area under the receiver operating characteristic
Back to article page

BMC Geriatrics

ISSN: 1471-2318

Contact us