Skip to main content

Table 1 The efficacy of KNN, LR, SVM, DT, MLP and XGboost in the training set

From: Comparison and development of machine learning tools for the prediction of chronic obstructive pulmonary disease in the Chinese population

MetricsKNNLRSVMDTMLPXGboost
(95% CI)(95% CI)(95% CI)(95% CI)(95% CI)(95% CI)
AU-ROC0.83 (0.76–0.86)0.89 (0.83–0.93)0.88 (0.84–0.91)0.85 (0.77–0.88)0.80 (0.74–0.84)0.94 (0.89–0.98)
AU-PRC0.93 (0.90–0.94)0.96 (0.93–0.98)0.95 (0.89–0.96)0.95 (0.94–0.97)0.92 (0.89–0.94)0.97 (0.93–0.99)
Accuracy0.82 (0.77–0.86)0.83 (0.77–0.86)0.84 (0.82–0.88)0.89 (0.84–0.92)0.76 (0.74–0.79)0.91 (0.88–0.95)
Precision0.88 (0.83–0.92)0.86 (0.83–0.89)0.88 (0.84–0.91)0.92 (0.89–0.95)0.76 (0.74–0.79)0.95 (0.93–0.96)
Recall0.88 (0.85–0.90)0.91 (0.85–0.96)0.92 (0.90–0.95)0.94 (0.92–0.98)0.99 (0.98–1.00)0.93 (0.88–0.97)
F1 score0.88 (0.84–0.90)0.89 (0.84–0.91)0.90 (0.88–0.92)0.93 (0.91–0.96)0.86 (0.85–0.88)0.94 (0.91–0.96)
MCC0.54 (0.39–0.64)0.54 (0.39–0.61)0.58 (0.51–0.69)0.70 (0.57–0.79)0.22 (0.10–0.40)0.77 (0.70–0.86)
SPC0.67 (0.53–0.80)0.59 (0.48–0.71)0.63 (0.50–0.76)0.79 (0.72–0.85)0.10 (0.05–0.26)0.85 (0.81–0.90)
NPV0.66 (0.56–0.71)0.72 (0.56–0.83)0.74 (0.69–0.79)0.81 (0.70–0.98)0.87 (0.54–1.00)0.81 (0.73–0.89)
  1. AU-ROC area under the receiver operating characteristic curve, AU-PRC area under the precision-recall curve, MCC Matthews correlation coefficient, SPC specificity, NPV negative prognostic value, KNN k-nearest neighbors classifier, LR logistic regression, SVM support vector machine, DT decision tree, MLP multilayer perceptron, 95% CI 95% confidence interval