Skip to main content

Advertisement

Table 2 The performance of models on AL diagnosis for In-Sample Test

From: Mathematical models of amino acid panel for assisting diagnosis of children acute leukemia

  SVM RF XGBoost
Sensitivity (%) 92.23 ± 4.32 94.44 ± 5.27 95.86 ± 4.21
Specificity (%) 94.43 ± 3.77 91.76 ± 4.85 94.21 ± 4.96
Accuracy (%) 87.24 ± 4.23 88.76 ± 5.11 90.23 ± 4.89
AUCa 0.812 ± 0.036 0.821 ± 0.032 0.828 ± 0.035
  1. SVM: support vector machine; RF: random forest; XGboost: eXtreme Gradient Boosting; AUC: area under curve
  2. aROC analysis