Research Article

Identification of Potential Type II Diabetes in a Large-Scale Chinese Population Using a Systematic Machine Learning Framework

Table 4

The results of classification algorithms.

Testing criteriaDTRFABXGB

Confusion matrix
Accuracy0.8320.8730.8780.906
Precision0.8230.8620.8710.910
Recall0.8450.8890.8880.902
0.8340.8750.8790.906
AUC0.8320.9470.9480.968

Abbreviations: AUC: the area under the receiver operating characteristic (ROC) curve; DT: decision tree; RF: random forest.