Table III.

The confusion matrix of our prediction models

The 1:1 model (high-coverage model) refers to the optimal model trained with an equal number of positive and negative examples. The 1:100 model (high-confidence model) refers to the optimal model trained with the expanded example data set in which the positive-to-negative ratio is 1:100. All measurements are provided in the format of mean ± sd computed by 100-iteration bootstrap evaluation.

Predicted	Actual
	Positive	Negative
Positive	TP: 3,498.32 ± 8.28 (1:1 model), 1,201.28 ± 5.57 (1:100 model)	FP: 389.88 ± 10.44 (1:1 model), 209.44 ± 5.43 (1:100 model)
Negative	FN: 640.68 ± 8.28 (1:1 model), 2,937.72 ± 5.57 (1:100 model)	TN: 3,749.12 ± 10.44 (1:1 model), 413,690 ± 5.43 (1:100 model)