Skip to main content

Table 3 Neural network model confusion matrix

From: Predicting the risk of acute kidney injury after cardiopulmonary bypass: development and assessment of a new predictive nomogram

Sample

Measured

Prediction

Non-AKI

AKI

Accuracy (%)

Training set

Non-AKI

516

38

93.1%

AKI

147

58

28.3%

Overall percentage

87.4%

12.6%

75.6%

Testing set

Non-AKI

224

16

93.3%

AKI

57

26

31.3%

Overall percentage

87.0%

13.0%

77.4%

Back to article page

BMC Anesthesiology

ISSN: 1471-2253

Contact us