Skip to main content

Table 2 Definition of true positive, false positive, true negative and false negative

From: The application of unsupervised deep learning in predictive models using electronic health records

 Predicted ValueMeasures
10  
True Value1true positive (a)false negative (c)Sensitivity: a/(a + c)Recall: a/(a + c)
0false positive (b)true negative (d)Specificity: d/(d + b) 
Measures PPV: a/(a + b)NPV: d/(c + d)  
 Precision: a/(a + b)