Skip to main content

Table 4 Confusion matrix for the prediction of NYHA class I-IV for HF among HF subjects using a two-stage neural network and the four CK metabolic parameters [PCr], [ATP], kf, and CK flux as input. The numbers at the top of the boxes are the number of cases classified correctly (green boxes), or misclassified (orange boxes), totaling 108 cases excluding the one case with uncertain NYHA class (See text). The percentages of the total are listed below the numbers. The % correct (green, bold font) and incorrect (red, bold font) are summarized for each output NYHA class (see Table 1 caption to guide interpretation)

From: Neural-network classification of cardiac disease from 31P cardiovascular magnetic resonance spectroscopy measures of creatine kinase energy metabolism