Follow-Up and Risk Assessment in Patients with Myocardial Infarction Using Artificial Neural Networks

Table 3

Classifier performance for different neural network architectures.

Number	Neural network architecture	Learning Rate	Accuracy	Sensitivity	Specificity	-measure
(1)	11-13-1	0.2	0.73	0.6	0.8	0.6
(2)	11-15-1	0.2	0.8	0.6	0.9	0.6
(3)	11-30-1	0.3	0.8	0.6	0.9	0.6
(4)	11-15-7-1	0.1	0.73	0.6	0.8	0.6
(5)	11-25-30-1	0.2	0.88	0.81	0.93	0.85
(6)	11-25-40-1	0.25	0.73	0.8	0.7	0.6