Table 11 Comparative analysis of each individual model with our proposed framework.

From: A hybrid ResNet-ViT approach to bridge the global and local features for myocardial infarction detection

Approaches

Precision (%)

Specificity (%)

F1 score (%)

Sensitivity (%)

False positive rate (%)

False negative rate (%)

ViT

0.93

0.921

0.929

0.938

0.078

0.061

ResNet

0.94

0.939

0.935

0.93

0.06

0.069

Proposed approach

0.95

0.95

0.954

0.959

0.049

0.04

Back to article page