Figure 3 | Scientific Reports

Figure 3

From: Development and validation of deep learning ECG-based prediction of myocardial infarction in emergency department patients

Figure 3

Four representative NSTEMIs correctly classified with high probability. Four Grad-CAM plots of NSTEMIs correctly classified with high probability, highlighting the parts in the ECG that the model focuses on for its prediction. Gradients corresponding to the activations in the first convolutional layer of the neural network are averaged to get the proportional importance of each channel, which is then used to compute a proportional mean of the activations. Positive values obtained were plotted as blue disks overlaid on top of the ECG, with size proportional to its magnitude.

Back to article page