The AI model achieved an AUROC of 0.83 for detecting cardiac ischemia from 12-lead ECGs, using three different XAI methods to visualize its decision-making process.
Explainable AI methods can visualize the decision-making process of deep learning models detecting cardiac ischemia from ECGs, but variability between methods highlights the need for further clinical validation before robust clinical use.
Absolute Event Rate: 0% vs 0%
Abstract Background (2) Saliency Maps, based on input gradients to highlight sensitive regions; and (3) SmoothGrad×SIGN, a technique that combines noise smoothing and signal-domain enhancements for clearer visual attributions. Our model achieved an AUROC of 0.83 for cardiac ischemia detection from 12-lead ECGs. All three XAI methods successfully visualized the model's decision-making process. To enhance interpretability, XAI outputs were similarly overlaid onto ECGs (Figure 1B: Grad-CAM, 1C: Saliency Map, 1D: SmoothGrad×SIGN). Interestingly, while all methods highlighted clinically relevant regions, the specific areas identified varied among methods. Conclusions We implemented three XAI methods for the visualization of AI-based interpretations of surface ECGs in an ED context. Overlaying the XAI outputs onto ECG curves facilitates clinical use. Since the three XAI methods highlight different regions in the same ECG when evaluated by the same model, further research is required. The next step will be a systematic evaluation of XAI methods incorporating the expertise of clinical domain specialists, aiming to enhance the practical value and trustworthiness of XAI in acute cardiovascular care.
Krishna et al. (Thu,) reported a other. The AI model achieved an AUROC of 0.83 for detecting cardiac ischemia from 12-lead ECGs, using three different XAI methods to visualize its decision-making process.