An Overview of Algorithms for Myocardial Infarction Diagnostics Using ECG Signals: Advances and Challenges

Myocardial infarction (MI) boasts the highest mortality rate, striking suddenly and often stealthily. Conducting an electrocardiogram (ECG) examination stands as the most straightforward and rapid method to diagnose MI, rendering research into MI intelligent diagnosis via ECG of paramount importance. We developed a search and selection strategy to extract articles from Google Scholar and PubMed and analyzed the existing studies of MI intelligent diagnosis algorithms using ECGs according to three typical aspects: MI data enhancement, MI diagnosis models, and interpretability of models. First, techniques for enhancing MI data were summarized, and then, handcrafted features and models with automatic feature extraction were discussed. Meanwhile, the interpretability of MI diagnosis models was analyzed, including class activation mapping with gradient (Grad-CAM), Shapley additive explanations (SHAP), multihead attention mechanism, and knowledge graph. A comparative analysis encompassing the methodologies, datasets, the number of leads and input modalities, performance evaluation, as well as interpretability for MI diagnosis was given. We found that deep learning has achieved good performance and knowledge graph accomplished the best interpretability. Finally, limitations and challenges were pointed out, including lack of high-quality MI records, absence of dynamic ECG records, effective representations of different ECG morphologies, the promotion of models under inter-patient paradigm, the improvement of transparency and interpretability of MI diagnosis, and the high complexity of models. To our knowledge, this is the first comprehensive and multidimensional review analyzing intelligent diagnosis of MI using ECG signals.