Visualized Lead Selection for Arrhythmia Classification Based on a Lead Activation Heatmap Using Multi-Lead ECGs

Visualizing the decision-making process is a key aspect of research regarding explainable arrhythmia recognition. This study proposed a visualized lead selection method to classify arrhythmia for multi-lead ECG signals. The proposed method has several advantages, as it uses a visualized approach to select effective leads, avoiding redundant leads and invalid information. It also captures the temporal dependencies of ECG signals and the complementary information between leads. The method deployed a lead activation heatmap (LA heatmap) based on a lead-wise network to select the proper 5 leads from 12-lead ECG heartbeats extracted from the public 2018 Chinese Physiological Signal Challenge database (CPSC 2018 DB), which were then fed into a ResBiTime network combining bidirectional long short-term memory (Bi-LSTM) networks and residual connections for a classification task of nine heartbeat categories (i.e., N, AF, I-AVB, RBBB, PAC, PVC, STD, LBBB, and STE). The results indicate an average precision of 93.25%, an average recall of 93.03%, an average F1-score of 0.9313, and that the proposed method can effectively extract additional information from ECG heartbeat data.