Cardioish: Lead-Based Feature Extraction for ECG Signals

Abstract

Background: Electrocardiography (ECG) signals are commonly used to detect cardiac disorders, with 12-lead ECGs being the standard method for acquiring these signals. The primary objective of this research is to propose a new feature engineering model that achieves both high classification accuracy and explainable results using ECG signals. To this end, a symbolic language, named Cardioish, has been introduced. Methods: In this research, two publicly available datasets were used: (i) a mental disorder classification dataset and (ii) a myocardial infarction (MI) dataset. These datasets contain ECG beats and include 4 and 11 classes, respectively. To obtain explainable results from these ECG signal datasets, a new explainable feature engineering (XFE) model has been proposed. The Cardioish-based XFE model consists of four main phases: (i) lead transformation and transition table feature extraction, (ii) iterative neighborhood component analysis (INCA) for feature selection, (iii) classification, and (iv) explainable results generation using the recommended Cardioish. In the feature extraction phase, the lead transformer converts ECG signals into lead indexes. To extract features from the transformed signals, a transition table-based feature extractor is applied, resulting in 144 features (12 × 12) from each ECG signal. In the feature selection phase, INCA is used to select the most informative features from the 144 generated, which are then classified using the k-nearest neighbors (kNN) classifier. The final phase is the explainable artificial intelligence (XAI) phase. In this phase, Cardioish symbols are created, forming a Cardioish sentence. By analyzing the extracted sentence, XAI results are obtained. Additionally, these results can be integrated into connectome theory for applications in cardiology. Results: The presented Cardioish-based XFE model achieved over 99% classification accuracy on both datasets. Moreover, the XAI results related to these disorders have been presented in this research. Conclusions: The recommended Cardioish-based XFE model achieved high classification performance for both datasets and provided explainable results. In this regard, our proposal paves a new way for ECG classification and interpretation.

Keywords: Cardioish; feature extraction; machine learning; symbolic language.

Figure 1

Overview of the proposed Cardioish-based XFE model.

Figure 2

The replacement of the 12-leads and the proposed Cardioish symbols.

Figure 3

The computed confusion matrices of the proposed Cardioish-based XFE model on the MI and mental disorder detection datasets. (a) MI detection. Here, 0: Normal, 1: Anterior, 2: Anterior Lateral, 3: Anterior Septal, 4: Inferior, 5: Inferior Lateral, 6: Inferior Posterior, 7: Inferior Posterior Lateral, 8: Lateral, 9: Posterior and 10: Posterior Lateral. (b) Mental disorder detection dataset. Here, 0: Normal, 1: Bipolar, 2: Depression, 3: Schizophrenia.

Figure 4

The generated connectome graphs. The number indicates the count of transitions.

Figure 4

The generated connectome graphs. The number indicates the count of transitions.

Figure 5

The connectome graphs of the mental disorders were utilized in this study. Herein, the computed transition table related to mental disorders is defined. Figure 5 illustrates the cardiac connectome diagrams for (a) Bipolar disorder, (b) Depression, and (c) Schizophrenia detection. The red circles represent Cardioish symbols, while the edges depict the connections between these symbols. The numbers indicate the counts of the transitions.

Figure 6

The identical connectome graphs of the MIs. Herein, the computed transition table related to MIs are depicted using graphical demonstration to obtain cardiac connectome diagram. Figure 6 showcases the cardiac connectome diagrams for (a) Anterior MI, (b) Anterior Lateral MI, (c) Anterior Septal MI, (d) Inferior MI, (e) Inferior Lateral MI, (f) Interior Posterior MI, (g) Interior Posterior Lateral MI, (h) Lateral MI, (i) Posterior MI and (j) Posterior Lateral MI detection. The red circles represent Cardioish symbols, while the edges depict the connections between these symbols. The numbers indicate the counts of the transitions.