Detection of Myocardial Infarction Using ECG and Multi-Scale Feature Concatenate

Abstract

Diverse computer-aided diagnosis systems based on convolutional neural networks were applied to automate the detection of myocardial infarction (MI) found in electrocardiogram (ECG) for early diagnosis and prevention. However, issues, particularly overfitting and underfitting, were not being taken into account. In other words, it is unclear whether the network structure is too simple or complex. Toward this end, the proposed models were developed by starting with the simplest structure: a multi-lead features-concatenate narrow network (N-Net) in which only two convolutional layers were included in each lead branch. Additionally, multi-scale features-concatenate networks (MSN-Net) were also implemented where larger features were being extracted through pooling the signals. The best structure was obtained via tuning both the number of filters in the convolutional layers and the number of inputting signal scales. As a result, the N-Net reached a 95.76% accuracy in the MI detection task, whereas the MSN-Net reached an accuracy of 61.82% in the MI locating task. Both networks give a higher average accuracy and a significant difference of p < 0.001 evaluated by the U test compared with the state-of-the-art. The models are also smaller in size thus are suitable to fit in wearable devices for offline monitoring. In conclusion, testing throughout the simple and complex network structure is indispensable. However, the way of dealing with the class imbalance problem and the quality of the extracted features are yet to be discussed.

Rapid Detection of Cardiac Pathologies by Neural Networks Using ECG Signals (1D) and sECG Images (3D)

“…This research described how to use RNNs (LSTM) and CNNs (ResNet34) to detect cardiac pathologies. First, the role of LSTMs is to classify number sequences [18]. In other words, it transforms the data entered so that they circulate through the network even in the following instant.…”

A Robustness Evaluation of Machine Learning Algorithms for ECG Myocardial Infarction Detection

“…The recent research on ECG classification computer-aid systems is based on new techniques of artificial intelligence. Various types of these techniques have been investigated and analyzed for this purpose and other purposes [ 22 , 23 ], such as decision trees [ 24 ], random forest (RF) [ 25 , 26 , 27 ], support vector machine (SVM) [ 28 , 29 ], k-nearest neighbor (KNN) [ 30 ], the hybrid FFPSONeural network classifier [ 31 ], in addition to other methods, such as [ 32 , 33 , 34 ]. In [ 35 ], the authors incorporated two categories, normal and MI, into their investigation.…”

Development and performance evaluation of a coronary artery disease prediction system with transfer learned model based on single lead and multi-lead ECG & TMT-ECG signals

“…There are large repository datasets available related to heart diseases such as arrhythmia (MIT-BIH [12], Physio-bank competition 2017 [13]), Arterial fibrillation [14], and cardiovascular diseases such as CAD [15], but compared to the first two, coronary artery disease-related datasets are scarcely found. The available repository dataset are 8 CAD patients and 11 normal patients dataset [16].…”