Myocardial Infarction Classification Based on Convolutional Neural Network and Recurrent Neural Network

Abstract

Myocardial infarction is one of the most threatening cardiovascular diseases for human beings. With the rapid development of wearable devices and portable electrocardiogram (ECG) medical devices, it is possible and conceivable to detect and monitor myocardial infarction ECG signals in time. This paper proposed a multi-channel automatic classification algorithm combining a 16-layer convolutional neural network (CNN) and long-short term memory network (LSTM) for I-lead myocardial infarction ECG. The algorithm preprocessed the raw data to first extract the heartbeat segments; then it was trained in the multi-channel CNN and LSTM to automatically learn the acquired features and complete the myocardial infarction ECG classification. We utilized the Physikalisch-Technische Bundesanstalt (PTB) database for algorithm verification, and obtained an accuracy rate of 95.4%, a sensitivity of 98.2%, a specificity of 86.5%, and an F1 score of 96.8%, indicating that the model can achieve good classification performance without complex handcrafted features.

Urban traffic accident risk prediction for knowledge-based mobile multimedia service

“…In general, the DNN has a feedforward neural network structure that derives results by moving one layer at a time from the input layer to the output layer. However, RNNs [21][22][23] receiving attention recently are similar to a feedforward neural network, but the difference is that the output is received as input again. Figure 1 shows an RNN structure having a single neuron; Fig.…”

Machine learning as a tool for diagnostic and prognostic research in coronary artery disease

“…При комбинации CNN и RNN чувствительность и специфичность модели составила 92,4% и 97,7%, соответственно. В работе [56] авторы, использовав аналогичные показатели и когорту пациентов, с помощью усовершенствованной комбинации многослойной CNN и RNN продемонстрировали способность модели верифицировать ИМ по ЭКГ с точностью 95,4%, чувствительностью -98,2% и специфичностью -86,5%.…”

Deep Learning Methods in Classification of Myocardial Infarction by employing ECG Signals

“…It has the connectivity resembling the biological network. CNN has pooling layer, convolutional layer, and fully connected layer (15) . The equation 1represents the mathematical model for CNN.…”

“…With this data, it learns predicts and outputs the classified 12 rhythms of each of the 256 samples. In (6) , a multi-channel automatic classification algorithm has been developed by combining CNN and LSTM. Being a part of signal processing domain, ECG signal feature extraction causes more implementation difficulties and which are reduced by applying deep learning techniques.…”

“…The experiment provides a new insight into the application of attention mechanism and parallel feature extraction structure based on deep learning. In (13) , a deep learning method is introduced by combining CNN and RNN, and also a multi-channel CNN and LSTM network architecture is established, preprocessed ECG signals are segmented, spatial features in the multi-channel convolution network are extracted, and the temporal characteristics through LSTM are acquired. In recent years, with the development of deep learning, CNN and LSTM have achieved success.…”