Procedia Computer Science · 2018 · 75 citations · 16 references
ComputingCardiologyComputer ScienceBiomedical Signal ProcessingElectrophysiologyMachine LearningCardiac ArrhythmiasCardiac Signal ProcessingDeep LearningElectrocardiogram AnalysisElectrocardiographyNeural NetworksConvolutional Neural NetworksCross-validationData ProcessingDeep Learning DetectionDeep Learning-based DetectionDeep Learning-based DiagnosisGated Recurrent Unit NetworksLong Short-term Memory Networks
Cardiac arrhythmia is a condition where heart beat is irregular. The goal of this paper is to apply deep learning techniques in the diagnosis of cardiac arrhythmia using ECG signals with minimal possible data pre-processing. We employ convolutional neural network (CNN), recurrent structures such as recurrent neural network (RNN), long short-term memory (LSTM) and gated recurrent unit (GRU) and hybrid of CNN and recurrent structures to automatically detect the abnormality. Unlike the conventional analysis methods, deep learning algorithms don’t have feature extraction based analysis methods. The optimal parameters for deep learning techniques are chosen by conducting various trails of experiments. All trails of experiments are run for 1000 epochs with learning rate in the range [0.01-0.5]. We obtain five-fold cross validation accuracy of 0.834 in distinguishing normal and abnormal (cardiac arrhythmia) ECG with CNN-LSTM. Moreover, the accuracy obtained by other hybrid architectures of deep learning algorithms is comparable to the CNN-LSTM.
16
Sepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 98.1K citations
PhysioBank, PhysioToolkit, and PhysioNet
Ary L. Goldberger, Luı́s A. Nunes Amaral, Leon Glass et al. · Circulation · 2000 · 14.5K citations · Full text
Jeffrey L. Elman · Cognitive Science · 1990 · 10.8K citations
TensorFlow: A system for large-scale machine learning
Martı́n Abadi, Paul Barham, Jianmin Chen et al. · arXiv (Cornell University) · 2016 · 8.8K citations · Full text