Key result
The proposed MTGBi-LSTM model achieved 99.2% accuracy on the MIT-BIH dataset and 96.48% accuracy on the CPSC 2018 dataset for arrhythmia classification, outperforming existing models.
Why the study?
Convolution neural network methods used for arrhythmia classification face an overfitting problem.
Does the MTGBi-LSTM deep learning method improve arrhythmia classification accuracy and sensitivity compared to existing methods?
Does the MTGBi-LSTM deep learning method improve arrhythmia classification accuracy and sensitivity compared to existing methods?
The proposed MTGBi-LSTM deep learning model demonstrates high accuracy and sensitivity for automated arrhythmia classification from ECG signals, outperforming existing methods like AFibNet.
Answers are grounded in this paper and cite their sources.
Should not yet alter clinical arrhythmia workflows; hypothesis-generating for multi-task ECG models pending external validation.
Early and accurate classification of arrhythmia helps the experts to select the treatment for the patient to increase the recovery rate. The deep learning method of convolution neural network (CNN) is used for classification, and this has an overfitting problem. In this research, the multi-task group bi-directional long short term memory (MTGBi-LSTM) method is proposed to increases the performance of arrhythmia classification. The multi-task learning technique learns two ECG signals in shared representation for effective learning. The global and intra LSTM method selects the relevant feature and easily escapes from local optima. The MTGBi-LSTM model learns the unique features in shared representation that helps to overcome overfitting problem and increases the learning rate of the model. The MTGBi-LSTM model in arrhythmia classification is evaluated on MIT-BIH dataset. The MTGBi-LSTM model has 96.48% accuracy, 97.73% sensitivity, existing AFibNet has 96.36% accuracy, and 93.65% sensitivity for arrhythmia classification in CPSC 2018 dataset.
No takes yet. Share an insight, caveat, or question.
Munawar et al. (2023) studied Arrhythmia (n=47). Multi-task group bi-directional long short term memory (MTGBi-LSTM) model vs. Existing machine learning models (e.g., CNN, AFibNet) was evaluated on Arrhythmia classification accuracy. The proposed MTGBi-LSTM model achieved 99.2% accuracy on the MIT-BIH dataset and 96.48% accuracy on the CPSC 2018 dataset for arrhythmia classification, outperforming existing models.
Synapse has enriched 10 related papers. Consider them for comparative context: