Key result
The proposed multimodal neural network, which processes both 12-lead ECG signals and patient metadata, achieved a cardiac arrhythmia recognition accuracy of 63.00%, outperforming the LSTM-only model.
Why the study?
Existing neural network methods for automatic electrocardiogram arrhythmia classification do not take into account patient characteristics.
Does a multimodal neural network incorporating patient metadata (age and gender) alongside 12-lead ECG signals improve the recognition accuracy of cardiac arrhythmias?
Does a multimodal neural network incorporating patient metadata (age and gender) alongside 12-lead ECG signals improve the recognition accuracy of cardiac arrhythmias?
Absolute Event Rate: 63% vs 55.55%
A multimodal neural network that integrates 12-lead ECG signals with patient age and gender metadata improves the accuracy of automated cardiac arrhythmia classification compared to using ECG signals alone.
May enhance ECG-based arrhythmia algorithms with metadata; leaves open prospective clinical validation.
Automatic classification of heart rhythm disturbances using an electrocardiogram is a reliable way to timely detect diseases of the cardiovascular system. The need to automate this process is to increase the number of electrocardiogram signals. Classification methods based on the use of neural networks provide a high percentage of arrhythmia recognition. However, known classification methods do not take into account patient characteristics. The work proposes a multimodal neural network that takes into account the age and gender characteristics of the patient. It includes a Long short-term memory (LSTM) network for feature extraction on twelve-channel electrocardiogram signals and a linear neural network for processing patient metadata such as age and gender. Extraction of electrocardiogram signal features occurs in parallel with metadata processing. The last unifying layer of the proposed multimodal neural network integrates heterogeneous data and features of electrocardiogram signals obtained using an LSTM network. The developed multimodal neural network was verified using the PhysioNet/Computing in Cardiology Challenge 2021 ECG database. The simulation results showed that the proposed multimodal neural network achieves a recognition accuracy of 63%, which is 2 percentage points higher compared to state-of-the-art methods.
No takes yet. Share an insight, caveat, or question.
Kiladze et al. (2023) studied Cardiac arrhythmias (n=3,000). Multimodal Neural Network (MM-NN) combining LSTM and linear perceptron vs. LSTM network alone or Linear perceptron alone was evaluated on Recognition accuracy of cardiac arrhythmias. The proposed multimodal neural network, which processes both 12-lead ECG signals and patient metadata, achieved a cardiac arrhythmia recognition accuracy of 63.00%, outperforming the LSTM-only model.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: