Enhancing shockable arrhythmia detection through variational mode decomposition and deep learning: a hybrid LSTM-CNN approach

Key Points

• Improved shockable arrhythmia detection rates, achieving over 90% accuracy with the novel approach.
• Deep learning techniques, including Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN), are utilized.
• Approach involves variational mode decomposition for optimal feature extraction from ECG signals.
• Highlights the potential for better clinical outcomes with advanced arrhythmia detection methods.