rECGnition_v2.0: Self-Attentive Canonical Fusion of ECG and Patient Data using deep learning for effective Cardiac Diagnostics
Preprint
Abstract
The variability in ECG readings influenced by individual patient characteristics has posed a considerable challenge to adopting automated ECG analysis in clinical settings. A novel feature fusion technique termed SACC (Self Attentive Canonical Correlation) was proposed to address this. This technique is combined with DPN (Dual Pathway Network) and depth-wise separable convolution to create a robust, interpretable, and fast end-to-end arrhythmia classification model named rECGnition_v2.0 (robust ECG abnormality detection). This study uses MIT-BIH, INCARTDB and EDB dataset to evaluate the efficiency of rECGnition_v2.0 for various classes of arrhythmias. To investigate the influence of constituting model components, various ablation studies were performed, i.e. simple concatenation, CCA and proposed SACC were compared, while the importance of global and local ECG features were tested using DPN rECGnition_v2.0 model and vice versa. It was also benchmarked with state-of-the-art CNN models for overall accuracy vs model parameters, FLOPs, memory requirements, and prediction time. Furthermore, the inner working of the model was interpreted by comparing the activation locations in ECG before and after the SACC layer. rECGnition_v2.0 showed a remarkable accuracy of 98.07% and an F1-score of 98.05% for classifying ten distinct classes of arrhythmia with just 82.7M FLOPs per sample, thereby going beyond the performance metrics of current state-of-the-art (SOTA) models by utilizing MIT-BIH Arrhythmia dataset. Similarly, on INCARTDB and EDB datasets, excellent F1-scores of 98.01% and 96.21% respectively was achieved for AAMI classification. The compact architectural footprint of the rECGnition_v2.0, characterized by its lesser trainable parameters and diminished computational demands, unfurled several advantages including interpretability and scalability.Keywords
All Related Versions
This publication has 47 references indexed in Scilit:
- Estimating age and gender from electrocardiogram signals: A comprehensive review of the past decadeArtificial Intelligence in Medicine, 2023
- DeepArr: An investigative tool for arrhythmia detection using a contextual deep neural network from electrocardiograms (ECG) signalsBiomedical Signal Processing and Control, 2023
- Cardiac arrhythmia classification by time–frequency features inputted to the designed convolutional neural networksBiomedical Signal Processing and Control, 2022
- Arrhythmia classification algorithm based on multi-head self-attention mechanismBiomedical Signal Processing and Control, 2022
- ECG beat classification based on discriminative multilevel feature analysis and deep learning approachBiomedical Signal Processing and Control, 2022
- Arrhythmia classification of LSTM autoencoder based on time series anomaly detectionBiomedical Signal Processing and Control, 2022
- Deep learning-based multidimensional feature fusion for classification of ECG arrhythmiaNeural Computing and Applications, 2021
- ECG arrhythmia classification by using a recurrence plot and convolutional neural networkBiomedical Signal Processing and Control, 2021
- Cardiac arrhythmia classification using tunable Q-wavelet transform based features and support vector machine classifierBiomedical Signal Processing and Control, 2020
- Deep learning for time series classification: a reviewData Mining and Knowledge Discovery, 2019