March 10, 2022Journal of ImagingOpen Access

A Novel Deep-Learning-Based Framework for the Classification of Cardiac Arrhythmia

Q: What is the clinical evidence from this study?

Population: Cardiac Arrhythmia (n=1000). Intervention: ArrhythmiaNet (Deep-Learning Framework) vs. Pre-trained D-CNNs and existing state-of-the-art models. Primary outcome: Classification accuracy.

Q: What does this research mean for the field?

The proposed ArrhythmiaNet deep-learning framework achieves 99.84% accuracy, 100% sensitivity, and 99.6% specificity in classifying 17 classes of cardiac arrhythmia using 2D ECG signals. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

View Full Paper

Ask AI

Bookmark

Key result

ArrhythmiaNet deep learning classifies cardiac arrhythmias from ECG signals with ~100% accuracy.

n=1,000

Why the study?

ECG signals are vital for diagnosing CVDs and detecting cardiac arrhythmia, motivating the development of a novel deep-learning-based classification approach.

Population

1,000 ECG signal samples from the MIT-BIH dataset representing normal sinus rhythm and 16 classes of cardiac…

Comparison

ArrhythmiaNet, a novel deep-learning-based… vs Pre-trained D-CNNs and existing state-of-the-art…

Authors

SJSonain JamilCentre National de la Recherche Scientifique MRMuhibUr RahmanHEC Montréal

Discussion

Member takes

Implication

May facilitate automated ECG arrhythmia screening; leaves open prospective clinical validation before adoption.

Structured PICO

Population

1,000 ECG signal samples from the MIT-BIH dataset representing normal sinus rhythm and 16 classes of cardiac arrhythmia.

Intervention

ArrhythmiaNet, a novel deep-learning-based framework using continuous wavelet transform (CWT) to convert ECG into 2D signals, an attention-based deep convolutional neural network (D-CNN), and a clump of features (CoF) module with a Support Vector Machine (SVM) classifier.

Comparator

Pre-trained D-CNNs (AlexNet, ResNet-50, VGG-19, Inception v3, GoogLeNet, ShuffleNet, SqueezeNet, EfficientNetb0, Xception, DarkNet-53) and existing state-of-the-art machine learning techniques.

Outcome

Classification accuracy, sensitivity, specificity, F1-score, and classification error.

A novel deep-learning framework, ArrhythmiaNet, demonstrated 99.84% accuracy in classifying 17 classes of cardiac arrhythmias from 2D-transformed ECG signals.

Limitations

The proposed framework is dependent on the attention block, and the accuracy of the model decreases if the attention block is removed.
The performance of the model also varies by selecting different features.
The inter-patient paradigm is also a factor which affects the performance of the model.
The proposed framework is dependent on the attention block, and accuracy decreases if it is removed.
The performance of the model varies by selecting different features.
The inter-patient paradigm is a factor which affects the performance of the model.

Cite This Study

Jamil et al. (2022) studied Cardiac Arrhythmia (n=1,000). ArrhythmiaNet (Deep-Learning Framework) vs. Pre-trained D-CNNs and existing state-of-the-art models was evaluated on Classification accuracy. The proposed ArrhythmiaNet deep-learning framework achieved 99.84% accuracy, 100% sensitivity, and 99.6% specificity in classifying 17 classes of cardiac arrhythmia using 2D ECG signals.

synapsesocial.com/papers/6a1588435347fbb1739fece6 https://doi.org/10.3390/jimaging8030070

View Full Paper

Ask AI

Bookmark