Key result
A model integrating Wavelet Scattering Network, Artificial Neural Network, time window selection, and majority vote achieved 87.35% accuracy and an 89.13% F1 score for classifying ECG rhythms.
Why the study?
Atrial fibrillation prevalence is projected to escalate and can lead to stroke and heart failure, underscoring the critical need for automated detection approaches.
Does a Wavelet Scattering Network combined with an Artificial Neural Network improve the accuracy of atrial fibrillation detection from short single-lead ECGs?
Does a Wavelet Scattering Network combined with an Artificial Neural Network improve the accuracy of atrial fibrillation detection from short single-lead ECGs?
A novel machine learning approach integrating wavelet scattering transform and neural networks achieved high accuracy (87.35%) in detecting atrial fibrillation from short single-lead ECGs.
Atrial Fibrillation (AF), a prevalent anomaly in cardiac rhythm, significantly impacts a substantial portion of the population, with projections indicating an escalation in its prevalence in the near future. This disorder manifests as irregular and accelerated heartbeats originating within the heart's upper chambers known as the atria. Neglecting to address this condition could potentially lead to serious consequences, particularly an elevated susceptibility to stroke and heart failure. This underscores the critical importance of developing an automated approach for detecting AF. In our study, an automatic approach was introduced for classifying short single-lead Electrocardiogram (ECG) recordings signals into four categories: Atrial fibrillation (AF), Normal rhythm (N), Noisy rhythm (~), or Other rhythms (O). The wavelet scattering network (WSN) is employed to extract morphological features from the ECG signals, which are then inputted into an Artificial Neural Network (ANN) with time windows selection and majority vote. The results from the testing data exhibit that our proposed model outperforms the state-of-art models, achieving a remarkable overall accuracy of 87.35% and an F1 score of 89.13%.
No takes yet. Share an insight, caveat, or question.
Bourkha et al. (2023) studied Atrial Fibrillation (n=8,528). Wavelet Scattering Network (WSN) with Artificial Neural Network (ANN), Time Window Selection, and Majority Vote vs. State-of-the-art machine learning models was evaluated on Overall classification accuracy and F1 score for detecting Atrial Fibrillation, Normal rhythm, Noisy rhythm, or Other rhythms. A model integrating Wavelet Scattering Network, Artificial Neural Network, time window selection, and majority vote achieved 87.35% accuracy and an 89.13% F1 score for classifying ECG rhythms.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: