Key result
The DenseNet201 deep learning model achieved 100% accuracy in classifying ECG signals into normal sinus rhythm, arrhythmia, and congestive heart failure, compared to 91% accuracy with GoogLeNet.
Why the study?
Characterization and prediction of cardiac illnesses using ECG signals have become increasingly important for clinicians and patients.
Does deep learning using CNN models (GoogleNet and DenseNet201) accurately classify ECG signals into normal sinus rhythm, arrhythmia, and congestive heart failure?
Does deep learning using CNN models (GoogleNet and DenseNet201) accurately classify ECG signals into normal sinus rhythm, arrhythmia, and congestive heart failure?
Absolute Event Rate: 100% vs 91%
The DenseNet201 convolutional neural network model demonstrated 100% accuracy in classifying ECG signals into normal, arrhythmia, and heart failure categories, highlighting the potential of deep learning for automated cardiac diagnosis.
Suggests promise for CNN-based ECG classification; leaves open prospective validation before clinical adoption.
In the last ten years, the characterization and expectation of cardiac illnesses based on ECG signals have become increasingly important for doctors and patients. This paper delivers a deep learning technique that has recently been created for the order of ECG information with Normal Sinus Rhythm (NSR), Abnormal Arrhythmia (ARR), and Congestive Heart Failure (CHF). A sum of 162 ECG signals is open, including 96 arrhythmias, 30 Congestive Heart failures, and 36 Normal Sinus Rhythm signals. To exhibit the classification performance of deep learning architectures, this paper studied ECG using the two CNN models GoogleNet and DenseNet201. The proposed study's classification accuracy is 91% and 100% respectively. The outcomes uncover that the proposed profound learning architecture is more precise than traditional machine learning classifiers at classifying ECG signals.
No takes yet. Share an insight, caveat, or question.
Wheed et al. (2023) studied Arrhythmia, Congestive Heart Failure, Normal Sinus Rhythm (n=162). DenseNet201 and GoogLeNet deep learning models vs. Traditional machine learning classifiers was evaluated on Classification accuracy. The DenseNet201 deep learning model achieved 100% accuracy in classifying ECG signals into normal sinus rhythm, arrhythmia, and congestive heart failure, compared to 91% accuracy with GoogLeNet.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: