Key result
A Convolutional Neural Network (CNN) combined with a Long Short-Term Memory (LSTM) Network improved the accuracy of atrial fibrillation detection from ECG images compared to existing benchmarks.
Why the study?
Atrial fibrillation is the most common heart arrhythmia and can be fatal if untreated, motivating the application of deep learning to categorize ECG images.
Does a CNN-LSTM network improve the accuracy of atrial fibrillation detection from ECG images compared to existing benchmarks?
Does a CNN-LSTM network improve the accuracy of atrial fibrillation detection from ECG images compared to existing benchmarks?
A combined CNN-LSTM deep learning model improves the accuracy of detecting atrial fibrillation from ECG images compared to existing benchmarks.
May support AI tools for ECG-based AF detection; leaves open prospective clinical validation.
Cardiovascular diseases (CVDs) are the leading cause of death. An electrocardiogram is indeed a critical tool for detecting CVDs (ECG). In some cases, the patient's ECG is continuously monitored to detect various arrhythmic disorders. Specifically, Atrial Fibrillation (AF) is the most common heart arrhythmia, a kind of CVD with a prevalence of 1–2 percent in the general population and can be fatal if left untreated. Atrial Fibrillation (AF) is an irregular heartbeat that can lead to a heart attack and death. Due to the obvious excellent accuracy of today's electronic technologies, most diagnoses are made by clinical specialists. AF is defined by sporadic RR stretches and the absence of P-waves on the electrocardiogram. Different formulas have been developed to distinguish AF from the ECG waveform based on the above characteristics. Deep learning has made tremendous progress in image and sound recognition by eliminating express component extraction and reaching high order accuracy. To categorize the ECG images in this study, a Convolutional Neural Network (CNN) with a Long Short-Term Memory (LSTM) Network has been used. Results show that the system's performance is improved in terms of accuracy, which is more when compared to the existing benchmarks.
No takes yet. Share an insight, caveat, or question.
Tallapragada et al. (2022) studied Atrial Fibrillation. Convolutional Neural Network (CNN) with a Long Short-Term Memory (LSTM) Network vs. Existing benchmarks was evaluated on Accuracy of categorizing ECG images. A Convolutional Neural Network (CNN) combined with a Long Short-Term Memory (LSTM) Network improved the accuracy of atrial fibrillation detection from ECG images compared to existing benchmarks.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: