Key result
The proposed DA-DRRNet model achieved an accuracy of 98.57% for beat-level and nearly 100% for 24-h record-level diagnosis of congestive heart failure using ECG signals.
Why the study?
Existing ECG-based methods for congestive heart failure detection have limited accuracy because they fail to capture temporal dynamics, and they lack model transparency and interpretability.
Does a diagnostic attention-based deep residual recurrent neural network (DA-DRRNet) improve the detection accuracy of congestive heart failure from ECG signals?
Population
ECG signals from three publicly available datasets (BIDMC-CHF, PTBDB, and MIT-BIH NSRDB)
Design
Model development and validation study
Authors
Loading...
May enhance ECG-based CHF screening if validated; leaves open need for prospective trials before adoption.
Does a diagnostic attention-based deep residual recurrent neural network (DA-DRRNet) improve the detection accuracy of congestive heart failure from ECG signals?
A novel deep learning model (DA-DRRNet) demonstrates high accuracy and interpretability for detecting congestive heart failure from ECG signals.
Prabhakararao et al. (2022) studied Congestive heart failure. Diagnostic attention-based deep residual recurrent neural network (DA-DRRNet) was evaluated on CHF detection accuracy. The proposed DA-DRRNet model achieved an accuracy of 98.57% for beat-level and nearly 100% for 24-h record-level diagnosis of congestive heart failure using ECG signals.
Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context: