A new gradient-based QRS detection algorithm and hybrid deep learning model achieved 96.77% sensitivity for QRS detection and 93.52% accuracy for heartbeat classification on the MIT/BIH dataset.
Does a hybrid deep learning model accurately detect QRS complexes and classify heartbeats in ECG data?
A novel hybrid deep learning model demonstrates high accuracy and sensitivity for automated QRS detection and heartbeat classification, performing on par with advanced algorithms.
The field of biomedical signal analysis has been developing a wide range of approaches to solve the challenge of developing an automated algorithm for analyzing ECG data to help diagnose cardiac disorders for over a century. The suggested techniques in this paper include a new gradient-based QRS detection algorithm that, when tested against the MIT/BIH dataset, produced a sensitivity of 96.77% and a positive predictivity of 99.81%. For the segmentation and classification of heartbeats, a hybrid deep learning model comes next, with a potential sensitivity of 85.31%, precision of 76.53%, accuracy of 93.52%, and F1-score of 92.87%. These outcomes are on par with the most advanced algorithms.
Hayek et al. (Tue,) conducted a other in Cardiac disorders (ECG analysis). Gradient-based QRS detection algorithm and hybrid deep learning model vs. Most advanced algorithms was evaluated on Sensitivity and positive predictivity for QRS detection; sensitivity, precision, accuracy, and F1-score for heartbeat classification. A new gradient-based QRS detection algorithm and hybrid deep learning model achieved 96.77% sensitivity for QRS detection and 93.52% accuracy for heartbeat classification on the MIT/BIH dataset.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: