Patient ECG Heartbeat Classification for Arrhythmia and Atrial Fibrillation Detection
Description
Electrocardiogram (ECG) signal is a common and powerful tool to study heart function and diagnose several abnormal arrhythmias. While there have been remarkable improvements in cardiac arrhythmia classification methods, they still cannot offer acceptable performance in detecting different heart conditions, especially when dealing with imbalanced datasets. This technology addresses the limitations of current classification approaches by developing an automatic heartbeat classification method using deep convolutional neural networks and sequence-to-sequence models. Specifically, this method can be applied for the detection of arrhythmias and atrial fibrillation (AF).
Additional information
Patent number and inventor
16/783,040
Fatemeh Afghah and Seyed Mousavi.
Potential applications
Clinical applications
Benefits and advantages
This method significantly outperforms the existing algorithms in the literature for both the intra-patient and inter-patient paradigms. Furthermore, this method can be applied to several other biomedical applications such as sleep staging, in which there are strong dependencies between each stage and sufficient data are not available. In addition, the present system can be used with wearable devices.
Case number and licensing status
2019-020
This invention is available for licensing.