A novel spiking neural network algorithm for ECG classification achieves comparable accuracy to existing methods while reducing energy consumption by 2 to 9 orders of magnitude, enabling ultra low-power wearable monitoring.
May enable continuous wearable ECG monitoring; leaves open clinical validation before practice adoption.
This paper presents a novel ECG classification algorithm for inclusion as part of real-time cardiac monitoring systems in ultra low-power wearable devices. The proposed solution is based on spiking neural networks which are the third generation of neural networks. In specific, we employ spike-timing dependent plasticity (STDP), and reward-modulated STDP (R-STDP), in which the model weights are trained according to the timings of spike signals, and reward or punishment signals. Experiments show that the proposed solution is suitable for real-time operation, achieves comparable accuracy with respect to previous methods, and more importantly, its energy consumption in real-time classification of ECG signals is significantly smaller. In specific, energy consumption is 1.78 μJ per beat, which is 2 to 9 orders of magnitude smaller than previous neural network based ECG classification methods.
No takes yet. Share an insight, caveat, or question.
Amirshahi et al. (2019) studied this question.
Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context: