Key result
Edge2Analysis AIoT platform achieves ~90% accuracy for AF recognition on edge devices.
Why the study?
Processing signals on edge devices offers low latency, low power consumption, and privacy protection, but limited embedded device resources have resulted in few studies attempting atrial fibrillation detection on edge nodes.
An AIoT platform deployed on edge devices can achieve approximately 90% accuracy for atrial fibrillation detection while offering low latency and privacy protection.
Supports edge-based AF detection feasibility; hypothesis-generating and requires prospective validation before clinical use.
Processing signals on edge nodes has become a popular trend, which requires data to be stored in terminals and processed, so it has the advantages of low latency, low power consumption and privacy protection. However, due to the limited resources of embedded devices, few studies have made relevant attempts. Our task was to implement a task for atrial fibrillation based on edge devices, using data from the open dataset CinC2017 and CPSC. The classification accuracy is about 90% and the model training can be completed on the edge platform. It is a feasible method to retrain the model by changing the training dataset of equipment.
No takes yet. Share an insight, caveat, or question.
Wu et al. (2022) studied Atrial fibrillation. Edge2Analysis AIoT Platform was evaluated on Classification accuracy. The Edge2Analysis AIoT platform for atrial fibrillation recognition on edge devices achieved a classification accuracy of approximately 90%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: