Key result
Optimized VLSI architecture for LSTM ECG classification achieves low-power continuous monitoring at ~41 mW.
Why the study?
A portable and efficient ECG classification system optimized for real-time use in wearable healthcare devices is essential for continuous cardiac monitoring.
The proposed LSTM-based VLSI design for ECG classification offers an optimized balance of power efficiency and real-time processing, making it suitable for continuous cardiac monitoring on wearable devices.
May enable real-time wearable ECG monitoring; leaves open prospective clinical validation before practice adoption.
A portable and efficient electrocardiogram (ECG) classification system is essential for continuous cardiac monitoring in wearable healthcare devices. This paper presents a highly efficient very large scale integration architecture optimized for real‐time ECG classification. The proposed system integrates a feature extraction module that utilizes a four‐level daubechies discret wavelet transform and a classification module comprising multiple long‐short‐term memory recurrent neural networks, fully connected layers, and a multilayer perceptron. The design achieves a classification accuracy of . The hardware architecture demonstrates low resource utilization and operates at a power consumption of 41 mW with a clock frequency of 54 MHz, ensuring real‐time classification. The presented design is verified on a Xilinx field‐programmable gate array and tested using the publicly available ECG data set. Compared to state‐of‐the‐art implementations, our approach achieves a superior balance between classification accuracy, power efficiency, and hardware resource optimization, making it suitable for wearable cardiac monitoring applications.
No takes yet. Share an insight, caveat, or question.
Fan et al. (2025) studied Continuous cardiac monitoring (ECG classification). LSTM-based ECG classification VLSI architecture vs. State-of-the-art implementations was evaluated on Classification accuracy, power consumption, and clock frequency. An optimized VLSI architecture for LSTM-based ECG classification operated at 41 mW power and 54 MHz clock frequency, demonstrating high efficiency for wearable continuous cardiac monitoring.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: