Key result
Flexible on-chip ECG classifier detects AF with ~87% accuracy in humans.
Why the study?
Does a fully integrated on-chip classifier on a flexible substrate accurately detect atrial fibrillation from ECG signals?
Does a fully integrated on-chip classifier on a flexible substrate accurately detect atrial fibrillation from ECG signals?
A novel mixed-signal classifier chip on a flexible substrate demonstrates high accuracy and low energy consumption for on-device detection of atrial fibrillation.
May enable flexible wearable AF monitoring; hypothesis-generating pending larger prospective validation.
This work presents a fully integrated on-chip classifier on a flexible substrate for on-device detection of atrial fibrillation (AFib) from a electrocardiogram (ECG) signal. The ECG signals are digitized using a 14-bit analog-to-digital converter followed by time-domain feature extraction. The features are provided as inputs to an in-memory computing analog, 3-layer artificial neural network (ANN) for classification. A prototype test-chip is fabricated in 65nm and consumes 58.3 μ ~J / classification while detecting AFib with 99.6% accuracy on Physionet dataset and 86.7% accuracy on participants in a small-scale human subjects study at Mayo Clinic Arizona.
No takes yet. Share an insight, caveat, or question.
Sánchez et al. (2024) studied Atrial fibrillation. Mixed-signal classifier chip on flexible substrate was evaluated on Atrial fibrillation detection accuracy. A fully integrated on-chip classifier on a flexible substrate detected atrial fibrillation from ECG signals with 99.6% accuracy on the Physionet dataset and 86.7% accuracy in human subjects.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: