Low-Power Flexible Classifier Chip for Atrial Fibrillation Detection

This paper outlines a fully integrated on-chip classifier on a flexible substrate for real-time detection of atrial fibrillation (AFib) from electrocardiogram (ECG) signals. The ECG signals are digitized by means of a 14-bit analog-to-digital converter (ADC), followed by a time-domain feature extractor. These features are sent to a switched-capacitor compute-in-memory, analog, three-layer artificial neural network (ANN) for classification. The test-chip, fabricated in 65nm technology, consumes 58.3<i>µ</i>J/ per inference and achieves an average accuracy greater than 99.5% on Physionet dataset, 80% on a small, prospective human study performed at Mayo Clinic, Arizona and 99.9% on a large, retrospective dataset provided by Mayo Clinic Enterprise referred to as Rochester dataset.