ECG Arrhythmia Classification on an Ultra-Low-Power Microcontroller.

Wearable biomedical systems allow doctors to continuously monitor their patients over longer periods, which is especially useful to detect rarely occurring events such as cardiac arrhythmias. Recent monitoring systems often embed signal processing capabilities to directly identify events and reduce the amount of data. This work is the first to document a complete beat-to-beat arrhythmia classification system implemented on a custom ultra-low-power microcontroller. It includes a single-channel analog front-end (AFE) circuit for electrocardiogram (ECG) signal acquisition, and a digital back-end (DBE) processor to execute the support vector machine (SVM) classification software with a Cortex-M4 CPU. The low-noise instrumentation amplifier in the AFE consumes 1.4 μW and has an input-referred noise of 0.9 μV RMS. The all-digital time-based ADC achieves 10-bit effective resolution over a 250-Hz bandwidth with an area of only 900 μm . The classification software reaches a sensitivity of 82.6% and 88.9% for supraventricular and ventricular arrhythmias respectively on the MIT-BIH arrhythmia database. The proposed system has been prototyped on the SleepRider SoC, a 28-nm fully-depleted silicon on insulator (FD-SOI) 3.1-mm chip. It consumes 13.1 μW on average from a 1.8-V supply.