Ultra-low-power System-on-Chip for automated screening of central apnea and hypopnea via chin electromyography

Abstract

Central Apnea (CA) and Central Hypopnea (CH) are sleep disorders arising from the brain’s inability to signal respiratory muscles, potentially leading to severe complications such as heart failure. This study presents a novel system for automating CA and CH event detection in sleep apnea patients using a feedforward neural network (FdNN) architecture integrated into an ultra-low-power System-on-Chip (SoC) with chin electromyography (EMG) signals. The SoC achieves sub-1-mW power consumption through careful co-optimization of the FdNN architecture, hardware design, and circuit-level considerations, ensuring efficient operation with high-accuracy event detection. Using the ISRUC database for training and testing, the optimized FdNN model demonstrates the effectiveness of surface EMG (sEMG) features in identifying CA and CH events, achieving a notable testing accuracy of 85.7%. While the proposed support vector machine (SVM) kernel approximation model shows superior performance, optimizations to the FdNN architecture enhance its hardware compatibility. Implemented on GlobalFoundries 22 nm Fully Depleted Silicon-On-Insulator (GF 22 nm FDSOI) technology, the SoC achieves a core area of 0.0170 mm${}^2$, running at 100 MHz, and consumes 602 $\mu$W at 0.72 V with a leakage power of 0.263 $\mu$W. Additionally, slope sign change (SSC) is proposed as a digital biomarker, emphasizing the need to distinguish between CA and obstructive apnea, as well as CH and obstructive hypopnea, through statistical analysis. In conclusion, the proposed SoC provides power-efficient and sophisticated automated CA and CH event screening to help clinicians diagnose and treat sleep disorders, offering an alternative to traditional polysomnography (PSG) methods.