A 186μW Photoplethysmography-Based Noninvasive Glucose Sensing SoC

• Published in: IEEE sensors journal Vol. 22; no. 14; pp. 14185 - 14195
• Main Authors: Hina, Aminah, Saadeh, Wala
• Format: Journal Article
• Language: English
• Published: New York IEEE 15.07.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Blood; Cutting; Diabetes; Feature extraction; Frequent glucose monitoring; Glucose; Light emitting diodes; Microprocessors; Monitoring; near-infrared (NIR); Noise prediction; photoplethysmography (PPG); Power consumption; Power management; Sensors; Signal processing; Skin; support vector regression (SVR); System on chip
• ISSN: 1530-437X; 1558-1748
• DOI: 10.1109/JSEN.2022.3180893

Recent trends in research and the market show high demand for frequent monitoring of glucose to estimate the blood sugar level non-invasively which can replace the conventional finger-prick glucometer for daily use. This paper presents a high precision near-infrared Photoplethysmography (PPG) based noninvasive glucose monitoring System on Chip (SoC). The proposed system implements a fully differential Analog Frontend (AFE) with nonlinear medium Gaussian support-vector-regression (NMG-SVR) for glucose estimation. The AFE design incorporates chopping which enables the reduction of the integrated input-referred current noise to 9.4pArms thus achieving a dynamic range of 115dB. The glucose prediction processor (GPP) removes noise from the PPG signal, extracts ten unique features, and estimates the blood glucose level using a trained customized NMG-SVR model that minimizes the hardware cost by 25%. The extracted features are carefully designed and implemented to ensure inter-feature dependency, which helps to reduce the overall area by more than 40%. Moreover, GPP is implemented using power and clock gating techniques to minimize both static and dynamic power consumption. The proposed SoC is realized with <inline-formula> <tex-math notation="LaTeX">0.18~\mu \text{m} </tex-math></inline-formula> CMOS technology and occupies an area of 6 mm 2 . It dissipates a power of <inline-formula> <tex-math notation="LaTeX">186~\mu \text{W} </tex-math></inline-formula> and achieves a mean absolute relative difference (mARD) of 6.9% verified on 200 subjects.