Finger-based optical sensing for blood glucose monitoring using smartphone photoplethysmography

Abstract

Accurate and continuous blood glucose monitoring remains a critical challenge due to the invasive nature of existing measurement techniques in remote and clinical settings. To address these challenges, this work presents a smartphonebased optical photoplethysmography (PPG) framework for low-cost, portable, and reliable blood glucose monitoring. Fingertip PPG signals are acquired from the left index finger using a smartphone camera for a duration of 15 s at 30 frames per second. The raw optical signal is extracted from the red colour channel, which is sensitive to blood volume variations dominated by haemoglobin absorption. Subsequently, a bandpass filter in the range of 0.5-5 Hz is used to isolate cardiacrelated pulsatile components. Baseline drift and motion-induced artifacts are attenuated using cubic spline interpolation while preserving PPG waveform morphology relevant to physiological analysis. From the pre-processed signals, time-domain and morphology-based PPG features are extracted and combined with demographic information and reference glucose values to construct the input dataset for glucose-level classification. The proposed framework is tested and evaluated using data collected from 80 subjects. Smartphone-acquired PPG signals are evaluated against the existing reference measurement system. The regression-based classification framework using XGBoost outperformed alternative algorithms, achieving a classification accuracy of 77%, precision of 85%, and numerical blood glucose prediction with a minimum RMSE of 15. The resultant findings demonstrated that smartphone based optical PPG represents a scalable noninvasive alternative for blood glucose monitoring, highlighting its potential for accessible remote monitoring applications.