14 August 2024 in IEEE Journal of Biomedical and Health Informatics
Recent advancements in non-invasive blood glucose detection have seen progress in both photoplethysmogram and multiple near-infrared methods. While the former shows better predictability of baseline glucose levels, it lacks sensitivity to daily fluctuations. Near-infrared methods respond well to short-term changes but face challenges due to individual and environmental factors. To address this, we developed a novel fingertip blood glucose detection system combining both methods. Using multiple light sensors and a lightweight deep learning model, our system achieved promising results in oral glucose tolerance tests. A total of 10 participants were involved in the study, each providing approximately 700 data segments of about 10 seconds each. With a root mean squared error of 0.242 mmol/L and 100% accuracy in zone A of the Parkes error grid, our approach demonstrates the potential of multiple near-infrared sensors for non-invasive glucose detection.
5 March 2025 in IEEE Transactions on Instrumentation and Measurement
The narrow range of blood oxygen saturation (SpO2) measurement overlooks severe hypoxemia patients and some mild hypoxemia patients, preventing them from receiving accurate and timely warnings, which increases the risk of disease deterioration and related complications. In this paper, we present an SpO2 measurement method from fingertip videos, covering an estimation range from 70% to 100%. Our approach incorporates the Transformer Encoder mixed with Squeeze and Excitation Block (SETE) network architecture and the signal quality assessment module with filtering function. The SETE model itself features powerful global information sensing capability and adopts a channel auto-adjustment weighting mechanism to promptly capture dynamic changes in SpO2 levels. The public dataset used in this work maintains subjects’ SpO2 levels over a wide range by controlling for the percentage of oxygen inhaled by participants, thus keeping low SpO2 values over an extended duration. Comparative tests demonstrate that the SETE model outperforms current state-of-the-art contact SpO2 measurements in terms of performance. Experimental results indicate the mean absolute error (MAE) of 1.35% and the root mean square error (RMSE) of 2.08% between the estimated and reference SpO2 values. Consequently, this method offers a novel and effective approach for users to conduct SpO2 measurements based on electronic devices.
23 April 2026 in IEEE Sensors Journal
Cuffless and non-invasive blood pressure (BP) monitoring remains challenging because cuff-based devices are bulky and prone to ”white-coat syndrome”, while optical photoplethysmography (PPG) is sensitive to skin tone. Electrocardiography (ECG) reflects cardiac electrical activity, and bioimpedance (BioZ) captures hemodynamic changes; their combination is promising for reliable cuffless BP estimation, especially in wearable form factors such as smart rings. However, no prior work has integrated ECG and BioZ into a finger ring, and existing dual-signal systems still lack the hardware optimization and signal consistency validation required for subsequent BP modeling. This study addresses these gaps with a finger-ring-based solution, laying the technical groundwork for cuffless BP monitoring. Methods: We designed a high anti-interference ECG circuit, optimized three BioZ electrode modes and 12 carrier frequencies (10kHz–1MHz), fabricated a 3D-printed ECG-BioZ integrated ring, and developed a signal-processing workflow including multi-stage filtering, optimal phase angle selection, and 3D visualization. Results: Based on a comprehensive parameter sweep on a pilot subject, Mode L1 (artery-aligned electrodes) with 50kHz was identified as the optimal configuration (SQI 88.3%, main frequency significance 26.9dB). Subsequent validation on a diverse cohort of 11 subjects confirmed that this configuration yields consistent BioZ and ECG synchronization (Pearson r=0.912, p<0.001). In the pilot BP estimation study (N = 11), the system achieved a Mean Absolute Error (MAE) of 6.56 mmHg for Systolic BP and 4.97 mmHg for Diastolic BP using a transfer-learning-based KAN model. Notably, the dual-signal integration reduced SBP error by 2.31 mmHg compared to ECG-only approaches. Conclusions: This work establishes a finger-ring-based ECG-BioZ dual-signal framework, completes system-level hardware optimization and workflow refinement, and validates cross-signal temporal consistency. It lays a solid technical foundation for subsequent development of BP estimation models integrating cardiac electrical activity and hemodynamic changes, advancing non-invasive multi-parameter physiological monitoring toward consumer applications.