The current glucose measurement approaches still rely on invasive techniques which are uncomfortable and raise the risk of infection. To facilitate daily care at home, we propose an intelligent, non-invasive blood glucose monitoring system which can differentiate a user's blood glucose level into normal, borderline and warning based on smartphone PPG signals. The main implementation processes of the proposed system include: (1) a novel algorithm for acquiring photoplethysmography (PPG) signals using only smartphone camera videos; (2) a fitting-based sliding window (FSW) algorithm to remove varying degrees of baseline drifts and segment the signal into single periods; (3) extracting characteristic features from the Gaussian functions by comparing PPG signals at different blood glucose levels; (4) categorizing the valid samples into three glucose levels by applying machine learning algorithms. Our proposed system was evaluated on a data set of 80 subjects. Experimental results demonstrate the superiority of our proposed system.

Noninvasive blood glucose (BG) measurement could significantly improve the prevention and management of diabetes. In this paper, we present a robust novel paradigm based on analyzing photoplethysmogram (PPG) signals. The method includes signal pre-processing optimization and a multi-view cross-fusion transformer (MvCFT) network for non-invasive BG assessment. Specifically, a multi-size weighted fitting (MSWF) time-domain filtering algorithm is proposed to optimally preserve the most authentic morphological features of the original signals. Meanwhile, the spatial position encoding-based kinetics features are reconstructed and embedded as prior knowledge to discern the implicit physiological patterns. In addition, a cross-view feature fusion (CVFF) module is designed to incorporate pairwise mutual information among different views to adequately capture the potential complementary features in physiological sequences. Finally, the subject- wise 5- fold cross-validation is performed on a clinical dataset of 260 subjects. The root mean square error (RMSE) and mean absolute error (MAE) of BG measurements are 1.129 mmol/L and 0.659 mmol/L, respectively, and the optimal Zone A in the Clark error grid, representing none clinical risk, is 87.89%. The results indicate that the proposed method has great potential for homecare applications.

The electrocardiogram (ECG) has emerged as a viable alternative to polysomnography (PSG) for the detection of obstructive sleep apnea (OSA). Given the limited feature information of ECG signals in a single domain, this study proposes an adaptive threshold denoising synchrosqueezed wavelet transform (ADSWT) algorithm to extract high-resolution time-frequency domain features of ECG signals. The ADSWT algorithm enhances the time-frequency resolution, enabling better extraction of key features while minimizing noise interference, and generates an ECG scalogram as input for the network. Additionally, we propose a hybrid residual neural network (HRN-Net) for the automatic classification of OSA. The HRN-Net is designed with a dynamic feature extraction module to parse complex local features and enhance the network's generalization capability, as well as a dependency modeling module to capture the relationships between global contextual information for better understanding and interpretation of the ECG signals. All-night PSG recordings from both public and private datasets are used to validate the proposed framework. The results show that the framework achieves an accuracy of 0.942, a sensitivity of 0.926, a specificity of 0.959, and an F1 score of 0.942 on the public dataset, and an accuracy of 0.946, a sensitivity of 0.921, a specificity of 0.972, and an F1 score of 0.945 on the private dataset. These results indicate that the proposed framework offers high accuracy in automatic OSA classification and has significant potential to aid clinical decision-making.

Objective. This study aimed to improve peripheral oxygen saturation (SpO2) estimation across a wide range for hypoxemic-risk assessment in chronic obstructive pulmonary disease (COPD) using dual-wavelength photoplethysmography (PPG) and machine learning. Approach. A MAX30102-based module acquired synchronized red (660 nm) and near-infrared (880 nm) PPG signals from the right index finger. A CMS50DA oximeter on the right middle finger provided concurrent reference SpO2 readings for training and evaluation. Smartphone video captured its display for manual label extraction and independent checking. The ratio-of-ratios (R) and morphological, temporal, statistical, and derivative features were extracted. Principal component analysis-based feature selection identified a feature subset. Machine-learning and PPG-oriented deep-learning models were compared with conventional R-ratio calibration using mean absolute error (MAE), root mean squared error (RMSE), and the coefficient of determination (R2). Main results. The Extra Trees regressor achieved the lowest RMSE among evaluated models, with an MAE of 0.38 percentage points, an RMSE of 0.90 percentage points, and an R2 of 0.91. It outperformed conventional R-ratio calibration. In the hypoxemic range (70% ≤ SpO2 ≤ 90%), MAE was 0.98 percentage points, RMSE was 2.04 percentage points, and R2 was 0.66. Significance. Combining dual-wavelength PPG with multi-domain features and machine learning shows potential for wide-range SpO2 estimation and hypoxemic-risk assessment in COPD.