Non-invasive Blood Glucose Research Articles

Intelligent estimation of blood glucose level using wristband PPG signal and physiological parameters

The inconvenience and risk associated with the regular use of invasive blood glucose measurements has led to tremendous research in this area. This paper proposes the design of a non-invasive blood glucose estimation system using novel Mel frequency cepstral coefficients features of wristband photoplethysmogram signal and physiological parameters. A dataset from 217 participants of a hospital in Cuenca Ecuador is used to validate the proposed model. The support vector regression (SVR) and extreme gradient boost regression (XGBR) techniques are used to estimate blood glucose levels (BGL). The XGBR technique achieves the least value for the standard error of prediction (SEP), 9.78 mg/dL. Further, 5 features are selected from the feature set based on the feature importance in XGBR. The XGBR model with the reduced feature set results in further reduction of SEP value (5.53 mg/dL) with a correlation coefficient of 0.99. Standard Clarke error grid analysis and Bland-Altman analysis shows that the predicted glucose values are in the clinically acceptable region. The results of the proposed model demonstrate the potential of wearable BGL monitoring technology.

Non-Invasive Blood Glucose Estimation System Based on a Neural Network with Dual-Wavelength Photoplethysmography and Bioelectrical Impedance Measuring.

This study proposed a noninvasive blood glucose estimation system based on dual-wavelength photoplethysmography (PPG) and bioelectrical impedance measuring technology that can avoid the discomfort created by conventional invasive blood glucose measurement methods while accurately estimating blood glucose. The measured PPG signals are converted into mean, variance, skewness, kurtosis, standard deviation, and information entropy. The data obtained by bioelectrical impedance measuring consist of the real part, imaginary part, phase, and amplitude size of 11 types of frequencies, which are converted into features through principal component analyses. After combining the input of seven physiological features, the blood glucose value is finally obtained as the input of the back-propagation neural network (BPNN). To confirm the robustness of the system operation, this study collected data from 40 volunteers and established a database. From the experimental results, the system has a mean squared error of 40.736, a root mean squared error of 6.3824, a mean absolute error of 5.0896, a mean absolute relative difference of 4.4321%, and a coefficient of determination (R Squared, R2) of 0.997, all of which fall within the clinically accurate region A in the Clarke error grid analyses.

GACSNet: A Lightweight Network for the Noninvasive Blood Glucose Detection

ABSTRACT Diabetes is a disease that requires long-term monitoring, and noninvasive glucose detection effectively reduces patient self-monitor resistance. Traditional noninvasive blood glucose methods are limited by many aspects, such as equipment, environment, and safety, which are not suitable for practical use. Aiming at this problem, propose a lightweight network called Group Asymmetric Convolution Shuffle Network (GACSNet) for noninvasive blood glucose detection: use infrared imaging to acquire human metabolic heat and construct a dataset, combine asymmetric convolution with channel shuffle unit, the novel convolution neural network is designed, and extract metabolic heat and cool-heat deviation features in thermal imaging. The test set was analyzed and compared using Clarke’s error grid. The current neural network showed an mean absolute percentage error of 9.17%, with a training time of 2 min 54 s and a inference time of 1.35 ms, which was superior to several traditional convolution neural networks’ accuracy, training cost, and real-time performance in the blood glucose region 3.9–9 mmol/L, and provided new insights into noninvasive blood glucose detection.

Investigational Outcomes of Normal and Diabetic Human Volunteers using Microwave based Non-invasive Blood Glucometer

—Noninvasive estimation of blood glucose using microwave based sensor is one of the most challenging research fields in recent days. These methods are more adaptable to avoid soreness and skin estrangement that occur in traditional invasive blood glucose measurement techniques. This paper suggests the investigational outcomes of a microwave based noninvasive blood glucose meter to check performance of the microwave antenna sensor. Narrowband micro strip antenna with resonating microwave frequency of 1.3 GHz is utilized to measure Blood Glucose Level (BGL) noninvasively. Validity of sensor is assessed by performing medical tests on non diabetic and diabetic human volunteers. Mean Absolute Relative Difference (MARD) and Surveillance Error Grid (SEG) analyses were performed during experimentation to find deviation of estimated BGL from reference BGL which is measured using available invasive technique. Direct assessment of estimated data with reference data provides excellent reliability and repeatability of proposed microwave technique. Keywords- glucometer, Blood Glucose Level (BGL), medical tests, Mean Absolute Relative Difference (MARD), Surveillance Error Grid (SEG)

Sense and Learn: Recent Advances in Wearable Sensing and Machine Learning for Blood Glucose Monitoring and Trend-Detection.

Diabetes mellitus is characterized by elevated blood glucose levels, however patients with diabetes may also develop hypoglycemia due to treatment. There is an increasing demand for non-invasive blood glucose monitoring and trends detection amongst people with diabetes and healthy individuals, especially athletes. Wearable devices and non-invasive sensors for blood glucose monitoring have witnessed considerable advances. This review is an update on recent contributions utilizing novel sensing technologies over the past five years which include electrocardiogram, electromagnetic, bioimpedance, photoplethysmography, and acceleration measures as well as bodily fluid glucose sensors to monitor glucose and trend detection. We also review methods that use machine learning algorithms to predict blood glucose trends, especially for high risk events such as hypoglycemia. Convolutional and recurrent neural networks, support vector machines, and decision trees are examples of such machine learning algorithms. Finally, we address the key limitations and challenges of these studies and provide recommendations for future work.

Deduction learning for precise noninvasive measurements of blood glucose with a dozen rounds of data for model training

Personalized modeling has long been anticipated to approach precise noninvasive blood glucose measurements, but challenged by limited data for training personal model and its unavoidable outlier predictions. To overcome these long-standing problems, we largely enhanced the training efficiency with the limited personal data by an innovative Deduction Learning (DL), instead of the conventional Induction Learning (IL). The domain theory of our deductive method, DL, made use of accumulated comparison of paired inputs leading to corrections to preceded measured blood glucose to construct our deep neural network architecture. DL method involves the use of paired adjacent rounds of finger pulsation Photoplethysmography signal recordings as the input to a convolutional-neural-network (CNN) based deep learning model. Our study reveals that CNN filters of DL model generated extra and non-uniform feature patterns than that of IL models, which suggests DL is superior to IL in terms of learning efficiency under limited training data. Among 30 diabetic patients as our recruited volunteers, DL model achieved 80% of test prediction in zone A of Clarke Error Grid (CEG) for model training with 12 rounds of data, which was 20% improvement over IL method. Furthermore, we developed an automatic screening algorithm to delete low confidence outlier predictions. With only a dozen rounds of training data, DL with automatic screening achieved a correlation coefficient ({R}_{P}) of 0.81, an accuracy score ({R}_{A}) of 93.5, a root mean squared error of 13.93 mg/dl, a mean absolute error of 12.07 mg/dl, and 100% predictions in zone A of CEG. The nonparametric Wilcoxon paired test on {R}_{A} for DL versus IL revealed near significant difference with p-value 0.06. These significant improvements indicate that a very simple and precise noninvasive measurement of blood glucose concentration is achievable.

The effect of near-surface electron trapping layer on the acetone sensing performance of black TiO2 capped with ZnO

In recent years, high-performance acetone gas sensors have attracted great attention for their potential in noninvasive blood glucose monitoring. In this work, black TiO2 (B-TiO2) was introduced as an electron trapping layer between TiO2 and ZnO to form TiO2@B-TiO2@ZnO core–shell nanoparticles, through a simple and safe method. The acetone sensing performance of TiO2@B-TiO2@ZnO varied with the thickness of ZnO. Because of the electron trapping effect of the introduced B-TiO2 layer, the best performing sample exhibited a low optimal operating temperature of 275 °C and a high response of 49.25–50 ppm acetone. In addition, a low detection limit of 170 ppb was obtained. The pretty selectivity of the sample was also been proved. The mechanism of enhanced acetone response was explained by the energy band-based model of TiO2@B-TiO2@ZnO core–shell nanoparticle and depletion layer theory.

Optimization and Evaluation of an Intelligent Short-Term Blood Glucose Prediction Model Based on Noninvasive Monitoring and Deep Learning Techniques.

Continuous noninvasive blood glucose monitoring and estimation management by using photoplethysmography (PPG) technology always have a series of problems, such as substantial time variability, inaccuracy, and complex nonlinearity. This paper proposes a blood glucose (BG) prediction model for more precise prediction based on BG series decomposition by complete aggregation empirical mode decomposition based on adaptive white noise (CEEMDAN) and the gated recurrent unit (GRU) that is optimized by improved bacterial foraging optimization (IBFO). Hierarchical clustering technology recombines the decomposed BG series according to their sample entropy and the correlations with the original BG trends. Dynamic BG trends are regressed separately for each recombined BG series by the GRU model to realize the more precise estimations, which are optimized by IBFO for its structure and superparameters. Through experiments, the optimized and basic LSTM, RNN, and support vector regression (SVR) are compared to evaluate the performance of the proposed model. The experimental results indicate that the root mean square error (RMSE) and mean absolute percentage error (MAPE) of the 15-min IBFO-GRU prediction is improved on average by about 13.1% and 18.4%, respectively, compared with those of the RNN and LSTM optimized by IBFO. Meanwhile, the proposed model improved the Clarke error grid results by about 2.6% and 5.0% compared with those of the IBFO-LSTM and IBFO-RNN in 30-min prediction and by 4.1% and 6.6% in 15-min ahead forecast, respectively. The evaluation outcomes of our proposed CEEMDAN-IBFO-GRU model have high accuracy and adaptability and can effectively provide early intervention control of the occurrence of hyperglycemic complications.

Spectral Methods for Response Enhancement of Microwave Resonant Sensors in Continuous Non-Invasive Blood Glucose Monitoring.

In this paper, the performance of three recent algorithms for the frequency-response enhancement of microwave resonant sensors are compared. The first one, a single-step algorithm, is based on a couple of direct-inverse Fourier transforms, giving a densely sampled response as a result. The second algorithm exploits an iterative procedure to progressively restricts the frequency response. The final one is based on the super-resolution MUSIC algorithm. The comparison is carried out through a Monte Carlo analysis. In particular, synthetic signals are firstly exploited to mimic the frequency response of a resonant microwave sensor. Then, experimental data collected from water-glucose solutions are adopted as validation test for potential applications in noninvasive blood-glucose monitoring.

Diffuse Imaging Approach for Universal Noninvasive Blood Glucose Measurements

We proposed a diffuse imaging approach for universal noninvasive blood glucose measurements based on visible light, which can predict the blood glucose concentration without personal calibration. The proposed approach used a CCD to obtain diffuse images from human index finger pulp. The denoising autoencoder algorithm adopted effectively extracted the scattering information highly related to blood glucose concentration from the diffuse images, and the gradient boosting regression algorithm enabled an accurate calculation of blood glucose concentration without prior personalized calibration.In vivoexperimental results showed that the proposed approach had a mean absolute error of 19.44 mg/dl, with all the predicted results observed within the clinically acceptable region (Region A: 78.9%) in the Clarke error grid analysis. Compared to other blood glucose concentration measurement methods of scattering coefficient, this new method does not require individual calibration, therefore it is easier to implement and popularize, which is critical for the noninvasive monitoring of blood glucose concentration.

Study on noninvasive blood glucose detection method using the near-infrared light based on particle swarm optimization and back propagation neural network

Most of the existing near-infrared noninvasive blood glucose detection models focus on the relationship between near-infrared absorbance and blood glucose concentration, but do not consider the impact of human physiological state on blood glucose concentration. In order to improve the performance of prediction model, particle swarm optimization (PSO) algorithm was used to train the structure paramters of back propagation (BP) neural network. Moreover, systolic blood pressure, pulse rate, body temperature and 1 550 nm absorbance were introduced as input variables of blood glucose concentration prediction model, and BP neural network was used as prediction model. In order to solve the problem that traditional BP neural network is easy to fall into local optimization, a hybrid model based on PSO-BP was introduced in this paper. The results showed that the prediction effect of PSO-BP model was better than that of traditional BP neural network. The prediction root mean square error and correlation coefficient of ten-fold cross-validation were 0.95 mmol/L and 0.74, respectively. The Clarke error grid analysis results showed that the proportion of model prediction results falling into region A was 84.39%, and the proportion falling into region B was 15.61%, which met the clinical requirements. The model can quickly measure the blood glucose concentration of the subject, and has relatively high accuracy.

Development of non-invasive blood glucose regression based on near-infrared spectroscopy combined with a deep-learning method

Extracting micro-scale spectral features from dynamic blood glucose concentrations is extremely difficult when using non-invasive measurement methods. This work proposes a new machine-learning method based on near-infrared spectroscopy, a deep belief network (DBN), and a support vector machine to improve prediction accuracy. First, the standard oral glucose tolerance test was used to collect near-infrared spectroscopy and actual blood glucose concentration values for specific wavelengths (1200, 1300, 1350, 1450, 1600, 1610, and 1650 nm); the blood glucose concentrations were within a clinical range of 70 ∼ 220 mg dl−1. Second, based on the DBN model, high-dimensional deep features of the non-invasive blood glucose spectrum were extracted. These were used to establish a support vector regression (SVR) model and to quantitatively analyze the influence of the spectral sample size and corresponding feature dimensions (i.e. DBN structure) on prediction accuracy. Finally, based on data from six volunteers, a comparative analysis of the SVR model’s prediction accuracy was performed both before and after using high-dimensional deep features. For volunteer 1, when the DBN-based high-dimensional deep features were used, the root mean square error of the SVR model was reduced by 71.67%, and the correlation coefficient (R 2) and the P value of the Clark grid analysis (P) were increased by 13.99% and 6.28%, respectively. Moreover, we had similar results when the proposed method was carried out on the data of other volunteers. The results show that the presented algorithm can play an important role in dynamic non-invasive blood glucose concentration prediction and can effectively improve the accuracy of the SVR model. Further, by applying the algorithm to six independent sets of data, this research also illustrates the high-precision regression and generalization capabilities of the DBN-SVR algorithm.

Highly integrated watch for noninvasive continual glucose monitoring

This article reports a highly integrated watch for noninvasive continual blood glucose monitoring. The watch employs a Nafion-coated flexible electrochemical sensor patch fixed on the watchband to obtain interstitial fluid (ISF) transdermally at the wrist. This reverse iontophoresis-based extraction method eliminates the pain and inconvenience that traditional fingerstick blood tests pose in diabetic patients’ lives, making continual blood glucose monitoring practical and easy. All electronic modules, including a rechargeable power source and other modules for signal processing and wireless transmission, are integrated onto a watch face-sized printed circuit board (PCB), enabling comfortable wearing of this continual glucose monitor. Real-time blood glucose levels are displayed on the LED screen of the watch and can also be checked with the smartphone user interface. With 23 volunteers, the watch demonstrated 84.34% clinical accuracy in the Clarke error grid analysis (zones A + B). In the near future, commercial products could be developed based on this lab-made prototype to provide the public with noninvasive continual glucose monitoring.

A novel approach to non-invasive blood glucose sensing based on a single-slot defected ground structure

AbstractIn this study, we explore a novel approach to measure blood glucose concentration in a non-invasive way using a compact defected ground structure (DGS) filter. The proposed sensor is promising because it is cost-effective, compact, non-ionizing in nature, and convenient for diabetics. Therefore, a portable microwave biosensor can be utilized using these features. In this study, we present a single DGS sensor which is designed on a Rogers RO4003C substrate and fed by a 50 Ω microstrip line, and operating in the industrial, scientific, and medical radio bands (2.4–2.5 GHz). The changes in dielectric properties in blood are mainly relying on glucose concentrations. The main concept of using a sensor is by placing a finger on the sensing area (the slot). The filter is demonstrated by simulations using CST Microwave Studio. Additionally, the blood layer with different glucose concentrations from 250 to 16 000 mg/dl is presented by the Cole–Cole model. The sensor can achieve a relatively good sensitivity of 7.8285 kHz/mg/dl. The size of the fabricated sensor is 40 × 40 × 0.883 mm3, which is suitable for hand-held use.

Noninvasive blood glucose detection system based on dynamic spectrum and “M+N″ theory

Noninvasive detection of blood glucose is an urgent problem to be solved in the prevention, treatment and management of diabetes. However, in the system of noninvasive detection of blood glucose content by spectral method, due to individual differences, interference in the measurement system and the fact that the content of blood glucose is three orders of magnitude smaller than the most abundant component in blood, the spectral signal of blood glucose component is weak, and the problem has not been solved so far. Dynamic spectrum (DS) method can theoretically eliminate the influence of individual differences and changes in measurement conditions, and “M + N″ theory comprehensively considers the internal and external factors of spectral quantitative analysis of complex solution components, and provides some strategies to suppress the errors caused by multiple factors in spectral quantitative analysis of complex solutions. Therefore, this paper proposes a system for non-invasive quantitative analysis of human blood glucose based on DS and “M + N″ theory. In this paper, feasible methods are used in each step of the system to effectively reduce the influence of noise and interference factors, so that the model has good prediction performance. The correlation coefficient and root mean square error of calibration set were 0.9539 and 0.3965 (mmol/L), respectively. The correlation coefficient and root mean square error of prediction set were 0.9542 and 0.7305 (mmol/L), respectively. The system of noninvasive quantitative analysis of blood glucose proposed in this paper is effective and feasible, which not only makes great progress in noninvasive detection of human blood glucose, but also has application value for realizing noninvasive real-time detection of human blood components.

Noninvasive Spectroscopic Detection of Blood Glucose and Analysis of Clinical Research Status.

Frequent measurement of blood glucose concentration in diabetic patients is an important means for diabetes control. Blood glucose monitoring with noninvasive detection technology can not only avoid the pain of patients and eliminate the harm of some biological materials for measuring glucose in vivo but also improve the frequency of detection, so as to control blood glucose concentration more closely. Traditional blood glucose detection methods are invasive and have some limitations. In this study, the significance of noninvasive blood glucose testing was analyzed and was pointed out that noninvasive blood glucose testing can monitor the blood glucose concentration of patients and relieve the pain of patients. Then, this study analyzed the spectral detection methods of noninvasive blood glucose, including conservation of energy metabolism, near infrared spectroscopy, and other spectral detection methods. Finally, this study made a comprehensive analysis of the domestic and international clinical application of noninvasive glucose spectrum monitoring and summarized the clinical application status of noninvasive glucose spectrum monitoring.

Non-invasively accuracy enhanced blood glucose sensor using shallow dense neural networks with NIR monitoring and medical features

Non-invasive and accurate method for continuous blood glucose monitoring, the self-testing of blood glucose is in quest for better diagnosis, control and the management of diabetes mellitus (DM). Therefore, this study reports a multiple photonic band near-infrared (mbNIR) sensor augmented with personalized medical features (PMF) in Shallow Dense Neural Networks (SDNN) for the precise, inexpensive and pain free blood glucose determination. Datasets collected from 401 blood samples were randomized and trained with ten-fold validation. Additionally, a cohort of 234 individuals not included in the model training set were investigated to evaluate the performance of the model. The model achieved the accuracy of 97.8% along with 96.0% precision, 94.8% sensitivity and 98.7% specificity for DM classification based on a diagnosis threshold of 126 mg/dL for diabetes in fasting blood glucose. For non-invasive real-time blood glucose monitoring, the model exhibited ± 15% error with 95% confidence interval and the detection limit of 60–400 mg/dL, as validated with the standard hexokinase enzymatic method for glucose estimation. In conclusion, this proposed mbNIR based SDNN model with PMF is highly accurate and computationally cheaper compared to similar previous works using complex neural network. Some groups proposed using complicated mixed types of sensors to improve noninvasive glucose prediction accuracy; however, the accuracy gain over the complexity and costs of the systems harvested is still in questioned (Geng et al. in Sci Rep 7:12650, 2017). None of previous works report on accuracy enhancement of NIR/NN using PMF. Therefore, the proposed SDNN over PMF/mbNIR is an extremely promising candidate for the non-invasive real-time blood glucose monitoring with less complexity and pain-free.

A Review of Non-invasive Electromagnetic Blood Glucose Monitoring Techniques

Diabetes is a big concern worldwide, and the International Diabetes Federation estimates there are over 450 million diabetics throughout the world. Researchers have been exploring a rapid and easy technique of calculating blood glucose. We already have reliable tests with improved precision for sensing blood glucose, but it comes with the expense of discomfort and agony because of employing a pricking needle. Technologies established during the previous few decades strive for a painless gadget that can be used as often as possible, dependable, efficient, and accurate. Most importantly, it must be straightforward to use with minimal hassles. This evaluation attempts to give the breakthroughs at present being researched for non-invasive electromagnetic (EM) glucose monitoring systems. This study acknowledges features and possibilities of accessible EM glucose monitoring techniques, just as basic qualities and execution elements for an ideal non-invasive instrument.

Indole as a new tentative marker in exhaled breath for non-invasive blood glucose monitoring of diabetic subjects

Blood glucose monitoring (BGM) is the most important part of diabetes management. In classical BGM, glucose measurement by test strips involves invasive finger pricking. We present results of a clinical study that focused on a non-invasive approach based on volatile organic compounds (VOCs) in exhaled breath. Main objective was the discovery of markers for prediction of blood glucose levels (BGLs) in diabetic patients. Exhaled breath was measured repeatedly in 60 diabetic patients (30 type 1, 30 type 2) in fasting state and after a standardized meal. Proton transfer reaction time of flight mass spectrometry was used to sample breath every 15 min for a total of 6 h. BGLs were tested in parallel via BGM test strips. VOC signals were plotted against glucose trends for each subject to identify correlations. Exhaled indole (a bacterial metabolite of tryptophan) showed significant mean correlation to BGL (with negative trend) and significant individual correlation in 36 patients. The type of diabetes did not affect this result. Additional experiments of one healthy male subject by ingestion of lactulose and 13C-labeled glucose (n = 3) revealed that exhaled indole does not directly originate from food digestion by intestinal microbiota. As indole has been linked to human glucose metabolism, it might be a tentative marker in breath for non-invasive BGM. Clinical studies with greater diversity are required for confirmation of such results and further investigation of metabolic pathways.

Commercial and Scientific Solutions for Blood Glucose Monitoring-A Review.

Diabetes is a chronic and, according to the state of the art, an incurable disease. Therefore, to treat diabetes, regular blood glucose monitoring is crucial since it is mandatory to mitigate the risk and incidence of hyperglycemia and hypoglycemia. Nowadays, it is common to use blood glucose meters or continuous glucose monitoring via stinging the skin, which is classified as invasive monitoring. In recent decades, non-invasive monitoring has been regarded as a dominant research field. In this paper, electrochemical and electromagnetic non-invasive blood glucose monitoring approaches will be discussed. Thereby, scientific sensor systems are compared to commercial devices by validating the sensor principle and investigating their performance utilizing the Clarke error grid. Additionally, the opportunities to enhance the overall accuracy and stability of non-invasive glucose sensing and even predict blood glucose development to avoid hyperglycemia and hypoglycemia using post-processing and sensor fusion are presented. Overall, the scientific approaches show a comparable accuracy in the Clarke error grid to that of the commercial ones. However, they are in different stages of development and, therefore, need improvement regarding parameter optimization, temperature dependency, or testing with blood under real conditions. Moreover, the size of scientific sensing solutions must be further reduced for a wearable monitoring system.