Non-invasive Blood Glucose Monitoring Research Articles

Internet of Things enabled open source assisted real-time blood glucose monitoring framework

Regular monitoring of blood glucose levels is essential for the management of diabetes and the development of appropriate treatment protocols. The conventional blood glucose (BG) testing have an intrusive technique to prick the finger and it can be uncomfortable when it is a regular practice. Intrusive procedures, such as fingerstick testing has negatively influencing patient adherence. Diabetic patients now have an exceptional improvement in their quality of life with the development of cutting-edge sensors and healthcare technologies. intensive care unit (ICU) and pregnant women also have facing challenges including hyperglycemia and hypoglycemia. The worldwide diabetic rate has incited to develop a wearable and accurate non-invasive blood glucose monitoring system. This research developed an Internet of Things (IoT) - enabled wearable blood glucose monitoring (iGM) system to transform diabetes care and enhance the quality of life. The TTGOT-ESP32 IoT platform with a red and near-infrared (R-NIR) spectral range for blood glucose measurement has integrated into this wearable device. The primary objective of this gadget is to provide optimal comfort for the patients while delivering a smooth monitoring experience. The iGM gadget is 98.82 % accuracy when used after 10 hours of fasting and 98.04 % accuracy after 2 hours of breakfast. The primary objective points of the research were continuous monitoring, decreased risk of infection, and improved quality of life. This research contributes to the evolving field of IoT-based healthcare solutions by streaming real-time glucose values on AWS IoT Core to empower individuals with diabetes to manage their conditions effectively. The iGM Framework has a promising future with the potential to transform diabetes management and healthcare delivery.

EMD-Based Noninvasive Blood Glucose Estimation from PPG Signals Using Machine Learning Algorithms

Effective management of diabetes requires accurate monitoring of blood glucose levels. Traditional invasive methods for such monitoring can be cumbersome and uncomfortable for patients. In this study, we introduce a noninvasive approach to estimate blood glucose levels using photoplethysmography (PPG) signals. We have focused on blood glucose prediction using wrist PPG signals and explored various PPG waveform-based features, including AC to DC ratio (AC/DC) and intrinsic mode function (IMF)-based features derived from empirical mode decomposition (EMD). To the best of our knowledge, no studies have been found using EMD-based features to estimate blood glucose levels noninvasively. Additionally, feature importance-based selection has also been used to further improve the accuracy of the proposed model. Among the four machine learning algorithms considered in this study, CatBoost consistently outperformed XGBoost, LightGBM, and random forest across a wide number of features. The best performing model, CatBoost, achieved Pearson’s r of 0.96, MSE 0.08, R2 score 0.92, and MAE 8.01 when considering the top 50 features selected from both PPG waveform-based features and IMF-based features. The p-values for all models were <0.001, indicating statistically significant correlations. Overall, this study provides valuable insights into the feasibility and effectiveness of noninvasive blood glucose monitoring using advanced machine learning techniques.

Next-generation healthcare infrastructure based on cross-layer optimization of biosignal sensing and communication

The human body already uses electric signals to transmit information to and from the brain and the rest of the body but is there potential to harness the complex interactions between living organisms and electromagnetic waves to advance scientific disciplines? Associate Professor Dairoku Muramatsu is the head of the Muramatsu Laboratory. He leads the Bioelectromagnetics Research Group, Graduate School of Information Science and Engineering Mechanical and Intelligent Systems, University of Electro-Communications, Japan. He is a specialist in bioelectromagnetic engineering that spans engineering and medicine interested in the interactions between living organisms and electromagnetic waves and how improved understanding of these interactions could lead to practical, real-world impacts. A key principle behind Muramatsu's research is that by passing a weak electric current through the human body and using the body itself as a path for electric signals, it is possible to exchange information between people and objects that come into contact with them. He is working to create innovative and highly usable technology by making full use of simulation and manufacturing. As research on human body communication, which is wireless communication that uses the human body itself as a transmission path for high-frequency signals, findings will play a key role in the spread of wearable devices. Muramatsu has already proposed bioelectromagnetic models that serve as a tool for a wide range of bioelectronics and sensor designs, including non-invasive blood glucose monitoring using bioelectromagnetic response as an evaluation criterion.

Highly sensitive blood glucose monitoring sensor with adjustable resonant frequency based on MP-CSRR

In this paper, a multi parallel CSRR (MP-CSRR) sensor for non-invasive blood glucose monitoring is introduced. The sensor divides six CSRR units into two parallel circuits, forming 2 × 3 CSRR matrix to expand the sensing area of the sensor. This sensor can adjust the resonant frequency of the sensor itself by adjusting the spacing between the horizontal or vertical CSRR units. In this paper, the sensor is achieved a resonance frequency of 2.5–3.5 GHz after loading glucose solution. When the concentration of the solution changes, the resonance frequency and S21 depth of the resonator changes with the dielectric parameters of the solution. Thus, non-invasive monitoring of glucose concentration is achieved. The variation relationship between resonant frequency and CSRR unit spacing and the feasibility of using it for solution detection are verified through simulation. The experimental results are showed that the resonant frequency sensitivity of the sensor is 9.59 × 10−2 MHz/(mg/dL), and the |S21| sensitivity is 7.47 × 10−3 dB/(mg/dL).

A review on flexible wearables – Recent developments in non-invasive continuous health monitoring

Wearable sensors hold profound significance in our increasingly interconnected world, revolutionizing the way we monitor and manage our health, daily activities, and environments. These compact, unobtrusive tools have transcended the realm of mere gadgets to become indispensable tools for individuals and healthcare professionals alike. By continuously collecting data on vital signs, physical activity, sleep patterns, and more, wearables empower users to gain valuable insights into their well-being, facilitating proactive health management. Beyond preventive medicine, wearables find applications in diverse fields, from sports performance optimization to industrial safety monitoring, making them catalysts for transformative change in the way we live, work, and thrive. As technology continues to advance, the significance of wearables in enhancing our lives and pushing the boundaries of knowledge will only continue to grow. In this review, we focused on the recent advances in the field of wearables for continuous non-invasive monitoring of cardiovascular, body temperature and blood glucose. These sensors are commonly incorporated into garments or stylish accessories such as watches, allowing individuals to monitor different facets of their health, including metabolic processes and vital signs. In premise, the worldwide wearables market is undergoing substantial growth propelled by technological advancements, expanding applications, and the need for inventive preventive healthcare solutions. Despite existing challenges, the industry is well-positioned for ongoing expansion as it tackles these issues and pushes the frontiers of wearable technology.

Application of Biosensors in Non-invasive Blood Glucose Monitoring

Blood glucose monitoring is essential for managing conditions like diabetes and liver dysfunction, with a growing need among various population groups, including the elderly, pregnant, and individuals engaging in specific dietary and exercise regimes. The technology for glucose monitoring is divided into invasive and non-invasive methods. Invasive techniques, while accurate, involve bodily fluid extraction, posing risks of infection and inconvenience for frequent monitoring. Conversely, non-invasive methods, which include biosensors that analyze internal signals, offer a safer and more user-friendly alternative, providing instant feedback on glucose levels. Recent advancements in biosensor technology have focused on enhancing accuracy, biocompatibility, and ease of use, with significant progress in areas like optical and electrochemical sensors. These developments aim to offer more reliable, convenient, and comprehensive glucose monitoring solutions, leveraging innovations in sensor technology and data analysis to cater to the diverse needs of individuals requiring blood glucose tracking.

PPG based Noninvasive Blood Glucose Monitoring using Multi-view Attention and Cascaded BiLSTM Hierarchical Feature Fusion Approach.

Diabetes is a chronic disease with exponential growth and poses significant challenges to global healthcare. Regular blood glucose (BG) monitoring is key for avoiding diabetic complications. Traditional BG measurement techniques are invasive and minimally invasive, causing pain, discomfort, cost, and infection risks. To address these issues, we developed a noninvasive BG monitoring approach on photoplethysmography (PPG) signals using multi-view attention and cascaded BiLSTM hierarchical feature fusion approach. Firstly, we implemented a convolutional multi-view attention block to extract the temporal features through adaptive contextual information aggregation. Secondly, we built a cascaded BiLSTM network to efficiently extract the fine-grained features through bidirectional learning. Finally, we developed a hierarchical feature fusion with bilinear polling through cross-layer interaction to obtain higher-order features for BG monitoring. For validation, we conducted comprehensive experimentation on up to 6 days of PPG and BG data from 21 participants. The proposed approach showed competitive results compared to existing approaches by RMSE of 1.67 mmol/L and MARD of 17.88%. Additionally, the clinical accuracy using Clarke error grid (CEG) analysis showed 98.80% of BG values in Zone A+B. Therefore, the proposed approach offers a favorable solution in diabetes management by noninvasively monitoring the BG levels.

Near-infrared Imaging and Convolutional Neural Network for Non-Invasive Blood Glucose Monitoring

Near-infrared Imaging and Convolutional Neural Network for Non-Invasive Blood Glucose Monitoring

Non-invasive blood glucose monitoring technology in diabetes management: review.

Diabetes is one of the leading non-communicable diseases globally, adversely impacting an individual's quality of life and adding a considerable burden to the healthcare systems. The necessity for frequent blood glucose (BG) monitoring and the inconveniences associated with self-monitoring of BG, such as pain and discomfort, has motivated the development of non-invasive BG approaches. However, the current research progress is slow, and only a few BG self-monitoring devices have made considerable progress. Hence, we evaluate the available non-invasive glucose monitoring technologies validated against BG recordings to provide future research direction to design, develop, and deploy self-monitoring of BG with integrated emerging technologies. We searched five databases, Embase, MEDLINE, Proquest, Scopus, and Web of Science, to assess the non-invasive technology's scope in the diabetes management paradigm published from 2000 to 2020. A total of three approaches to non-invasive screening, including saliva, skin, and breath, were identified and discussed. We observed a statistical relationship between BG measurements obtained from non-invasive methods and standard clinical measures. Opportunities exist for future research to advance research progress and facilitate early technology adoption for healthcare practice. The results promise clinical validity; however, formulating regulatory guidelines could foresee the deployment of approved non-invasive BG monitoring technologies in healthcare practice. Further, research prospects are there to design, develop, and deploy integrated diabetes management systems with mobile technologies, data analytics, and the internet of things (IoT) to deliver a personalised monitoring system.

Measurement Analysis of Non-Invasive Blood Glucose On Sensor Coplanar Waveguide Loaded Square Ring Resonator with Interdigital Coupling Capacitor

This study presents the experimental results of a system with a sensor structure detecting human blood glucose levels. A microwave-based sensor is used for non-invasive blood glucose monitoring. The sensor design uses an asymmetrically loaded CPW structure as a square ring resonator with an interdigital coupling capacitor on the ground side. Simulated with a load of artificial finger tissue made from gelatin, modeled in four layers. The first layer is the skin is the outermost tissue, the next layer is fat, blood and bone. Each layer of tissue has a certain thickness size; skin (0.3mm), fat (0.2mm), blood (1.5mm), and bone (4mm). The measurement simulation is used, HFSS as modeling simulation and VNA as a measurement of the physical representation of the design results with parametric optimization methods. To verify the correlation and the expected sensitivity, media with different dielectrics were mounted on the surface of the sensor resonator with blood glucose levels of 1mg/dl, 72mg/dl, 126mg/dl, 162mg/dl and 216mg/dl. Reflection factor S11 was observed based on dielectric constant blood glucose levels (dB) fluctuations. Analysis of the data on the graph between the independent variables, namely blood glucose concentration and the dependent variable levels of S11 has an “R” correlation value of 0.97. The sensitivity level of the sensor on the S11 reflection factor with HFSS simulation averages 73.36mdB/mgdl-1 and VNA reaches 82.39mdB/mgdl-1. The results are interesting for developing a more optimal glucose sensor system.

Measurement Analysis of Non-Invasive Blood Glucose On Sensor Coplanar Waveguide Loaded Square Ring Resonator with Interdigital Coupling Capacitor

This study presents the experimental results of a system with a sensor structure detecting human blood glucose levels. A microwave-based sensor is used for non-invasive blood glucose monitoring. The sensor design uses an asymmetrically loaded CPW structure as a square ring resonator with an interdigital coupling capacitor on the ground side. Simulated with a load of artificial finger tissue made from gelatin, modeled in four layers. The first layer is the skin is the outermost tissue, the next layer is fat, blood and bone. Each layer of tissue has a certain thickness size; skin (0.3mm), fat (0.2mm), blood (1.5mm), and bone (4mm). The measurement simulation is used, HFSS as modeling simulation and VNA as a measurement of the physical representation of the design results with parametric optimization methods. To verify the correlation and the expected sensitivity, media with different dielectrics were mounted on the surface of the sensor resonator with blood glucose levels of 1mg/dl, 72mg/dl, 126mg/dl, 162mg/dl and 216mg/dl. Reflection factor S11 was observed based on dielectric constant blood glucose levels (dB) fluctuations. Analysis of the data on the graph between the independent variables, namely blood glucose concentration and the dependent variable levels of S11 has an “R” correlation value of 0.97. The sensitivity level of the sensor on the S11 reflection factor with HFSS simulation averages 73.36mdB/mgdl-1 and VNA reaches 82.39mdB/mgdl-1. The results are interesting for developing a more optimal glucose sensor system.

Review of Noninvasive Continuous Glucose Monitoring in Diabetics.

For diabetics, taking regular blood glucose measurements is crucial. However, traditional blood glucose monitoring methods are invasive and unfriendly to diabetics. Recent studies have proposed a biofluid-based glucose sensing technique that creatively combines wearable devices with noninvasive glucose monitoring technology to enhance diabetes management. This is a revolutionary advance in the diagnosis and management of diabetes, reflects the thoughtful modernization of medicine, and promotes the development of digital medicine. This paper reviews the research progress of noninvasive continuous blood glucose monitoring (CGM), with a focus on the biological liquids that replace blood in monitoring systems, the technical principles of continuous noninvasive glucose detection, and the output and calibration of sensor signals. In addition, the existing limits of noninvasive CGM systems and prospects for the future are discussed. This work serves as a resource for further promoting the development of noninvasive CGM systems.

Telemedicine and AI in Remote Patient Monitoring

This article explores how telemedicine, especially with the help of artificial intelligence (AI), is transforming healthcare. It covers its applications in monitoring patients, managing chronic diseases like diabetes, and improving cardiovascular care. The importance of wearable devices and non-invasive blood glucose monitoring is highlighted. The article emphasizes how AI-driven remote patient monitoring can enhance healthcare by providing early intervention, reducing hospitalizations, and offering personalized care

OPTICAL BASED NON INVASIVE GLUCOMETER WITH IOT

Diabetes mellitus (DM) nicknamed as sugar is becoming one of incurable and critical challenge to medical field. Serious illness such as premature mortality even cause of death, which can be identified by continuous monitoring from a remote location. The traditional and conventional method such as finger pricking's demerits such as pain and damage to tissues that cause infection. Such type of infections can be overcome by non-invasive technique. The objective of this paper is to monitor glucose level using non-invasive technique by optical and IoT technology. The proposed sensor circuit consists of IR LED's of wavelength 650–2500nm for optical blood glucose measurement and NIR photodiodes (InGaAs) to receive the reflected light from body parts to determine the glucose level. The Beer-Lambert law is used for signal processing along with WIFI based IoT real time information transmission. The project is implemented using Arduino IDE for finding the performance matrix of the system as well as various analytical studies. With the rapid development of wearable technology and transdermal biosensors, non-invasive blood glucose monitoring will become more efficient, affordable, robust, and more competitive on the market. Key Words: Diabetes mellitus, blood glucose measurement, WIFI based IoT, wearable technology

NON-INVASIVE PPG-BASED ESTIMATION OF BLOOD GLUCOSE LEVEL

This paper focuses on non-invasive blood glucose determination using photoplethysmographic (PPG) signals, which is crucial for managing diabetes. Diabetes stands as one of the world’s major chronic diseases. Untreated diabetes frequently leads to fatalities. Current self-monitoring techniques for measuring diabetes require invasive procedures such as blood or bodily fluid sampling, which may be very uncomfortable. Hence, there is an opportunity for non-invasive blood glucose monitoring through smart devices capable of measuring PPG signals. The primary goal of this research was to propose methods for glycemic classification into two groups (low and high glycemia) and to predict specific glycemia values using machine learning techniques. Two datasets were created by measuring PPG signals from 16 individuals using two different smart devices – a smart wristband and a smartphone. Simultaneously, the reference blood glucose levels were invasively measured using a glucometer. The PPG signals were preprocessed, and 27 different features were extracted. With the use of feature selection, only 10 relevant features were chosen. Numerous machine learning models were developed. Random Forest (RF) and Support Vector Machine (SVM) with the radial basis function (RBF) kernel performed best in classifying PPG signals into two groups. These models achieved an accuracy of 76% (SVM) and 75% (RF) on the smart wristband test dataset. The functionality of the proposed models was then verified on the smartphone test dataset, where both models achieved similar accuracy: 74% (SVM) and 75% (RF). For predicting specific glycemia values, RF performed best. Mean Absolute Error (MAE) was 1.25 mmol/l on the smart wristband test dataset and 1.37 mmol/l on the smartphone test dataset.

A NON-INVASIVE BLOOD GLUCOSE MONITORING FOR DIABETICS WITH BREATH BIOMARKERS: AN ENSEMBLE-OF-CLASSIFIERS MODEL

As a supplemental technique for disease diagnosis, expelled breath monitoring is becoming extremely prevalent. Nevertheless, because of the significant number of factors that must be considered, researchers are forced to create new algorithms for accurate data interpretations. In our study, a novel noninvasive breath biomarkers-based diabetic detection strategy is introduced by upcoming three main processes “pre-processing, feature extraction and diabetes detection”. Raw data (breath signal) are initially pre-processed via data normalization to increase acquired breath signal quality. Most important features, such as “Improved empirical wavelet functions (IEWF), empirical mode decomposition (EMD), local mean decomposition (LMD), continuous wavelet transform (CWT) method, and entropy-based feature,” are extracted from the pre-processed data. These attributes are fused together and are subsequently used to train the ensemble of classifiers in the diabetes detection stage. An ensemble of classifiers, including an “optimized quantum deep neural network (QDNN), a convolutional neural network (CNN), and a recurrent neural network (RNN)”, is used to depict the diabetes detection phase. The CNN and RNN are trained using the retrieved fused features. The optimized QDNN receives the output of the CNN and RNN. The final detected result is provided by the optimized QDNN. A unique hybrid optimization model, Archimedes Principle with Enhanced Honey Badger Exploitation (APEHBE) algorithm, that combines the Archimedes Optimization Algorithm (ArchOA) and the Honey Badger Algorithm (HBA) is used to fine-tune the weight of QDNN. The effectiveness of the anticipated model is then verified by a comparison analysis.

Integrated Device Based on a Sudomotor Nanomaterial for Sweat Detection

The compositions of sweat and blood are related. Therefore, sweat is an ideal noninvasive test body fluid that could replace blood for linear detection of many biomarkers, especially blood glucose. However, access to sweat samples remains limited to physical exercise, thermal stimulation, or electrical stimulation. Despite intensive research, a continuous, innocuous, and stable method for sweat stimulation and detection has not yet been developed. In this study, a nanomaterial for a sweat-stimulating gel based on the transdermal drug delivery system is presented, which transports acetylcholine chloride into the receptors of sweat glands to achieve the function of biological stimulation of skin sweating. The nanomaterial was applied to a suitable integrated sweat glucose detection device for noninvasive blood glucose monitoring. The total amount of evaporated sweat enabled by the nanomaterial is up to 35 μL·cm–2 for 24 h, and the device detects up to 17.65 μM glucose under optimal conditions, showing stable performance regardless of the user’s activity level. In addition, the in vivo test was performed and compared with several studies and products, which showed excellent detection performance and osmotic relationship. The nanomaterial and associated integrated device represent a significant advance in continuous passive sweat stimulation and noninvasive sweat glucose measurement for point-of-care applications.

A Non-Invasive Glucose Monitoring Device using NIR (Near Infra Red)

In a developing country like India, systemic chronic diseases reach unsustainable heights as the population grows. According to WHO, diabetes affects an estimated 28.7 million people worldwide, or 28.5% of the population. Diabetes affects around 8.5 million people who have yet to be diagnosed (2022). Diabetes is one of these metabolic systemic chronic diseases that has captured the world's attention. The primary goal of our research is to develop non-invasive blood glucose monitoring technology that will benefit a large number of patients. We analyze the research progress and significant problems of non-invasive blood glucose detecting technologies in our project evaluation. In our study, we present an effective NIR-based optical detecting system. The existing non-invasive glucose monitoring device had a 60% accuracy level, however the proposed model will have an accuracy of 80% and will have a significant advantage over the existing system. Furthermore, the information is continuously delivered to the personal computer via serial communication via the UART protocol.

Hybrid model with optimal features for non-invasive blood glucose monitoring from breath biomarkers

Analysis of exhaled breath is becoming more and more used as an additional diagnostic technique in medicine. Researchers must create unique algorithms for accurate data interpretation due to the sheer quantity of factors that must be considered. Therefore, a new NICBGM-based model from exhaled breath is introduced in this study. This work exploited median filtering (MF) for pre-processing. Then, “Improved Empirical Wavelet Functions (I-EWF), R-peak detection, QT intervals, PR intervals, Entropy-based feature, improved Discrete wavelet transform (DWT), Continuous Wavelet Transform (CWT), and short-time Fourier transformation (I-STFT)” are extracted. Further, optimal features are chosen, which are then put through a hybrid scheme that combines “Deep Max out (DMO) and Long Short-Term Memory (LSTM)”. Then, the mean is taken by DMO and LSTM to attain the fine result. Here, the Wild Beest Updated HGSO (WBU-HGSO) model is used to optimize the LSTM weights. The final step is an analysis that proves the superiority of the WBU-HGSO-based model.

Non-invasive, intelligent, and continuous monitoring of human blood glucose with UWB dual-antenna and cascade CNN

Finger-prick blood collection process has become unrealistic for a long-term and frequent blood glucose detection. Hence, an appropriate non-invasive detection system is highly desirable to effectively address this concern. A non-invasive and intelligent dual-sensing system is forwarded in this paper. The feasibility of the proposed system has been verified using glucose solution, animal serum, and human trials. In the in vivo experiments, the detection signal exhibited a high correlation (r = 0.96) with blood glucose levels. An improved cascade convolution neural network is suggested to accurately predict the BGL. For the estimation results of BGL, the root mean squared error of 7.3217 mg dl−1 and a mean absolute relative difference of 4.7209% are achieved. The estimated results also fell by 100% in the clinically acceptable zones of the Clarke error grid analysis, indicating that the proposed system could potentially be used for clinical measurements.