Non-invasive Glucose Research Articles

Development of a passive wireless sensor for fluidic detection and characterization utilizing the PCB-based coplanar electrode (PCE) configuration

During the global economic development, there's a growing focus on healthcare, especially in the advancement of medical diagnostic technologies, with a significant emphasis on glucose level evaluation. Glucose biosensors, predominantly electrochemical, have evolved over four generations, with the first three being enzyme-based and known for sensitivity and cost-effectiveness, albeit with limitations due to environmental susceptibility and reliance on enzyme activity. Recent advancements in non-invasive blood glucose monitoring, utilizing optical, microwave, and electrochemical techniques, offer diverse benefits without tissue penetration. Among these, impedance sensing stands out due to its flexibility and integration capability in handheld devices. This study proposes a wireless passive impedance method leveraging the inductor-capacitor (LC) sensing technique and PCB (Printed Circuit Board)-based coplanar electrode (PCE) configuration for fluidic sample detection. The proposed system integrates a two-coplanar-electrode layout with a square spiral inductor to assess fluidic conductivity and characterize various fluid types within samples. The effectiveness of this configuration was validated through experiments with NaCl and glucose solutions, confirming the feasibility of integrating PCB-based coplanar electrodes into conventional LC passive wireless sensing designs for fluidic detection and characterization.

Optimization and validation of a fat-on-a-chip model for non-invasive therapeutic drug discovery.

Obesity is a significant public health concern that is closely associated with various comorbidities such as heart disease, stroke, type II diabetes (T2D), and certain cancers. Due to the central role of adipose tissue in many disease etiologies and the pervasive nature in the body, engineered adipose tissue models are essential for drug discovery and studying disease progression. This study validates a fat-on-a-chip (FOAC) model derived from primary mature adipocytes. Our FOAC model uses a Micronit perfusion device and introduces a novel approach for collecting continuous data by using two non-invasive readout techniques, resazurin and glucose uptake. The Micronit platform proved to be a reproducible model that can effectively maintain adipocyte viability, metabolic activity, and basic functionality, and is capable of mimicking physiologically relevant responses such as adipocyte hypertrophy and insulin-mediated glucose uptake. Importantly, we demonstrate that adipocyte size is highly dependent on extracellular matrix properties, as adipocytes derived from different patients with variable starting lipid areas equilibrate to the same size in the hyaluronic acid hydrogel. This model can be used to study T2D and monitor adipocyte responses to insulin for longitudinally tracking therapeutic efficacy of novel drugs or drug combinations.

Design and Implementation of a Low-Power Device for Non-Invasive Blood Glucose

Glucose is a simple sugar molecule. The chemical formula of this sugar molecule is C6H12O6. This means that the glucose molecule contains six carbon atoms (C), twelve hydrogen atoms (H), and six oxygen atoms (O). In human blood, the molecule glucose circulates as blood sugar. Normally, after eating or drinking, our bodies break down the sugars in food and use them to obtain energy for our cells. To execute this process, our pancreas produces insulin. Insulin “pulls” sugar from the blood and puts it into the cells for use. If someone has diabetes, their pancreas cannot produce enough insulin. As a result, the level of glucose in their blood rises. This can lead to many potential complications, including blindness, disease, nerve damage, amputation, stroke, heart attack, damage to blood vessels, etc. In this study, a non-invasive and therefore easily usable method for monitoring blood glucose was developed. With the experiment carried out, it was possible to measure glucose levels continuously, thus eliminating the disadvantages of invasive systems. Near-IR sensors (optical sensors) were used to estimate the concentration of glucose in blood; these sensors have a wavelength of 940 nm. The sensor was placed on a small black parallelepiped-shaped box on the tip of the finger and the output of the optical sensor was then connected to a microcontroller at the analogue input. Another sensor used, but only to provide more medical information, was the heartbeat sensor, inserted into an armband (along with the microprocessor). After processing and linear regression analysis, the glucose level was predicted, and data were sent via the Bluetooth network to a developed APP. The results of the implemented device were compared with available invasive methods (commercial products). The hardware consisted of a microcontroller, a near-IR optical sensor, a heartbeat sensor, and a Bluetooth module. Another objective of this experiment using low-cost and low-power hardware was to not carry out complex processing of data from the sensors. Our practical laboratory experiment resulted in an error of 2.86 per cent when compared to a commercial product, with a hardware cost of EUR 8 and a consumption of 50 mA.

Comparison of Ensemble Method Performance in Classifying Blood Sugar Levels Output from Non-Invasive Device

Diabetes Mellitus (DM) is a persistent health issue in many countries and is a leading cause of heart disease, kidney failure, and blindness The International Diabetes Federation (IDF) estimated in 2019 that at least 463 million people worldwide aged 20-79 suffer from diabetes. This number is expected to rise to 578 million by 2030 and 700 million by 2045. Machine learning is a type of machine learning that is very helpful in various fields, including healthcare. In classification cases, ensemble methods classify by combining decisions from several other models, one way being through majority voting. Ensemble methods often produce more accurate classification or prediction results. Several ensemble methods include random forest, extra trees, rotation forest, and double random forest. The data used in this study is part of research on the development and clinical testing of a prototype non-invasive blood glucose monitoring device by the non-invasive biomarking team at IPB. The data includes both invasive and non-invasive blood glucose measurements collected in 2019. This study compares the performance of the random forest, extra trees, rotation forest, and double random forest models on blood glucose level data obtained from non-invasive devices. The research results show that the Rotation Forest algorithm is the best model, with the highest average accuracy compared to the other three algorithms, achieving an accuracy level of 0.7142857 (71.42%).

Defect-rich cypress-leaf-like Cu2+1O@NiF for high-performance non-invasive glucose detection with low detection limit

Non-invasive detection of body fluid glucose concentration is of great significance in the diagnosis and treatment of diabetes, which poses a new challenge to the reduction of the detection limit of glucose sensors. In this work, a novel non-enzymatic glucose sensor (defect-rich cypress-leaf-like Cu2+1O@NiF) was proposed by rapid electrodeposition of cypress-leaf-like Cu2+1O on the surface of nickel foam (NiF) substrate. Due to the high electrochemical active surface area and abundant defects of cypress-leaf-like Cu2+1O providing more catalytic active sites, the prepared non-enzymatic sensor has an ultra-low detection limit (0.9 nM), high sensitivity (88,419.4 μA∙mM−1∙cm−2 (1 nM-0.5 μM) and 2095.5 μA∙mM−1∙cm−2 (1 μM-4.33 mM)) and wide linear range (1 nM-4.33 mM) with good selectivity, reproducibility and stability. Furthermore, the obtained sensors exhibited high detection stability, accuracy and recovery for glucose detection of human body fluid samples, which means that the defect-rich cypress-leaf-like Cu2+1O@NiF electrode is an ideal candidate for non-invasive glucose sensors.

Detection and intelligent optimization of blood glucose signals based on MXene-assisted sensors

Two-dimensional materials exhibit unique properties that make them ideal for electronic sensing applications, particularly in the field of biosensors. In this study, a Ti3C2Tx MXene/graphene composite was investigated for its potential use in non-invasive blood glucose detection. The strong electrostatic interaction between MXene and graphene nanosheets effectively reduces the self-stacking of both components, resulting in the formation of a porous interlayer structure with enlarged interlayer spacing. This unique structure creates an efficient nanoscale transport channel, which increases the number of active sites and shortens ion diffusion paths. Consequently, the electrochemical properties of the composite membrane are enhanced, making it a promising candidate for sensing element applications. As the human blood glucose level is primarily determined by the glucose concentration in the blood, the concentration of glucose solution serves as the foundation for noninvasive blood glucose concentration detection. In this work, a prediction model was established using the partial least squares fitting method to correlate the electrochemical fingerprinting data with the glucose aqueous solution concentration, and the reliability of the model was verified. To address the limitations of the partial least squares method, which lacks nonlinear fitting capabilities, an RBF (radial basis function) network model was employed. Finally, a genetic algorithm was utilized to perform global optimization of the training parameters of the RBF network, and the quantitative relationship between the NIR spectral data and glucose concentration was validated. The findings of this study provide a theoretical basis for the development of equipment and the improvement of measurement accuracy in the field of human noninvasive glucose detection.

Optimizing the Performance of AI Model for Non-Invasive Continuous Glucose Monitoring: Hyperparameter Tuning and Random Oversampling Approach

Diabetes Mellitus (DM) as a non-communicable disease (NCD) continues to increase every year. Continuous glucose monitoring (CGM) is essential for effective DM management. However, existing disposable glucose monitoring methods still rely on invasive techniques, cause pain, and lack continuous monitoring capabilities. On the other hand, non-invasive techniques are not feasible for CGM due to the biometric data's complexity and the classification system's inadequate performance. This study aims to develop a non-invasive technology to improve the performance of a non-invasive blood glucose classification system using Artificial Intelligence (AI), specifically Convolutional Neural Network (CNN) and an oversampling technique. The oversampling technique could improve data quantity by balancing the amount of data for each class. This study recruited twenty-three participants in the age range of 20 to 22 years comprising seven females and fifteen males. During data recording sessions, blood glucose levels were simultaneously assessed using a gold-standard glucometer and a non-invasive CGM prototype. The proposed CNN model successfully improved the classification accuracy of non-invasive blood glucose monitoring significantly. With the implementation of oversampling for augmenting the data, the accuracy of the proposed model increased to more than 88%. This study concludes that non-invasive approaches combined with AI technology have the potential to provide a convenient and pain-free alternative to traditional monitoring methods, significantly improving diabetes management and enhancing the overall quality of life for those affected by this condition. These findings could revolutionize the field of diabetes management, offering a more comfortable and accurate monitoring solution that could potentially transform the lives of millions of diabetes patients.

Smart Contact Lens for Colorimetric Visualization of Glucose Levels in the Body Fluid.

Frequent blood glucose monitoring is a crucial routine for diabetic patients. Traditional invasive methods can cause discomfort and pain and even pose a risk of infection. As a result, researchers have been exploring noninvasive techniques. However, a limited number of products have been developed for the market due to their high cost. In this study, we developed a low-cost, highly accessible, and noninvasive contact lens-based glucose monitoring system. We functionalized the surface of the contact lens with boronic acid, which has a strong but reversible binding affinity to glucose. To achieve facile conjugation of boronic acid, we utilized a functional coating layer called poly(tannic acid). The functionalized contact lens binds to glucose in body fluids (e.g., tear) and releases it when soaked in an enzymatic cocktail, allowing for the glucose level to be quantified through a colorimetric assay. Importantly, the transparency and oxygen permeability of the contact lens, which are crucial for practical use, were maintained after functionalization, and the lenses showed high biocompatibility. Based on the analysis of colorimetric data generated by the smartphone application and ultraviolet-visible (UV-vis) spectra, we believe that this contact lens has a high potential to be used as a smart diagnostic tool for monitoring and managing blood glucose levels.

Development and optimisation of a near-infrared spectroscopic system for glucose quantification in aqueous and intralipid-based samples

A non-invasive glucose sensing device could revolutionise diabetes treatment. Near Infrared (NIR) spectroscopy is a promising technology for glucose sensing; however, the design and choice of components for NIR spectroscopy can greatly affect the sensing accuracy. We aimed to develop a NIR absorption spectroscopy system to determine liquid glucose concentrations in the physiological range, by evaluating a range of NIR photodetector components and light sources. Three detection assemblies were tested: (i) a dispersive spectrometer with photodiode array, (ii) a Czerny–Turner monochromator with InGaAs photodiode and (iii) a miniature Fourier Transform Infrared (FTIR) spectrometer. A halogen lamp and NIR globar were trialled as potential light sources. The components were systematically tested by comparing the coefficient of determination and standard error of prediction (SEP) for the same set of aqueous glucose samples through 10 mmol l−1 concentration steps. The Czerny–Turner monochromator with InGaAs photodiode, along with the globar, were identified as the optimal components for the system. A range of concentration steps (1–10 mmol l−1) were scanned to identify the physiologically relevant limit of detection, which was identified as 5 mmol/l for glucose in solution. Spectra were then collected from glucose samples in 10% intralipid suspension in the 10–20 mmol l−1 range and the equivalent concentrations in solution. The SEP was greater for the intralipid samples due to strong scattering. Scattering was dominant above 1300 nm, whilst absorption was dominant below 1300 nm. Although alternative approaches achieve better resolution, our system uses simple and readily-available components and presents a platform for a non-invasive NIR glucose sensing device.

Design and Development of a Non-invasive Opto-Electronic Sensor for Blood Glucose Monitoring Using a Visible Light Source.

Background The management of diabetes is critically dependent on the continuous monitoring of blood glucose levels. Contemporary approaches primarily utilize invasive methods, which often prove to be uncomfortable and can deter patient adherence. There is a pressing need for the development of novel strategies that improve patient compliance and simplify the process of glucose monitoring. Aim and objectives The primary objective of this research is to develop a non-invasive blood glucose monitoring system (NIBGMS) that offers a convenient alternative to conventional invasive methods. This study aims to demonstrate the feasibility and accuracy of using visible laser light at a wavelength of 650 nm for glucose monitoring and to address physiological and technical challenges associated with in vivo measurements. Methods Our approach involved the design of a device that exploits the quantitative relationship between glucose concentration and the refraction phenomena of laser light. The system was initially calibrated and tested using glucose solutions across a range of concentrations (25-500 mg/dL). To get around the problems that come up when people's skin and bodies are different, we combined an infrared (IR) transmitter (800 nm) and receiver that checks for changes in voltage, which are indicative of glucose levels. Results The prototype device was compared with a commercially available blood glucose monitor (Accu-Chek active machine; Roche Diabetes Care, Inc., Mumbai, India). The results demonstrated an average linearity of 95.7% relative to the Accu-Chek machine, indicating a high level of accuracy in the non-invasive measurement of glucose levels. Conclusions The findings suggest that our NIBGMS holds significant promise for clinical application. It reduces the discomfort associated with blood sampling and provides reliable measurements that are comparable to those of existing invasive methods. The successful development of this device paves the way for further commercial translation and could significantly improve the quality of life for individuals with diabetes, by facilitating easier and more frequent monitoring.

Smartphone based wearable sweat glucose sensing device correlated with machine learning for real-time diabetes screening

BackgroundDiabetes is a significant health threat, with its prevalence and burden increasing worldwide indicating its challenge for global healthcare management. To decrease the disease severity, the diabetic patients are recommended to regularly check their blood glucose levels. The conventional finger-pricking test possesses some drawbacks, including painfulness and infection risk. Nowadays, smartphone has become a part of our lives offering an important benefit in self-health monitoring. Thus, non-invasive wearable sweat glucose sensor connected with a smartphone readout is of interest for real-time glucose detection. ResultsWearable sweat glucose sensing device is fabricated for self-monitoring of diabetes. This device is designed as a body strap consisting of a sensing strip and a portable potentiostat connected with a smartphone readout via Bluetooth. The sensing strip is modified by carbon nanotubes (CNTs)-cellulose nanofibers (CNFs), followed by electrodeposition of Prussian blue. To preserve the activity of glucose oxidase (GOx) immobilized on the modified sensing strip, chitosan is coated on the top layer of the electrode strip. Herein, machine learning is implemented to correlate between the electrochemical results and the nanomaterial content along with deposition cycle of prussian blue, which provide the highest current response signal. The optimized regression models provide an insight, establishing a robust framework for design of high-performance glucose sensor. SignificanceThis wearable glucose sensing device connected with a smartphone readout offers a user-friendly platform for real-time sweat glucose monitoring. This device provides a linear range of 0.1–1.5 mM with a detection limit of 0.1 mM that is sufficient enough for distinguishing between normal and diabetes patient with a cut-off level of 0.3 mM. This platform might be an alternative tool for improving health management for diabetes patients.

Noninvasive Real-Time Glucose Monitoring Is in the Near Future.

Objective: Since the introduction of continuous glucose monitoring (CGM) technology, developers have rigorously researched the feasibility of creating a noninvasive glucose monitoring device. In a recent pilot study, investigators reported a strong correlation between glucose values obtained from novel noninvasive monitoring device (GWave) values to venous and capillary glucose measurements. Research Design and Methods: We investigated whether the level of accuracy observed in the pilot study could be reproduced in a larger cohort, using a smaller third-generation manufacturable device (Gen III GWave) containing a standardized sensor chip that can be mass produced for commercial use. The evaluation assessed concordance with capillary blood glucose, reproducibility between two Gen III devices, and accuracy during insulin-induced hypoglycemia. Results: Assessment of samples from 75 subjects (type 2 diabetes, n = 6; type 1 diabetes, n = 28; nondiabetic pregnant subjects, n = 10; and nondiabetic, n = 31) showed that 97% of values were in Zone A with 3% in Zone B of the Clarke Error Grid, with a mean absolute relative difference of 6.7% from reference blood glucose. Comparison between two independent Gen III GWave devices demonstrated reproducibility between the sensors (R2 = 0.95), with 100% of values within Zone A. In the hypoglycemia assessment, measurements from the Gen III sensor tightly followed the capillary glucose measurements down to 42 mg/dL (2.3 mmol/L), whereas the CGM measurements from two different CGM only converged with the GWave and capillary glucose readings after 90 min of decreasing glucose levels. Conclusion: Our results show promise as potentially the first noninvasive technology. Future studies will focus on larger number of people in all glucose ranges. Real-time noninvasive blood glucose monitoring is possible using GWave technology.

Using Artificial Intelligence to Improve the Accuracy of a Wrist-Worn, Noninvasive Glucose Monitor: A Pilot Study.

Self-monitoring of glucose is important to the successful management of diabetes; however, existing monitoring methods require a degree of invasive measurement which can be unpleasant for users. This study investigates the accuracy of a noninvasive glucose monitoring system that analyses spectral variations in microwave signals. An open-label, pilot design study was conducted with four cohorts (N = 5/cohort). In each session, a dial-resonating sensor (DRS) attached to the wrist automatically collected data every 60 seconds, with a novel artificial intelligence (AI) model converting signal resonance output to a glucose prediction. Plasma glucose was measured in venous blood samples every 5 minutes for Cohorts 1 to 3 and every 10 minutes for Cohort 4. Accuracy was evaluated by calculating the mean absolute relative difference (MARD) between the DRS and plasma glucose values. Accurate plasma glucose predictions were obtained across all four cohorts using a random sampling procedure applied to the full four-cohort data set, with an average MARD of 10.3%. A statistical analysis demonstrates the quality of these predictions, with a surveillance error grid (SEG) plot indicating no data pairs falling into the high-risk zones. These findings show that MARD values approaching accuracies comparable to current commercial alternatives can be obtained from a multiparticipant pilot study with the application of AI. Microwave biosensors and AI models show promise for improving the accuracy and convenience of glucose monitoring systems for people with diabetes.

Development of Sweat and Saliva Glucose Sensors as Alternative for Non-Invasive Blood Glucose Monitoring

Development of Sweat and Saliva Glucose Sensors as Alternative for Non-Invasive Blood Glucose Monitoring

Are the variations in ECG morphology associated to different blood glucose levels? implications for non-invasive glucose monitoring for T1D paediatric patients

AimsRecent clinical trials and real-world studies highlighted those variations in ECG waveforms and HRV recurrently occurred during hypoglycemic and hyperglycemic events in patients with diabetes. However, while several studies have been carried out for adult age, there is lack of evidence for paediatric patients. The main aim of the study is to identify the correlations of variations in ECG Morphology waveforms with blood glucose levels in a paediatric population. Methods: T1D paediatric patients who use CGM were enrolled. They wear an additional non-invasive wearable device for recording physiological data and respiratory rate. Glucose metrics, ECG parameters and HRV features were collected, and Wilcoxon rank-sum test and Spearman’s correlation analysis were used to explore if different levels of blood glucose were associated to ECG morphological changes. Results: Results showed that hypoglycaemic events in paediatric patients with T1D are strongly associated with variations in ECG morphology and HRV. Conclusions: Results showed the opportunity of using the ECG as a non-invasive adding instrument to monitor the hypoglycaemic events through the integration of the ECG continuous information with CGM data. This innovative approach represents a promising step forward in diabetes management, offering a more comprehensive and effective means of detecting and responding to critical changes in glucose levels.

The progress of clinical research on the detection of 1,5-anhydroglucitol in diabetes and its complications.

1,5-Anhydroglucitol (1,5-AG) is sensitive to short-term glucose fluctuations and postprandial hyperglycemia, which has great potential in the clinical application of diabetes as a nontraditional blood glucose monitoring indicator. A large number of studies have found that 1,5-AG can be used to screen for diabetes, manage diabetes, and predict the perils of diabetes complications (diabetic nephropathy, diabetic cardiovascular disease, diabetic retinopathy, diabetic pregnancy complications, diabetic peripheral neuropathy, etc.). Additionally, 1,5-AG and β cells are also associated with each other. As a noninvasive blood glucose monitoring indicator, salivary 1,5-AG has much more benefit for clinical application; however, it cannot be ignored that its detection methods are not perfect. Thus, a considerable stack of research is still needed to establish an accurate and simple enzyme assay for the detection of salivary 1,5-AG. More clinical studies will also be required in the future to confirm the normal reference range of 1,5-AG and its role in diabetes complications to further enhance the blood glucose monitoring system for diabetes.

Hydrogels in biosensing and medical diagnostics

This article presents an in-depth examination of recent advancements in medical and biotechnological sensing technologies, focusing on the forefront of innovation in hydrogel-based sensors within the domains of biomedical engineering and regenerative medicine. It delves into cutting-edge sensing technologies that facilitate non-invasive glucose monitoring, highlights progress in the development of intelligent solutions for wound care, and discusses the application of optical and fluorescence-based sensors for real-time diagnostics within the body. Further, it reviews the latest glucose monitoring devices, alongside wearable and implantable sensors designed for the continuous monitoring of health, including the measurement of physiological strain and stress. The exploration extends to the latest in non-invasive and minimally invasive technologies for ongoing health assessment, and to imaging and visualization techniques critical for medical diagnostics and therapeutic procedures. These advancements mark a pivotal move toward more efficient, precise, and patient-focused healthcare technologies, signaling new avenues for diagnosis, monitoring, and treatment in the healthcare sector.

Non-invasive Blood Glucose Monitoring System

The project presents a novel approach to blood glucose monitoring, offering a non-invasive and pain-free method for individuals with diabetes to track their glucose levels. The system utilizes advanced sensor technology coupled with signal processing techniques to detect glucose levels in the body without the need for traditional needle pricking. The key components of the system include a power supply, voltage regulator, ESP32 microcontroller, LCD display, photo sensor, amplifier circuit, and linearization circuit, all seamlessly integrated to provide accurate and real-time glucose readings. This breakthrough technology holds great promise in revolutionizing diabetes management, enhancing the quality of life for millions of affected individuals.By placing the sensor on the individual’s hand, the Glucometer system employs a combination of photonic and electronic principles to non-invasively measure glucose levels. The photo sensor captures specific wavelengths of light that interact with glucose molecules within the tissue, generating a signal proportional to the glucose concentration. This signal is then amplified and processed through the integrated circuits, ensuring accurate linearization and calibration. The ESP32 microcontroller orchestrates these operations, facilitating seamless communication with the LCD display to present the glucose reading in a clear and user-friendly format.The Glucometer’s innovative design eliminates the discomfort associated with traditional blood sampling methods, making it a highly accessible and convenient tool for diabetes management. The system’s efficiency in providing accurate glucose readings without the need for invasive procedures represents a significant advancement in healthcare technology. With further development and refinement, the Glucometer holds the potential to significantly enhance the daily lives of individuals living with diabetes, offering a reliable and painless means of monitoring blood glucose levels.

Non-invasive Blood Glucose Monitoring Using a Radiofrequency Sensor and a Machine Learning Model

Diabetes Mellitus (DM) affects over 530 million people globally and is a condition characterized by high blood glucose (BG) that can result in severe long-term health consequences if poorly managed. To mitigate the risks associated with DM, it is crucial to regulate BG levels through regular monitoring. Current methods of monitoring BG come with drawbacks in the form of pain and expense. With the rapid increase in prevalence of DM, there is an increasing need for economical, accurate, and non-invasive continuous measures of BG. Here we present a validation for a novel sensor that rapidly scans through a wide range of radio frequencies (RF) and uses machine learning (ML) techniques for the purpose of non-invasive BG measurement. After model training, the RF sensor and ML techniques employed in this study can predict BG at a level significantly better than chance, as shown below. Data were collected from 13 healthy participants over a series of tests lasting 2 – 3 hours. During each test, participants placed their forearm on an RF sensor that measured their BG levels using sweeps across the 500 MHz – 1500 MHz range at 0.1 MHz intervals. Participants ingested 37.5 grams of glucose solution to generate BG readings across normoglycemic and hyperglycemic ranges. Each sweep took approximately 22 seconds, including a one second pause between sweeps. Across 110 tests, we collected 3,311 BG observations. Concurrent measurements from a Continuous Glucose Monitor (CGM) were taken as reference. Data were divided using a 60-20-20 (training-validation-test) split and trained on a Light Gradient-Boosting Machine (lightGBM) model to predict BG values. A ‘blind’ evaluation of model performance was determined using the held-out test dataset. We predicted BG values in the held-out test dataset with a Mean Absolute Relative Difference (MARD) of 10.8% in the normoglycemic range and 15.9% in the hyperglycemic range (11.27% overall MARD). These results were significantly better than a chance model (two-sample t-test, p <0.01). In a Surveillance Error Grid analysis of model accuracy, 89.0% of predictions fell in Risk Level 0, 10.1% in Risk Level 1, and 0.9% in Risk Level 2. These results demonstrate that the novel RF sensor and ML techniques described can predict a reference BG value in the population under study. More research is underway to refine and expand these methods using a gold-standard blood glucose reference device and among a broader participant population with an expanded glucose range. DK and VS are consultants for and own stock in Know Labs. JA and KC are employed by and have stock options in Know Labs. CW and KP are consultants for Know Labs. NA. This is the full abstract presented at the American Physiology Summit 2024 meeting and is only available in HTML format. There are no additional versions or additional content available for this abstract. Physiology was not involved in the peer review process.

Reconfigurable Multimode Microwave Sensor With Resonance and Transmission Sensing Capabilities for Noninvasive Glucose Monitoring

Reconfigurable Multimode Microwave Sensor With Resonance and Transmission Sensing Capabilities for Noninvasive Glucose Monitoring