Millimeter-wave Adaptive Glucose Concentration Estimation with Complex-Valued Neural Networks

Skin-Penetrating Interfaces for Millimeter-Wave Non-Invasive Glucose Concentration Estimation: Numerical Analysis

Millimeter-wave (MMW) glucose concentration estimation possesses a great advantage of non-invasiveness. The long history of investigation, however, has not yet reached practical applications because of its insufficient accuracy and stability. To solve these problems, this paper proposes two high skin-penetration interfaces, which we name equivalent quarter-wavelength interface and equivalent Brewster's-angle interface. We analyze their scattering characteristics in a frequency range of 60 - 90 GHz. Analysis results show that both the interfaces suppress the body-surface scattering, allowing the MMWs to penetrate through body surface into tissues to extract information on blood-glucose concentration with higher sensitivity, e.g., with 147-times enhancement of phase changes. These interfaces can be an important step toward realizing non-invasive blood glucose concentration estimation.

A Fair Performance Comparison between Complex-Valued and Real-Valued Neural Networks for Disease Detection

Our aim is to contribute to the classification of anomalous patterns in biosignals using this novel approach. We specifically focus on melanoma and heart murmurs. We use a comparative study of two convolution networks in the Complex and Real numerical domains. The idea is to obtain a powerful approach for building portable systems for early disease detection. Two similar algorithmic structures were chosen so that there is no bias determined by the number of parameters to train. Three clinical data sets, ISIC2017, PH2, and Pascal, were used to carry out the experiments. Mean comparison hypothesis tests were performed to ensure statistical objectivity in the conclusions. In all cases, complex-valued networks presented a superior performance for the Precision, Recall, F1 Score, Accuracy, and Specificity metrics in the detection of associated anomalies. The best complex number-based classifier obtained in the Receiving Operating Characteristic (ROC) space presents a Euclidean distance of 0.26127 with respect to the ideal classifier, as opposed to the best real number-based classifier, whose Euclidean distance to the ideal is 0.36022 for the same task of melanoma detection. The 27.46% superiority in this metric, as in the others reported in this work, suggests that complex-valued networks have a greater ability to extract features for more efficient discrimination in the dataset.

A Contactless Glucose Solution Concentration Measurement System Based on Improved High Accurate FMCW Radar Algorithm

To reduce the pain and the probability of cross-infection caused by the invasive blood glucose testing instruments, the ex vivo glucose measurement is of high significance. The electrical property of blood varies with the density of the glucose, which can be sensed by measuring its reflected coefficient in millimeter-wave. In this article, we built a contactless glucose solution concentration measurement system based on 77-GHz FMCW radar. Several preliminary signal processing algorithms are cascaded with a deep neural network to improve the accuracy of glucose solution concentration measurement. Our experiment shows that the resolution of this ex vivo glucose measurement can achieve up to 0.1 mg/mL.

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.

Non-Invasive Determination of Glucose Concentration Using a Near-Field Sensor

The article presents a model of a near-field sensor for non-invasive glucose monitoring. The sensor has a specific design and forms a rather extended near-field. Due to this, the high penetration of electromagnetic waves into highly absorbing media (biologic media) is achieved. It represents a combined slot antenna based on a flexible RO3003 substrate. Moreover, it is small and rather flat (25 mm in diameter, 0.76 mm thick). These circumstances are the distinguishing features of this sensor in comparison with microwave sensors of other designs. The article presents the results of numerical modeling and experimental verification of a near-field sensor. Furthermore, a phantom of human biological media (human hand) was created for experimentation. In the case of numerical modeling, the sensor is located close to the hand model. In a full-scale experiment, it is located close to the phantom of the human hand for the maximum interaction of the near-field with biological materials. As a result of a series of measurements for this sensor, the reflection coefficient is measured, and the dependences of the reflected signal on the frequency are plotted. According to the results of the experiments carried out, there is a clear difference in glucose concentrations. At the same time, the accuracy of determining the difference in glucose concentrations is high. The values of the amplitude of the reflected signal with a change in concentration differ by 0.5-0.8 dB. This sensor can be used for developing a non-invasive blood glucose measurement procedure.

Non-Invasive Glucose Monitoring Using Optical Sensor and Machine Learning Techniques for Diabetes Applications

Diabetes is a major public health challenge affecting more than 451 million people. Physiological and experimental factors influence the accuracy of non-invasive glucose monitoring, and these need to be overcome before replacing the finger prick method. Also, the suitable employment of machine learning techniques can significantly improve the accuracy of glucose predictions. One aim of this study is to use light sources with multiple wavelengths to enhance the sensitivity and selectivity of glucose detection in an aqueous solution. Multiple wavelength measurements have the potential to compensate for errors associated with inter- and intra-individual differences in blood and tissue components. In this study, the transmission measurements of a custom built optical sensor are examined using 18 different wavelengths between 410 and 940 nm. Results show a high correlation value (0.98) between glucose concentration and transmission intensity for four wavelengths (485, 645, 860 and 940 nm). Five machine learning methods are investigated for glucose predictions. When regression methods are used, 9% of glucose predictions fall outside the correct range (normal, hypoglycemic or hyperglycemic). The prediction accuracy is improved by applying classification methods on sets of data arranged into 21 classes. Data within each class corresponds to a discrete 10 mg/dL glucose range. Classification based models outperform regression, and among them, the support vector machine is the most successful with F1-score of 99%. Additionally, Clarke error grid shows that 99.75% of glucose readings fall within the clinically acceptable zones. This is an important step towards critical diagnosis during an emergency patient situation.