Prediction Of Glucose Concentration Research Articles

AI powered electrochemical multi-component detection of insulin and glucose in serum

Multi-component detection of insulin and glucose in serum is of great importance and urgently needed in clinical diagnosis and treatment due to its economy and practicability. However, insulin and glucose can hardly be determined by traditional electrochemical detection methods. Their mixed oxidation currents and rare involvement in the reaction process make it difficult to decouple them. In this study, AI algorithms are introduced to power the electrochemical method to conquer this problem. First, the current curves of insulin, glucose, and their mixed solution are obtained using cyclic voltammetry. Then, seven features of the cyclic voltammetry curve are extracted as characteristic values for detecting the concentrations of insulin and glucose. Finally, after training using machine learning algorithms, insulin and glucose concentrations are decoupled and regressed accurately. The entire detection process only takes three minutes. It can detect insulin at the pmol level and glucose at the mmol level, which meets the basic clinical requirements. The average relative error in predicting insulin concentrations is around 6.515%, and that in predicting glucose concentrations is around 4.36%. To verify the performance and effectiveness of the proposed method, it is used to determine the concentrations of insulin and glucose in fetal bovine serum and real clinical serum samples. The results are satisfactory, demonstrating that the method can meet basic clinical needs. This multi-component testing system delivers acceptable detect limit and accuracy and has the merits of low cost and high efficiency, holding great potential for use in clinical diagnosis.

Physical Activity and Psychological Stress Detection and Assessment of Their Effects on Glucose Concentration Predictions in Diabetes Management.

Continuous glucose monitoring (CGM) enables prediction of the future glucose concentration (GC) trajectory for making informed diabetes management decisions. The glucose concentration values are affected by various physiological and metabolic variations, such as physical activity (PA) and acute psychological stress (APS), in addition to meals and insulin. In this work, we extend our adaptive glucose modeling framework to incorporate the effects of PA and APS on the GC predictions. A wristband conducive of use by free-living ambulatory people is used. The measured physiological variables are analyzed to generate new quantifiable input features for PA and APS. Machine learning techniques estimate the type and intensity of the PA and APS when they occur individually and concurrently. Variables quantifying the characteristics of both PA and APS are integrated as exogenous inputs in an adaptive system identification technique for enhancing the accuracy of GC predictions. Data from clinical experiments illustrate the improvement in GC prediction accuracy. The average mean absolute error (MAE) of one-hour-ahead GC predictions with testing data decreases from 35.1 to 31.9mg/dL (p-value = 0.01) with the inclusion of PA information, and it decreases from 16.9 to 14.2mg/dL (p-value = 0.006) with the inclusion of PA and APS information. The first-ever glucose prediction model is developed that incorporates measures of physical activity and acute psychological stress to improve GC prediction accuracy. Modeling the effects of physical activity and acute psychological stress on glucose concentration values will improve diabetes management and enable informed meal, activity and insulin dosing decisions.

Sammon's mapping regression for the quantitative analysis of glucose from both mid infrared and near infrared spectra.

This paper proposes a novel regression method based on Sammon's mapping dimensionality reduction technique for the quantification of glucose from both near infrared and mid infrared spectra. The proposed regression model was validated to determine the concentration of glucose from the spectra of aqueous mixtures consisting of human serum albumin and glucose in phosphate buffer solution from both near infrared (NIR) and mid infrared (MIR) regions. The performance of the proposed prediction model has been analysed with traditional regression methods principal component regression (PCR) and partial least squares regression (PLSR) models. The results indicate that the proposed model yields improved prediction performance compared to PCR and PLSR methods. In detail, the proposed Sammon's mapping regression (SMR) model provides better prediction ability by reducing the root mean square error of prediction (RMSEP) from 35.74 mg dL-1 for PCR and 31.39 mg dL-1 for PLSR to 21.89 mg dL-1 for the proposed regression model in the MIR region and the RMSEP has been reduced from 38.15 mg dL-1 for the PCR model and 37.5 mg dL-1 for the PLSR model to 29.74 mg dL-1 for the SMR model in the NIR region.

Prediction of Blood Glucose Concentration Based on CEEMD and Improved Particle Swarm Optimization LSSVM.

Aiming at the difficulty of accurate prediction due to the randomness and nonstationary nature of blood glucose concentration series, a blood glucose concentration prediction model based on complementary ensemble empirical mode decomposition (CEEMD) and least squares support vector machine (LSSVM) is proposed. Firstly, CEEMD is used to convert the blood glucose concentration sequence into a series of intrinsic mode functions (IMFs) to reduce the impact of randomness and nonstationary signals on prediction performance. Then, a LSSVM prediction model is established for each mode IMF. The comprehensive learning particle swarm optimization (CLPSO) algorithm is used to optimize the kernel parameters of LSSVM. Finally, the prediction results of all IMFs are superimposed to yield the final blood glucose concentration prediction value. The experimental results show that the proposed prediction model has higher prediction accuracy in short-term blood glucose concentration values.

Tuning monoclonal antibody galactosylation using Raman spectroscopy-controlled lactic acid feeding.

A key aspect of large-scale production of biotherapeutics is a well-designed and consistently-executed upstream cell culture process. Process analytical technology tools provide enhanced monitoring and control capabilities to support consistent process execution, and also have potential to aid in maintenance of product quality at desired levels. One such tool, Raman spectroscopy, has matured as a useful technique to achieve real-time monitoring and control of key cell culture process attributes. We developed a Raman spectroscopy-based nutrient control strategy to enable dual control of lactate and glucose levels for a fed-batch CHO cell culture process for monoclonal antibody (mAb) production. To achieve this, partial least squares-based chemometric models for real-time prediction of glucose and lactate concentrations were developed and deployed in feedback control loops. In particular, feeding of lactic acid post-metabolic shift was investigated based on previous work that has shown the impact of lactate levels on ammonium as well as mAb product quality. Three feeding strategies were assessed for impact on cell metabolism, productivity, and product quality: bolus-fed glucose, glucose control at 4 g/L, or simultaneous glucose control at 4 g/L and lactate control at 2 g/L. The third feeding strategy resulted in a significant reduction in ammonium levels (68%) while increasing mAb galactosylation levels by approximately 50%. This work demonstrated that when deployed in a cell culture process, Raman spectroscopy is an effective technique for simultaneous control of multiple nutrient feeds, and that lactic acid feeding can have a positive impact on both cell metabolism and mAb product quality.

Influence of Raman Spectrometer Collection Efficiency on Performance of Noninvasive Blood Glucose Detection for Device Miniaturization.

Recently the world population with diabetes has increased significantly, and the market demand for noninvasive blood glucose monitoring has increased accordingly. Our previous study demonstrated the capability to detect glucose through the direct observation of glucose Raman fingerprint peaks from in vivo skin but using a benchtop device. From the perspective of commercialization, miniaturized devices are expected to make more impact on the market than bulky benchtop devices. In this study, as an effort for commercialization of noninvasive glucose sensing technology, we investigate the relationship between Raman spectrometer specification, especially collection efficiency, and glucose prediction performance. Raman spectra were synthesized at given spectrometer collection efficiencies in computer simulation, in which spectra are designed to contain glucose signal at specific concentrations. Then, we estimated glucose concentrations back using regression analysis and evaluated prediction performances. Finally, the relationship was analyzed between the collection efficiencies and glucose prediction performances. In order to mimic actual conditions with skin tissue, Monte-Carlo simulations were conducted to count the number of Raman photons escaping from the skin surface in a multi-layered skin model. As the collection efficiency decreased from 3.2 % to 0.2 %, the correlation coefficient between the actual and predicted glucose concentrations dropped from 0.91 to 0.35. The glucose Raman peaks at 1125 cm-1 was identified as the most important wavelength for glucose sensing. This study may help identify optimal Raman spectrometer specifications for transcutaneous blood glucose sensing in miniaturized devices and commercialize noninvasive blood glucose sensors in Raman spectroscopy.

Blood glucose concentration prediction based on kernel canonical correlation analysis with particle swarm optimization and error compensation

Background and objective: Blood glucose levels in humans change over time. Continuous glucose monitoring system (CGMS), can constantly monitor the change of blood glucose concentration. Given the historical data of blood glucose, predicting the trend of blood glucose in a short term is important for diabetes. Appropriate behaviors can be adopted to prevent hypoglycemia or hyperglycemia. Methods: The method proposed in this paper only uses historical blood glucose data as input, rather than complex multi-dimensional input. Previous articles have demonstrated that canonical correlation analysis (CCA) can effectively predict blood glucose. The linear relationship between historical blood glucose values and predicted values was only considered regrettably. To compensate for this, this paper adds a kernel function to find out the non-linear relationship between blood glucose. In the introduced kernel function, some parameters need to be adjusted. To reduce the deviation caused by manual parameter adjustment, this paper discusses the role of particle swarm optimization (PSO). Besides, this article puts forward an error compensation for CCA to enhance the precision. Finally based on the prediction results of PSO-KCCA, a personalized hypoglycemic warning threshold is proposed. Results: The proposed method is validated using clinical data by the root mean square error (RMSE) and differential coefficient (R2). The average RMSE result in PSO-KCCA was 8.01, 11.98, 12.45, 13.23, 14.53, 16.40 mg/dL in prediction horizon (PH) =5, 10, 15, 20, 25, 30 min. The average R2 was 0.95, 0.95, 0.98, 0.97, 0.98, and 0.97, respectively. The CCA with error compensation (EC-CCA) reduced RMSE by 33.45% compared with CCA. For the hypoglycemic warning, the average sensitivity obtained at 6 different PH values was 94.37%, and the specificity was 92.25%. Conclusions: The experimental results confirm the effectiveness of PSO-KCCA in blood glucose prediction. The proposed EC-CCA successfully reduces the delay in the time series prediction. The personalized hypoglycemic warning threshold consider the influence of the model accuracy on the prediction results. This method guarantees the rate of underreporting during monitoring and ensures patient safety.

Noninvasive blood glucose monitoring system based on near-infrared method

Diabetes is considered one of the life-threatening diseases in the world which need continuous monitoring to avoid the complication of diabetes. There is a need to develop a non-invasive monitoring system that avoids the risk of infection problems and pain caused by invasive monitoring techniques. This paper presents a method for developing a noninvasive technique to predict the blood glucose concentration (BCG) based on the Near-infrared (NIR) light sensor. A prototype is developed using a finger sensor based on LED of 940 nm wavelength to collect photoplethysmography (PPG) signal which is variable depending on the glucose concentration variance, a module circuit to preprocess PPG signals is realized, which includes an amplifier and analog filter circuits, an Arduino UNO is used to analog-to-digital conversion. A digital Butterworth filterer is used to remove PPG signal trends, then detect the PPG data peaks to determine the relationship between the PPG signal and (BCG) and use it as input parameters to build the calibration model based on linear regression. Experiments show that the Root Mean Squares Error (RMSE) of the prediction is between 8.264mg/dL and 13.166 mg/dL, the average of RMSE is about 10.44mg/dL with a correlation coefficient (R^2) of 0.839, it is observed that the prediction of glucose concentration is in the clinically acceptable region of the standard Clark Error Grid (CEG).

Accurate prediction of glucose concentration and identification of major contributing features from hardly distinguishable near-infrared spectroscopy

In this study, we tackle the accurate prediction of glucose aqueous concentration from hardly distinguishable near-infrared (NIR) spectroscopy. We adopted several machine learning approaches for the spectral analyses and identified important features learned by each model. The models we investigated include Partial Least Squares Regression (PLSR), Support Vector Machine Regression (SVMR), Random Forest Regression (RF), Extra Trees Regression (ETR), eXtreme Gradient Boosting (Xgboost), and hybrid Principal Component Analysis-Neural Network (PCA-NN) methods. From 47 different glucose aqueous concentrations which cover the range of 40–500 mg/dl, we measured 564 near-infrared (NIR) absorbance spectra samples with wavelength range 900 nm–2200 nm. Then the spectra samples were randomly split into 80% for the training set and 20% for the testing set. In our test, we found that the models SVMR, ETR, and PCA-NN reach extremely good performance, which had correlation coefficient R > 0.99 and determination of coefficient R2 > 0.985. To explore the robustness of each machine learning approach, we extracted their high-weighting features and examine their distribution. We found that having large overlapping of the high-weighting features learned by the model when trained by different data sets may be an indication of model stability. In addition, our analysis came up with the essential region of features to disentangle the hardly distinguishable signal. Our study demonstrates a robust machine learning models for the prediction of glucose aqueous concentration in an in-vitro setup using near-infrared spectroscopy.

Detection of glucose concentration in a turbid medium using a stacked auto-encoder deep neural network

In order to detect the components of a turbid medium, this paper proposes a glucose concentration reconstruction method based on a stacked auto-encoder (SAE) deep neural network. Analysis of different optical properties is performed using multiple diffused reflection spectroscopy and multiple source-detector separation (SDS). In this experiment, a 20% intralipid solution was used to prepare 4%, 5% and 10% intralipid solutions as the research object. At a certain glucose concentration, thirty source-detector separations of diffused reflection spectral signals within the 0.47–4.095 mm range (0.125 mm interval) from the incident position were detected, and a SAE deep neural network was used for modeling and predicting glucose concentration under multiple spectra. The root mean square error of prediction (RMSEP) of the SAE deep neural network using the 4% and 5% intralipid solutions decreased by approximately 26.42% compared with the results using only the 4% intralipid solutions by partial least squares regression (PLSR) method. Moreover, the RMSEP of the SAE deep neural network using the 4% and 5% intralipid solutions decreased by approximately 34.25% compared with the PLSR method using the 5% intralipid solution sample. These results show that the reconstruction accuracy of the SAE deep neural network is higher than the traditional PLSR method, which proves that the SAE neural network is highly suitable for prediction of turbid medium concentration.

Counting-based microfluidic paper-based devices capable of analyzing submicroliter sample volumes.

In this paper, we report the development of semiquantitative counting-based lateral flow assay (LFA)-type microfluidic paper-based analytical devices ( PADs) to analyze samples at submicroliter volumes. The ability to use submicroliter sample volumes is a significant advantage for PADs since it enables enhanced multiplexing, reduces cost, and increases user-friendliness since small sample volumes can be collected using methods that do not require trained personnel, such as finger pricking and microneedles. The challenge of accomplishing a semiquantitative test readout using submicroliter sample volumes was overcome with a counting-based approach. In order to use submicroliter sample volumes, we developed a flow strategy with a running liquid to facilitate flow through the assay. The efficacy of the devices was confirmed with glucose and total human immunoglobulin E (IgE) tests using 0.5 l and 1 l of sample solutions, respectively. Semiquantitative results were generated to predict glucose concentrations in the range of 0-12 mmol/l and IgE concentrations in the range of 0-400 ng/ml. The counting-based approach correlates the number of dots that exhibited a color change to the concentration of the analyte, which provides a more user-friendly method as compared with interpreting the intensity of a color change. The devices reported herein are the first counting-based LFA-type PADs capable of semiquantitative testing using submicroliter sample volumes.

CausalBG: Causal Recurrent Neural Network for the Blood Glucose Inference With IoT Platform

Predicting blood glucose concentration facilitates timely preventive measures against health risks induced by abnormal glucose events. Advances in IoT devices, such as continuous blood glucose monitors (CGMs) have made it convenient for measurements of blood glucose in real time. However, accurate and personalized blood glucose concentration prediction is still challenging. Previous inference models yield low-inference accuracy due to the ineffective feature extraction and the limited, imbalanced personal training data. The underlying causal correlations among the blood glucose series are scarcely captured by these models. In this article, we propose CausalBG, a causal recurrent neural network (CausalRNN) deployed on an IoT platform with smartphones and CGM for the accurate and efficient individual blood glucose concentration prediction. CausalBG automatically captures the underlying causal relationships embedded in the blood glucose features through CausalRNN, and efficiently shares the limited personal data among users for the sufficient training via the multitask framework. Evaluations and case studies on 112 users demonstrate that CausalBG significantly outperforms the conventional predictive models on the blood glucose dynamics inference.

A Glucose Prediction Model based on Variational Mode Decomposition and Least Squares Support Vector Regression

Online prediction of subcutaneous glucose concentration plays a critical role in glucose management for type 1 diabetes. In this work, a new method combining Variational Mode Decomposition (VMD) and Least Squares Support Vector Regression (LSSVR) is proposed with three main stages to improve the prediction accuracy. Firstly, the time series of blood glucose are decomposed into different frequency series by VMD method. Secondly, the LSSVR model is trained to predict each subsequence. Finally, the predicted sequences are reconstructed to obtain the overall glucose predictions. The experimental results demonstrate the effectiveness and accuracy of the proposed model for short term glucose prediction.

Prediction of Glucose Concentration in Blood Plasma with Support Vector Regression Algorithm

Diabetes Mellitus is due to the disorder of glucose metabolism because of defects in insulin secretion or insulin action. It has become a major health challenge nowadays. Monitoring and regulation of blood glucose is inevitable to avoid diabetic complications. Prediction of near future glucose levels and giving alert for appropriate action could be done by machine learning techniques. This would greatly assist the diabetes patients in the daily management of diabetes. This paper discusses the effectiveness of Support Vector Regression in diabetes management. The methodology has been applied to three different data sets and performance measure is analyzed with Root Mean Square Error values.

Comparison of Raman and Mid-Infrared Spectroscopy for Real-Time Monitoring of Yeast Fermentations: A Proof-of-Concept for Multi-Channel Photometric Sensors

Raman and mid-infrared (MIR) spectroscopy are useful tools for the specific detection of molecules, since both methods are based on the excitation of fundamental vibration modes. In this study, Raman and MIR spectroscopy were applied simultaneously during aerobic yeast fermentations of Saccharomyces cerevisiae. Based on the recorded Raman intensities and MIR absorption spectra, respectively, temporal concentration courses of glucose, ethanol, and biomass were determined. The chemometric methods used to evaluate the analyte concentrations were partial least squares (PLS) regression and multiple linear regression (MLR). In view of potential photometric sensors, MLR models based on two (2D) and four (4D) analyte-specific optical channels were developed. All chemometric models were tested to predict glucose concentrations between 0 and 30 g L−1, ethanol concentrations between 0 and 10 g L−1, and biomass concentrations up to 15 g L−1 in real time during diauxic growth. Root-mean-squared errors of prediction (RMSEP) of 0.68 g L−1, 0.48 g L−1, and 0.37 g L−1 for glucose, ethanol, and biomass were achieved using the MIR setup combined with a PLS model. In the case of Raman spectroscopy, the corresponding RMSEP values were 0.92 g L−1, 0.39 g L−1, and 0.29 g L−1. Nevertheless, the simple 4D MLR models could reach the performance of the more complex PLS evaluation. Consequently, the replacement of spectrometer setups by four-channel sensors were discussed. Moreover, the advantages and disadvantages of Raman and MIR setups are demonstrated with regard to process implementation.

Near Infrared Spectrum for Non-Invasive Glucose Measurement

This paper deals with novel approach for non-invasive glucose monitoring based on NIR spectroscopy. The technique was demonstrated on 300 human serums of different concentrations range of 08-297 mg/dl. In order to compare the proposed approach to a standard one, a regression analysis was performed and used to predict glucose concentration overall range of values. In vitro experiments showed a strong correlation between noninvasively device result and real glucose concentration. The correlation was 0.97 and Clarke error grid analysis showed that 97.33% of the measured fall within the clinically acceptable regions. Results showed that the created model can open a new path to a real-time, painless and a portable device that would well-being the lives of millions of diabetics in the world.

Near Infrared Spectrum for Non-Invasive Glucose Measurement

This paper deals with novel approach for non-invasive glucose monitoring based on NIR spectroscopy. The technique was demonstrated on 300 human serums of different concentrations range of 08-297 mg/dl. In order to compare the proposed approach to a standard one, a regression analysis was performed and used to predict glucose concentration overall range of values. In vitro experiments showed a strong correlation between noninvasively device result and real glucose concentration.

A Noninvasive Accurate Measurement of Blood Glucose Levels with Raman Spectroscopy of Blood in Microvessels.

Raman spectra of human skin obtained by laser excitation have been used to non-invasively detect blood glucose. In previous reports, however, Raman spectra thus obtained were mainly derived from the epidermis and interstitial fluid as a result of the shallow penetration depth of lasers in skin. The physiological process by which glucose in microvessels penetrates into the interstitial fluid introduces a time delay, which inevitably introduces errors in transcutaneous measurements of blood glucose. We focused the laser directly on the microvessels in the superficial layer of the human nailfold, and acquired Raman spectra with multiple characteristic peaks of blood, which indicated that the spectra obtained predominantly originated from blood. Incorporating a multivariate approach combining principal component analysis (PCA) and back propagation artificial neural network (BP-ANN), we performed noninvasive blood glucose measurements on 12 randomly selected volunteers, respectively. The mean prediction performance of the 12 volunteers was obtained as an RMSEP of 0.45 mmol/L and R2 of 0.95. It was no time lag between the predicted blood glucose and the actual blood glucose in the oral glucose tolerance test (OGTT). We also applied the procedure to data from all 12 volunteers regarded as one set, and the total predicted performance was obtained with an RMSEP of 0.27 mmol/L and an R2 of 0.98, which is better than that of the individual model for each volunteer. This suggested that anatomical differences between volunteer fingernails do not reduce the prediction accuracy and 100% of the predicted glucose concentrations fall within Region A and B of the Clarke error grid, allowing acceptable predictions in a clinically relevant range. The Raman spectroscopy detection of blood glucose from microvessels is of great significance of non-invasive blood glucose detection of Raman spectroscopy. This innovative method may also facilitate non-invasive detection of other blood components.

Model-Based Conditional Weighted Residuals Analysis for Structural Model Assessment

Nonlinear mixed effects models are widely used to describe longitudinal data to improve the efficiency of drug development process or increase the understanding of the studied disease. In such settings, the appropriateness of the modeling assumptions is critical in order to draw correct conclusions and must be carefully assessed for any substantial violations. Here, we propose a new method for structure model assessment, based on assessment of bias in conditional weighted residuals (CWRES). We illustrate this method by assessing prediction bias in two integrated models for glucose homeostasis, the integrated glucose-insulin (IGI) model, and the integrated minimal model (IMM). One dataset was simulated from each model then analyzed with the two models. CWRES outputted from each model fitting were modeled to capture systematic trends in CWRES as well as the magnitude of structural model misspecifications in terms of difference in objective function values (ΔOFVBias). The estimates of CWRES bias were used to calculate the corresponding bias in conditional predictions by the inversion of first-order conditional estimation method’s covariance equation. Time, glucose, and insulin concentration predictions were the investigated independent variables. The new method identified correctly the bias in glucose sub-model of the integrated minimal model (IMM), when this bias occurred, and calculated the absolute and proportional magnitude of the resulting bias. CWRES bias versus the independent variables agreed well with the true trends of misspecification. This method is fast easily automated diagnostic tool for model development/evaluation process, and it is already implemented as part of the Perl-speaks-NONMEM software.

Multispectral photoacoustic sensing for accurate glucose monitoring using a supercontinuum laser

Accurate monitoring of glucose levels constitutes the most important parameter for diabetes management and treatment planning. In this work, we report on an in vitro glucose monitoring system based on multispectral photoacoustic sensing (MSPAS) using a cost-effective supercontinuum (SC) laser. We demonstrate for the first time, to the best of our knowledge, how the use of a broadband SC source allows the identification of distinct absorption characteristics of two major analytes (glucose and cholesterol) present in the human body in the extended near-infrared 1540–1840 nm spectral range. Employing the reported SC-based MSPAS system with a ratiometric analysis, we were able to accurately (coefficient of determination ≥0.938) measure a wide range of glucose concentration levels in vitro. We further demonstrate clinically accurate prediction of glucose concentrations over commonly encountered physiological levels inside the human body (0–400 mg/dL) with reference to a Clarke error grid analysis. These findings pave the way for devising potentially noninvasive and label-free continuous glucose monitoring systems.