Evaluation of a Continuous Blood Glucose Monitor: A Novel and Non-Invasive Wearable Using Bioimpedance Technology

BACKGROUND

Frequent blood glucose level (BGL) monitoring is essential for effective diabetes management. Poor compliance is common due to the painful finger pricking or subcutaneous lancet implantation required from existing technologies. There are currently no commercially available non-invasive devices that can effectively measure BGL. In this real-world study, a prototype non-invasive continuous glucose monitoring system (NI-CGM) developed as a wearable ring was used to collect bioimpedance data. The aim was to develop a mathematical model that could use these bioimpedance data to estimate BGL in real time.

METHODS

The prototype NI-CGM was worn by 14 adult participants with type 2 diabetes for 14 days in an observational clinical study. Bioimpedance data were collected alongside paired BGL measurements taken with a Food and Drug Administration (FDA)-approved self-monitoring blood glucose (SMBG) meter and an FDA-approved CGM. The SMBG meter data were used to improve CGM accuracy, and CGM data to develop the mathematical model.

RESULTS

A gradient boosted model was developed using a randomized 80-20 training-test split of data. The estimated BGL from the model had a Mean Absolute Relative Difference (MARD) of 17.9%, with the Parkes error grid (PEG) analysis showing 99% of values in clinically acceptable zones A and B.

CONCLUSIONS

This study demonstrated the reliability of the prototype NI-CGM at collecting bioimpedance data in a real-world scenario. These data were used to train a model that could successfully estimate BGL with a promising MARD and clinically relevant PEG result. These results will enable continued development of the prototype NI-CGM as a wearable ring.

Feature Transformation for Efficient Blood Glucose Prediction in Type 1 Diabetes Mellitus Patients

Diabetes Mellitus, a metabolic disease, causes the body to lose control over blood glucose regulation. With recent advances in self-monitoring systems, a patient can access their personalized glycemic profile and may utilize it for efficient prediction of future blood glucose levels. An efficient diabetes management system demands the accurate estimation of blood glucose levels, which, apart from using an appropriate prediction algorithm, depends on discriminative data representation. In this research work, a transformation of event-based data into discriminative continuous features is proposed. Moreover, a multi-layered long short-term memory (LSTM)-based recurrent neural network is developed for the prediction of blood glucose levels in patients with type 1 diabetes. The proposed method is used to forecast the blood glucose level on a prediction horizon of 30 and 60 min. The results are evaluated for three patients using the Ohio T1DM dataset. The proposed scheme achieves the lowest RMSE score of 14.76 mg/dL and 25.48 mg/dL for prediction horizons of 30 min and 60 min, respectively. The suggested methodology can be utilized in closed-loop systems for precise insulin delivery to type 1 patients for better glycemic control.

Learning the structure of the mTOR protein signaling pathway from protein phosphorylation data

Statistical learning of the structures of cellular networks, such as protein signaling pathways, is a topical research field in computational systems biology. To get the most information out of experimental data, it is often required to develop a tailored statistical approach rather than applying one of the off-the-shelf network reconstruction methods. The focus of this paper is on learning the structure of the mTOR protein signaling pathway from immunoblotting protein phosphorylation data. Under two experimental conditions eleven phosphorylation sites of eight key proteins of the mTOR pathway were measured at ten non-equidistant time points. For the statistical analysis we propose a new advanced hierarchically coupled non-homogeneous dynamic Bayesian network (NH-DBN) model, and we consider various data imputation methods for dealing with non-equidistant temporal observations. Because of the absence of a true gold standard network, we propose to use predictive probabilities in combination with a leave-one-out cross validation strategy to objectively cross-compare the accuracies of different NH-DBN models and data imputation methods. Finally, we employ the best combination of model and data imputation method for predicting the structure of the mTOR protein signaling pathway.

Stacked LSTM based deep recurrent neural network with kalman smoothing for blood glucose prediction

BACKGROUND

Blood glucose (BG) management is crucial for type-1 diabetes patients resulting in the necessity of reliable artificial pancreas or insulin infusion systems. In recent years, deep learning techniques have been utilized for a more accurate BG level prediction system. However, continuous glucose monitoring (CGM) readings are susceptible to sensor errors. As a result, inaccurate CGM readings would affect BG prediction and make it unreliable, even if the most optimal machine learning model is used.

METHODS

In this work, we propose a novel approach to predicting blood glucose level with a stacked Long short-term memory (LSTM) based deep recurrent neural network (RNN) model considering sensor fault. We use the Kalman smoothing technique for the correction of the inaccurate CGM readings due to sensor error.

RESULTS

For the OhioT1DM (2018) dataset, containing eight weeks' data from six different patients, we achieve an average RMSE of 6.45 and 17.24 mg/dl for 30 min and 60 min of prediction horizon (PH), respectively.

CONCLUSIONS

To the best of our knowledge, this is the leading average prediction accuracy for the ohioT1DM dataset. Different physiological information, e.g., Kalman smoothed CGM data, carbohydrates from the meal, bolus insulin, and cumulative step counts in a fixed time interval, are crafted to represent meaningful features used as input to the model. The goal of our approach is to lower the difference between the predicted CGM values and the fingerstick blood glucose readings-the ground truth. Our results indicate that the proposed approach is feasible for more reliable BG forecasting that might improve the performance of the artificial pancreas and insulin infusion system for T1D diabetes management.

EPTs-TL: A two-level approach for efficient event prediction in healthcare

Recently, the event prediction on time series (EPTs) was discussed as one of the important and interesting research trends that its usage is growing for taking proper decisions in the various sciences. In the real-world, time series event-based analysis can pose as one of the challenging prediction problems in healthcare, which have a direct impact and a key role in supporting health management. In this paper, an efficient approach of two-level (TL) is proposed to the EPTs problem in healthcare, which named EPTs-TL. At the first level, unseen time series data is predicted by using an enhanced hybrid model based on soft computing technology. Then, a new feature extraction-based method is proposed for fuzzy detection of future events in two-level. The EPTs -TL approach employed concepts of three components: weighting, fuzzy logic, and metaheuristics in two-level of the proposed approach. The empirical results demonstrate the excellent performance of the EPTs -TL approach in comparison to conventional prediction models in healthcare and medicine. Also, the proposed approach can be introduced as a strong tool to handle the complex and uncertain behaviors of time series, analyze unusual variations of those, forewarn the possible critical situations in the society, and fuzzy predict event in healthcare.

Pattern Recognition Reveals Characteristic Postprandial Glucose Changes: Non-Individualized Meal Detection in Diabetes Mellitus Type 1

Accurate continuous glucose monitoring (CGM) is essential for fully automated glucose control in diabetes mellitus type 1. State-of-the-art glucose control systems automatically regulate the basal insulin infusion. Users still need to manually announce meals to dose the prandial insulin boluses. An automated meal detection could release the user and improve the glucose regulation. In this study, patterns in the postprandial CGM data are exploited for meal detection. Binary classifiers are trained to recognize the postprandial pattern in horizons of the estimated glucose rate of appearance and in CGM data. The appearance rate is determined by moving horizon estimation based on a simple model. Linear discriminant analysis (LDA) is used for classification. The proposed method is compared to methods that detect meals when thresholds are violated. Diabetes care data from 12 free-living pediatric patients was downloaded during regular screening. Experts identified meals and their start by retrospective evaluation. The classification was tested by cross-validation. Compared to the threshold-based methods, LDA showed higher sensitivity to meals with a low rate of false alarms. Classifying horizons outperformed the other methods also with respect to time of detection. The onset of meals can be detected by pattern recognition based on estimated model states and consecutive CGM measurements. No individual tuning is necessary. This makes the method easily adopted in the clinical practice.

Differences Between Flash Glucose Monitor and Fingerprick Measurements

Freestyle Libre (FL) is a factory calibrated Flash Glucose Monitor (FGM). We investigated Mean Absolute Relative Difference (MARD) between Self Monitoring of Blood Glucose (SMBG) and FL measurements in the first day of sensor wear in 39 subjects with Type 1 diabetes. The overall MARD was 12.3%, while the individual MARDs ranged from 4% to 25%. Five participants had a MARD ≥ 20%. We estimated bias and lag between the FL and SMBG measurements. The estimated biases range from -1.8 mmol / L to 1.4 mmol / L , and lags range from 2 min to 24 min . Bias is identified as a main cause of poor individual MARDs. The biases seem to persist in days 2⁻7 of sensor usage. All cases of MARD ≥ 20% in the first day are eliminated by bias correction, and overall MARD is reduced from 12.3% to 9.2%, indicating that adding support for voluntary user-supplied bias correction in the FL could improve its performance.

Effect of sensor location on continuous intraperitoneal glucose sensing in an animal model

Background

In diabetes research, the development of the artificial pancreas has been a major topic since continuous glucose monitoring became available in the early 2000’s. A prerequisite for an artificial pancreas is fast and reliable glucose sensing. However, subcutaneous continuous glucose monitoring carries the disadvantage of slow dynamics. As an alternative, we explored continuous glucose sensing in the peritoneal space, and investigated potential spatial differences in glucose dynamics within the peritoneal cavity. As a secondary outcome, we compared the glucose dynamics in the peritoneal space to the subcutaneous tissue.

Material and methods

Eight-hour experiments were conducted on 12 anesthetised non-diabetic pigs. Four commercially available amperometric glucose sensors (FreeStyle Libre, Abbott Diabetes Care Ltd., Witney, UK) were inserted in four different locations of the peritoneal cavity and two sensors were inserted in the subcutaneous tissue. Meals were simulated by intravenous infusions of glucose, and frequent arterial blood and intraperitoneal fluid samples were collected for glucose reference.

Results

No significant differences were discovered in glucose dynamics between the four quadrants of the peritoneal cavity. The intraperitoneal sensors responded faster to the glucose excursions than the subcutaneous sensors, and the time delay was significantly smaller for the intraperitoneal sensors, but we did not find significant results when comparing the other dynamic parameters.