Glycaemic variability-based classification of impaired glucose tolerance vs. type 2 diabetes using continuous glucose monitoring data

Continuous Glucose Monitoring for Prediabetes: What Are the Best Metrics?

BACKGROUND

Continuous glucose monitoring (CGM) has transformed the care of type 1 and type 2 diabetes, and there is potential for CGM to also become influential in prediabetes identification and management. However, to date, we do not have any consensus guidelines or high-quality evidence to guide CGM goals and metrics for use in prediabetes.

METHODS

We searched PubMed for all English-language articles on CGM use in nonpregnant adults with prediabetes published by November 1, 2023. We excluded any articles that included subjects with type 1 diabetes or who were known to be at risk for type 1 diabetes due to positive islet autoantibodies.

RESULTS

Based on the limited data available, we suggest possible CGM metrics to be used for individuals with prediabetes. We also explore the role that glycemic variability (GV) plays in the transition from normoglycemia to prediabetes.

CONCLUSIONS

Glycemic variability indices beyond the standard deviation and coefficient of variation are emerging as prominent identifiers of early dysglycemia. One GV index in particular, the mean amplitude of glycemic excursion (MAGE), may play a key future role in CGM metrics for prediabetes and is highlighted in this review.

Two novel GCK mutations in Chinese patients with maturity-onset diabetes of the young

PURPOSE

Heterozygous inactivating mutations in the glucokinase (GCK) gene result in the asymptomatic fasting hyperglycemia named as GCK-MODY or MODY2. The genetic testing can effectively avoid the misdiagnosis and inappropriate treatment for GCK-MODY.

METHODS

A total of 25 unrelated families with MODY were screened for mutations in coding region of GCK by using direct sequencing. Three different bioinformatics tools such as PolyPhen2, Mutation Taster and PROVEAN were performed to predict the function of mutant proteins. The glucose profile was recorded by continuous glucose monitoring system (CGMS) to evaluate the glycemic variability for the GCK-MODY patient.

RESULTS

Our study identified five GCK mutations in 24% of the families (6/25): two novel mutations (I126fs and G385A) and three already described mutations (G44S, H50fs and S383L). In silico analyses predicted that these mutations altered structural conformational changes. The values of mean amplitude of glycemic excursions (MAGE), an important index of blood glucose fluctuation in CGMS system, were 0.81 in the first 24 h and 1.61 in the second 24 h record in the patient with GCK-MODY (F3), suggesting little glucose fluctuation.

CONCLUSION

The genetic testing is suggested to be important to differentiate GCK-MODY from other types of diabetes. CGMS might be used to screen GCK-MODY cases prior to genetic testing.

A Combined Method for Diabetes Mellitus Diagnosis Using Deep Learning, Singular Value Decomposition, and Self-Organizing Map Approaches

Diabetes in humans is a rapidly expanding chronic disease and a major crisis in modern societies. The classification of diabetics is a challenging and important procedure that allows the interpretation of diabetic data and diagnosis. Missing values in datasets can impact the prediction accuracy of the methods for the diagnosis. Due to this, a variety of machine learning techniques has been studied in the past. This research has developed a new method using machine learning techniques for diabetes risk prediction. The method was developed through the use of clustering and prediction learning techniques. The method uses Singular Value Decomposition for missing value predictions, a Self-Organizing Map for clustering the data, STEPDISC for feature selection, and an ensemble of Deep Belief Network classifiers for diabetes mellitus prediction. The performance of the proposed method is compared with the previous prediction methods developed by machine learning techniques. The results reveal that the deployed method can accurately predict diabetes mellitus for a set of real-world datasets.

A dual-attention based coupling network for diabetes classification with heterogeneous data

Diabetes Mellitus (DM) is a group of metabolic disorders characterized by hyperglycaemia in the absence of treatment. Classification of DM is essential as it corresponds to the respective diagnosis and treatment. In this paper, we propose a new coupling network with hierarchical dual-attention that utilizes heterogeneous data, including Flash Glucose Monitoring (FGM) data and biomarkers in electronic medical records. The long short-term memory-based FGM sub-network extracts the time-dependent features of dynamic FGM sequences, while the biomarkers sub-network learns the features of static biomarkers. The convolutional block attention module (CBAM) for dispersing the feature weights of the spatial and channel dimensions is implemented into the FGM sub-network to endure the variability of FGM and allows us to extract high-level discriminative features more accurately. To better adjust the importance weights of the characteristics of the two sub-networks, self-attention is introduced to integrate the characteristics of heterogeneous data. Based on the dataset provided by Peking University People's Hospital, the proposed method is evaluated through factorial experiments of multi-source heterogeneous data, ablation studies of various attention strategies, time consumption evaluation and quantitative evaluation. The benchmark tests reveal the proposed network achieves a type 1 and 2 diabetes classification accuracy of 95.835% and the comprehensive performance metrics, including Matthews correlation coefficient, F1-score and G-mean, are 91.333%, 94.939% and 94.937% respectively. In the factorial experiments, the proposed method reaches the maximum area under the receiver operating characteristic curve of 0.9428, which indicates the effectiveness of the coupling between the nominated sub-networks. The coupling network with a dual-attention strategy performs better than the one without or only with a single-attention strategy in the ablation study as well. In addition, the model is also tested on another data set, and the accuracy of the test reaches 94.286%, reflecting that the model is robust when it is transferred to untrained diabetes data. The experimental results show that the proposed method is feasible in the classification of diabetes types. The code is available at https://github.com/bitDalei/Diabetes-Classification-with-Heterogeneous-Data.

Analysis of detrended fluctuation function derived from continuous glucose monitoring may assist in distinguishing latent autoimmune diabetes in adults from T2DM

BACKGROUND

We aimed to explore the performance of detrended fluctuation function (DFF) in distinguishing patients with latent autoimmune diabetes in adults (LADA) from type 2 diabetes mellitus (T2DM) with glucose data derived from continuous glucose monitoring.

METHODS

In total, 71 LADA and 152 T2DM patients were enrolled. Correlations between glucose parameters including time in range (TIR), mean glucose, standard deviation (SD), mean amplitude of glucose excursions (MAGE), coefficient of variation (CV), DFF and fasting and 2-hour postprandial C-peptide (FCP, 2hCP) were analyzed and compared. Receiver operating characteristics curve (ROC) analysis and 10-fold cross-validation were employed to explore and validate the performance of DFF in diabetes classification respectively.

RESULTS

Patients with LADA had a higher mean glucose, lower TIR, greater SD, MAGE and CV than those of T2DM (P<0.001). DFF achieved the strongest correlation with FCP (r = -0.705, P<0.001) as compared with TIR (r = 0.485, P<0.001), mean glucose (r = -0.337, P<0.001), SD (r = -0.645, P<0.001), MAGE (r = -0.663, P<0.001) and CV (r = -0.639, P<0.001). ROC analysis showed that DFF yielded the greatest area under the curve (AUC) of 0.862 (sensitivity: 71.2%, specificity: 84.9%) in differentiating LADA from T2DM as compared with TIR, mean glucose, SD, MAGE and CV (AUC: 0.722, 0.650, 0.800, 0.820 and 0.807, sensitivity: 71.8%, 47.9%, 63.6%, 72.7% and 78.8%, specificity: 67.8%, 83.6%, 80.9%, 80.3% and 72.4%, respectively). The kappa test indicated a good consistency between DFF and the actual diagnosis (kappa = 0.551, P<0.001). Ten-fold cross-validation showed a stable performance of DFF with a mean AUC of 0.863 (sensitivity: 78.8%, specificity: 77.8%) in 10 training sets and a mean AUC of 0.866 (sensitivity: 80.9%, specificity: 84.1%) in 10 test sets.

CONCLUSIONS

A more violent glucose fluctuation pattern was marked in patients with LADA than T2DM. We first proposed the possible role of DFF in distinguishing patients with LADA from T2DM in our study population, which may assist in diabetes classification.

Flash glucose monitoring data analysed by detrended fluctuation function on beta-cell function and diabetes classification

AIM

We aimed to use data-driven glucose pattern analysis to unveil the correlation between the metrics reflecting glucose fluctuation and beta-cell function, and to identify the possible role of this metric in diabetes classification.

MATERIALS AND METHODS

In total, 78 participants with type 1 diabetes and 59 with type 2 diabetes were enrolled in this study. All participants wore a flash glucose monitoring system, and glucose data were collected. A detrended fluctuation function (DFF) was utilized to extract glucose fluctuation information from flash glucose monitoring data and a DFF-based glucose fluctuation metric was proposed.

RESULTS

For the entire study population, a significant negative correlation between the DFF-based glucose fluctuation metric and fasting C-peptide was observed (r = -0.667; P <.001), which was larger than the correlation coefficient between the fasting C-peptide and mean amplitude of plasma glucose excursions (r = -0.639; P < .001), standard deviation (r = -0.649; P <.001), mean blood glucose (r = -0.519; P < .001) and time in range (r = 0.593; P < .001). As glucose data analysed by DFF revealed a clear bimodal distribution among the total participants, we randomly assigned the 137 participants into discovery cohorts (n = 100) and validation cohorts (n = 37) for 10 times to evaluate the consistency and effectiveness of the proposed metric for diabetes classification. The confidence interval for area under the curve according to the receiver operating characteristic analysis in the 10 discovery cohorts achieved (0.846, 0.868) and that for the 10 validation cohorts was (0.799, 0.862). In addition, the confidence intervals for sensitivity and specificity in the discovery cohorts were (75.5%, 83.0%), (81.3%, 88.5%) and (71.8%, 88.3%), (76.5%, 90.3%) in the validation cohorts, indicating the potential capacity of DFF in distinguishing type 1 and type 2 diabetes.

CONCLUSIONS

Our study first proposed the possible role of data-driven analysis acquired glucose metric in predicting beta-cell function and diabetes classification, and a large-scale, multicentre study will be needed in the future.

Simple Linear Support Vector Machine Classifier Can Distinguish Impaired Glucose Tolerance Versus Type 2 Diabetes Using a Reduced Set of CGM-Based Glycemic Variability Indices

BACKGROUND

Many glycemic variability (GV) indices exist in the literature. In previous works, we demonstrated that a set of GV indices, extracted from continuous glucose monitoring (CGM) data, can distinguish between stages of diabetes progression. We showed that 25 indices driving a logistic regression classifier can differentiate between healthy and nonhealthy individuals; whereas 37 GV indices and four individual parameters, feeding a polynomial-kernel support vector machine (SVM), can further distinguish between impaired glucose tolerance (IGT) and type 2 diabetes (T2D). The latter approach has some limitations to interpretability (complex model, extensive index pool). In this article, we try to obtain the same performance with a simpler classifier and a parsimonious subset of indices.

METHODS

We analyzed the data of 62 subjects with IGT or T2D. We selected 17 interpretable GV indices and four parameters (age, sex, BMI, waist circumference). We trained a SVM on the data of a baseline visit and tested it on the follow-up visit, comparing the results with the state-of-art methods.

RESULTS

The linear SVM fed by a reduced subset of 17 GV indices and four basic parameters achieved 82.3% accuracy, only marginally worse than the reference 87.1% (41-features polynomial-kernel SVM). Cross-validation accuracies were comparable (69.6% vs 72.5%).

CONCLUSION

The proposed SVM fed by 17 GV indices and four parameters can differentiate between IGT and T2D. Using a simpler model and a parsimonious set of indices caused only a slight accuracy deterioration, with significant advantages in terms of interpretability.

Continuous Glucose Monitoring Sensors for Diabetes Management: A Review of Technologies and Applications

By providing blood glucose (BG) concentration measurements in an almost continuous-time fashion for several consecutive days, wearable minimally-invasive continuous glucose monitoring (CGM) sensors are revolutionizing diabetes management, and are becoming an increasingly adopted technology especially for diabetic individuals requiring insulin administrations. Indeed, by providing glucose real-time insights of BG dynamics and trend, and being equipped with visual and acoustic alarms for hypo- and hyperglycemia, CGM devices have been proved to improve safety and effectiveness of diabetes therapy, reduce hypoglycemia incidence and duration, and decrease glycemic variability. Furthermore, the real-time availability of BG values has been stimulating the realization of new tools to provide patients with decision support to improve insulin dosage tuning and infusion. The aim of this paper is to offer an overview of current literature and future possible developments regarding CGM technologies and applications. In particular, first, we outline the technological evolution of CGM devices through the last 20 years. Then, we discuss about the current use of CGM sensors from patients affected by diabetes, and, we report some works proving the beneficial impact provided by the adoption of CGM. Finally, we review some recent advanced applications for diabetes treatment based on CGM sensors.

TLR4 gene in the regulation of periodontitis and its molecular mechanism

Regulatory effect of Toll-like receptor 4 (TLR4) gene on periodontitis in mice was investigated to explore its possible mechanism. Thirty C57/BL6 mice were randomly divided into the blank control group (N group, n=10), the periodontitis group (P group, n=10) and the periodontitis + TAK-242 group (PT group, n=10). The mice in P and PT group were ligatured with silk threads dipped with porphyromonas gingivalis (P. gingivalis) in the logarithmic phase to induce experimental periodontitis, and TAK-242 was intraperitoneally injected on the day when the periodontitis model was established. After fasting for 8 h, the expression levels of high-sensitivity C-reactive protein and inflammatory cytokines were measured in each group of mice. Their alveolar bones were isolated and changes were detected. Quantitative polymerase chain reaction was used to detect the expression levels of TLR4. After the mice were given TAK-242, the levels of hs-CPR, MCP-1, IL-6 and IL-1β in the PT group evidently increased (P<0.01) compared with those in the N group. After the mice were administered TAK-242, the alveolar bone density, the percentage of bone volume and the number of bone trabeculae in PT group were significantly reduced, and the bone trabecular space and structural model index were evidently decreased (P<0.01). In addition, the expression levels of and T-bet/GATA3 messenger ribonucleic acids (mRNAs) in peria of mice in the P group were significantly higher than those in the N group (P<0.01), whereas the expression level of Foxp3 mRNA was notably decreased (P<0.01). The involvement of TLR4 gene in the inflammatory response of periodontitis results in periodontitis, and its mechanism may be that it activates TLR4, so as to affect the expression of T-bet, GATA3 and Foxp3.

Assessment of glucose variability in subjects with prediabetes

The aim of the study was to assess glucose variability in subjects with prediabetes by means of CGM.

MATERIAL AND METHODS

32 subjects with prediabetes - mean age 56.6 ± 9.6 years, mean BMI 30.3 ± 5.3 kg/m² and 18 subjects with normal glucose tolerance (NGT) - mean age 54.4 ± 9.9 years, mean BMI 24.8 ± 6.9 kg/m², were enrolled. Glucose tolerance was studied during OGTT. HbA1c was measured by NGSP certified method. CGM was performed with FreeStyle Libre Pro sensor.

RESULTS

The following indices of glucose variability were significantly higher in the prediabetes group - CV (p < 0.041), J-index (p < 0.014), CONGA (p < 0.047) and GRADE (p < 0.036). A significant increase in HbA1c (p < 0.036), mean interstitial glucose (p < 0.025), time above range (p < 0.018) and a significant decrease in time in range (p < 0.014) was found in prediabetes compared to NGT. Significant correlations between HbA1c and LBGI (r = -0.33, p = 0.02), HBGI (r = 0.31, p = 0.03), CONGA (r = 0.36, p = 0.01), J-index (r = 0.37, p = 0.01) and M-value (r = -0.34, p = 0.02) were established.

CONCLUSION

Glucose variability is significantly increased in prediabetes and is an additional parameter in the assessment of glucose homeostasis even at these early stages of glucose dysregulation.

Continuous Glucose Monitoring: Current Use in Diabetes Management and Possible Future Applications

The recent announcement of the production of new low-cost continuous glucose monitoring (CGM) sensors, the approval of marketed CGM sensors for making treatment decisions, and new reimbursement criteria have the potential to revolutionize CGM use. After briefly summarizing current CGM applications, we discuss how, in our opinion, these changes are expected to extend CGM utilization beyond diabetes patients, for example, to subjects with prediabetes or even healthy individuals. We also elaborate on how the integration of CGM data with other relevant information, for example, health records and other medical device/wearable sensor data, will contribute to creating a digital data ecosystem that will improve our understanding of the etiology and complications of diabetes and will facilitate the development of data analytics for personalized diabetes management and prevention.