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

Abstract

Many glycaemic variability (GV) indices extracted from continuous glucose monitoring systems data have been proposed for the characterisation of various aspects of glucose concentration profile dynamics in both healthy and non-healthy individuals. However, the inter-index correlations have made it difficult to reach a consensus regarding the best applications or a subset of indices for clinical scenarios, such as distinguishing subjects according to diabetes progression stage. Recently, a logistic regression-based method was used to address the basic problem of differentiating between healthy subjects and those affected by impaired glucose tolerance (IGT) or type 2 diabetes (T2D) in a pool of 25 GV-based indices. Whereas healthy subjects were classified accurately, the distinction between patients with IGT and T2D remained critical. In the present work, by using a dataset of CGM time-series collected in 62 subjects, we developed a polynomial-kernel support vector machine-based approach and demonstrated the ability to distinguish between subjects affected by IGT and T2D based on a pool of 37 GV indices complemented by four basic parameters-age, sex, BMI, and waist circumference-with an accuracy of 87.1%.

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

“…In the present article, we address these limitations and overcome them by working, in parallel, on two fronts: we reduce the number of GV indices by privileging those deemed of most immediate significance, and we forego the application of the kernel trick to our SVM. We demonstrate that these simplifications lead to comparable performance (82.3% accuracy) relative to the complex model presented in Longato et al, 7 arguably with a significant gain in terms of usability and interpretability.…”

“…Particularly in Acciaroli et al, 6 the authors compute 25 literature GV indices from CGM traces, feed them to a cascade of logistic regression classifiers, and successfully distinguish (cross-validation accuracy of 91.4%) healthy subjects from those with either impaired glucose tolerance (IGT) or type 2 diabetes (T2D). In Longato et al, 7 the subsequent distinction between IGT and T2D has since been addressed by considering more GV indices, complementing them with basic individual parameters, and using a more complex model (accuracy of 87.1%). This satisfactory result, however, came at the cost of ease of interpretation, as it relied on a complex model—a support vector machine (SVM) with a polynomial kernel—that, by design, sacrifices a clear input-output relationship to boost performance.…”

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

“…Notably, glycemic variability cannot be captured by sparse SMBG measurements, but it can be detected by CGM almost continuous-time profiles. Several CGM-based glycemic variability metrics have been proposed in the literature [30]. Recently an international panel of physicians, researchers and patients expert in CGM technologies defined the key metrics for CGM data analysis and reporting [31].…”

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

“…For example, mobile decision support systems could be designed not only for people with diabetes but also for healthy individuals as tools to educate subjects about their personal risk factors for diabetes (and other health conditions) and to promote positive behavioral changes. In addition, software applications to identify subjects at high risk of developing diabetes can be designed by implementing models for predicting the onset of diabetes; 94 these models currently include mostly demographics, biometrics and blood test biomarkers as risk factors but can be potentially improved by the incorporation of CGM-based glucose variability indices, 95,96 as well as behavioral, socioeconomic, and environmental factors. This development will allow health care agencies to devise targeted prevention and screening plans for diabetes, thus promoting the efficient use of resources.…”