Predicting Type 2 Diabetes Metabolic Phenotypes Using Continuous Glucose Monitoring and a Machine Learning Framework

Abstract

AbstractType 2 diabetes (T2D) and prediabetes are classically defined by the level of fasting glucose or surrogates such as hemoglobin HbA1c. This classification does not take into account the heterogeneity in the pathophysiology of glucose dysregulation, the identification of which could inform targeted approaches to diabetes treatment and prevention and/or predict clinical outcomes. We performed gold-standard metabolic tests in a cohort of individuals with early glucose dysregulation and quantified four distinct metabolic subphenotypes known to contribute to glucose dysregulation and T2D: muscle insulin resistance, β-cell dysfunction, impaired incretin action, and hepatic insulin resistance. We revealed substantial inter-individual heterogeneity, with 34% of individuals exhibiting dominance or co-dominance in muscle and/or liver IR, and 40% exhibiting dominance or co-dominance in β-cell and/or incretin deficiency. Further, with a frequently-sampled oral glucose tolerance test (OGTT), we developed a novel machine learning framework to predict metabolic subphenotypes using features from the dynamic patterns of the glucose time-series (“shape of the glucose curve”). The glucose time-series features identified insulin resistance, β-cell deficiency, and incretin defect with auROCs of 95%, 89%, and 88%, respectively. These figures are superior to currently-used estimates. The prediction of muscle insulin resistance and β-cell deficiency were validated using an independent cohort. We then tested the ability of glucose curves generated by a continuous glucose monitor (CGM) worn during at-home OGTTs to predict insulin resistance and β-cell deficiency, yielding auROC of 88% and 84%, respectively. We thus demonstrate that the prediabetic state is characterized by metabolic heterogeneity, which can be defined by the shape of the glucose curve during standardized OGTT, performed in a clinical research unit or at-home setting using CGM. The use of at-home CGM to identify muscle insulin resistance and β-cell deficiency constitutes a practical and scalable method by which to risk stratify individuals with early glucose dysregulation and inform targeted treatment to prevent T2D.Article HighlightsThe study challenges the conventional classification of type 2 diabetes (T2D) and prediabetes based solely on glycemic levels. Instead, the results highlight the heterogeneity of underlying physiological processes that represent separate pathways to hyperglycemia. Individuals with normoglycemia and prediabetes can be classified according to the relative contribution of four distinct metabolic subphenotypes: insulin resistance, muscle and hepatic, β-cell dysfunction, and incretin defect, which comprise a single dominant or codominant physiologic process in all but 9% of individuals.Use of multiple time points during OGTT generates time-series data to better define the shape of the glucose curve: the application of a novel machine learning framework utilizing features derived from dynamic patterns in glucose time-series data demonstrates high predictive accuracy for identifying metabolic subphenotypes as measured by gold-standard tests in the clinical research unit. This method predicts insulin resistance, β-cell deficiency, and incretin defect better than currently-used estimates, with auROCs of 95%, 89%, and 88%, respectively.The muscle insulin resistance and β-cell deficiency prediction models above were validated with an independent cohort and then tested using glucose data series derived from OGTT performed at home with a continuous glucose monitor (auROC of at-home prediction of insulin resistance and β-cell deficiency is 88% and 84%, respectively). This approach offers a practical and scalable method for metabolic subphenotyping and risk stratification in individuals with normoglycemia or prediabetes, with potential to inform targeted treatments to prevent progression to T2D.