JMIR Publications

ABSTRACT

Background:

HbA1c is a convenient tool to evaluate glycemic status but its ability to detect individuals at risk for Type 2 Diabetes is limited.

Objective:

Exploiting the glycemic variability captured in continuous glucose monitoring (CGM), we used a well-characterised Asian cohort study from Singapore, to assess whether utilising CGM features in a machine learning model can improve detection of prediabetes than HbA1c alone.

Methods:

406 non-diabetic Asian participants underwent an oral glucose tolerance test and had their fasting and 2h plasma glucose concentrations measured, together with HbA1c, to classify them as with normoglycemia or prediabetes. They also wore a CGM sensor for 14 days. CGM profile features were extracted and prediction models were constructed with random subsampling validation to evaluate predictive efficacy. The use of CGM and HbA1c data alone or in combination was assessed for the ability to correctly distinguish prediabetes from normoglycemia.

Results:

In this cohort, 189 (47%) individuals had prediabetes. The majority of the cohort were women (58%) and of Chinese ethnicity (66%). Those with prediabetes were slightly older, heavier and had higher glucose levels with more variability than the normoglycemia group. A two-step approach was used where those with HbA1c ≥ 5.7% were automatically categorised as having prediabetes; the model then focused on the prediction capability of the CGM features among individuals with HbA1c < 5.7%. The prediction models with CGM yielded a lower specificity of 73%-80% (compared to 100% by HbA1c alone) but a vastly improved sensitivity of 40%-55% (compared to 0% by HbA1c alone).

Conclusions:

Adding CGM to HbA1c in a two-step approach, greatly improved the sensitivity of detecting prediabetes in an Asian population. Given the benefits to optimize lifestyle behaviors and its growing acceptability amongst the non-diabetic population, CGM is a promising alternative for type 2 diabetes mellitus risk screening.