A self-organizing map based morphological analysis of oral glucose tolerance test curves in women with gestational diabetes mellitus

Gestational diabetes mellitus (GDM) makes women at risk of type 2 diabetes during their life. In order to predict this later abnormal glucose intolerance, several antepartum and postpartum predictors have been identified. In this study we conjecture that future evolution is predictable from morphology of the oral glucose tolerance test (OGTT) curves at baseline. To test our hypothesis, as a first step we evaluated the association between the curve morphologies of normal and diabetic patient condition at baseline. In particular, we analysed glucose and insulin curves of a group of women with a history of GDM. A Self-organizing map (SOM) was proposed to evaluate shape differences among control, normal, impaired glucose tolerance and diabetic curves shape. We compared our results with the currently applied clinical classification. We found that morphology contains information about the current status of the patient, because the SOM analysis clearly allows to discriminate subjects belonging to healthy or diabetic group. Moreover, SOMs highlighted additional information that could be used for prognostic purposes.