Empirical Index for Easy Assessment of Pancreatic Beta-Cell Glucose Sensitivity During Pregnancy: A Machine Learning Approach

Based on data measured during an oral glucose tolerance test, machine learning techniques were implemented to derive a simple empirical index for the estimation of the pancreatic beta-cell function in pregnant women, as assessed by mathematical modelling (beta-cell glucose sensitivity parameters). We studied a group of 84 pregnant women, who were analyzed by measuring and assessing a wide set of variables and parameters. Through a LASSO regularized support vector machine, we analyzed such wide batteries of variables/parameters and identified an index based on a simple algebraic equation (including glucose and C-peptide measurements only), which can predict the beta-cell glucose sensitivity with good accuracy (R
²
=0.64, p<0.0001, in the test set). In conclusion, the index is a good surrogate marker for the assessment of model-based beta-cell glucose sensitivity in pregnant women, thus it can be useful for easy application in the clinical context, where modelling analysis is not always possible.