The following is a summary of “Correlation analysis of diabetes based on Copula,” published in the February 2024 issue of Endocrinology by Liu et al.

Researchers conducted a retrospective study to investigate whether the ratio of Triglycerides (TG) to high-density lipoprotein cholesterol (HDL-C) could predict diabetes diagnoses.

They utilized the Copula function to model and fit the non-linear correlation among fasting blood glucose (Glu), glycosylated hemoglobin (HbA1C), and TG/HDL-C in diabetic patients. The chosen Copula function included the two-dimensional Archimedes and Elliptical distribution family and the multidimensional Vine Copula function for data fitting. The fitting effect was evaluated using the mean absolute error (MAE) and mean square error (MSE).

The results showed that the Clayton Copula demonstrates superior effectiveness in fitting the pairwise relationship between Glu and the ratio of TG/HDL-C, as well as HbA1C and TG/HDL-C, with the smallest fitting error. Moreover, the Vine Copula function yields a satisfactory fit for the relationship among all three indicators. Compared to linear analysis methods, the Copula function more precisely depicts the correlation among these three indicators.

Investigators concluded that Copula function revealed stronger correlations, especially for lower Glu and HbA1C/TG/HDL-C, suggesting its potential for accurate auxiliary diabetes diagnosis.

Source: frontiersin.org/journals/endocrinology/articles/10.3389/fendo.2024.1291895/full