The effect of comorbidities on glycemic control among Colombian adults with diabetes mellitus: a longitudinal approach with real-world data

Abstract

Background: Achieving an optimal glycemic control has been described to reduce the incidence of diabetes mellitus (DM) related complications. The association between comorbidities and glycemic control remains unclear. Our aim is to evaluate the effect of comorbidities on glycemic control in people living with DM.

Methods: A retrospective longitudinal study on data from the National Registry of Chronic Kidney Disease from 2014 to 2019 in Colombia. The outcome was poor glycemic control (PGC = HbA1c ≥7.0%). The association between each comorbidity (hypertension (HTN), chronic kidney disease (CKD) or obesity) and PGC was evaluated through multivariate mixed effects logistic regression models. The measures of effect were odds ratios (OR) and their 95% confidence intervals (CI). We also evaluated the main associations stratified by gender, insurance, and early onset diabetes as well as statistical interaction between each comorbidity and ethnicity.

Results: From 969,531 people at baseline, 85% had at least one comorbidity; they were older and mostly female. In people living with DM and CKD, the odds of having a PGC were 78% (OR: 1.78, CI 95%: 1.55-2.05) higher than those without CKD. Same pattern was observed in obese for whom the odds were 52% (OR: 1.52, CI 95%: 1.31-1.75) higher than in non-obese. Non-significant association was found between HTN and PGC. We found statistical interaction between comorbidities and ethnicity (afro descendant) as well as effect modification by health insurance and early onset DM.

Conclusions: Prevalence of comorbidities was high in adults living with DM. Patients with concomitant CKD or obesity had significantly higher odds of having a PGC.

Keywords: Chronic kidney Disease; Comorbidity; Diabetes mellitus; Glycated hemoglobin A1c; Hypertension; Obesity.

Fig. 1

Eligibility flow of studied population from the National Registry of Chronic Kidney Disease, Colombia 2014-2019. Abbreviations: DM: diabetes mellitus, NRCKD: National Registry of Chronic Kidney Disease, HbA1c: glycated hemoglobin

Fig. 2

Longitudinal trend of glycated hemoglobin by comorbidities. Colombia 2014-2019. Figure 2 shows the variation on HbA1c over time by comorbidities. In general, there was a pattern on HbA1c levels in people with diabetes and HTN (a) or CKD (b), characterized by higher HbA1c in those without the comorbidities. However, an inverse trend was observed in obese (c). Abbreviations: HTN: hypertension, CKD: chronic kidney disease, HbA1c: glycated hemoglobin

Fig. 3

Predicted probabilities of poor glycemic control according to comorbidities and ethnicity, Colombia 2014-2019. Figure 3 shows the predicted probabilities of poor glycemic control according to the presence of comorbidities and ethnicity estimated in a multivariate model adjusted by for age, gender, BMI (only for HTN and CKD), health insurance and diabetes duration. Predicted probabilities of poor glycemic control were significantly lower in afro descendant with HTN (a). An opposite association was found in afro descendant with CKD (b). In afro descendant with obesity, the association was similar to those with HTN although it was not statistically significant (c). Abbreviations: HTN: hypertension, CKD: chronic kidney disease, HbA1c: glycated hemoglobin, BMI: body mass index