Hypoglycemia in Diabetes Mellitus as a Coronary Artery Disease Risk Factor in Patients at Elevated Vascular Risk

Abstract

Context: Although clinical trials have shown that hypoglycemia is associated with coronary artery disease (CAD), little is known whether hypoglycemia is a CAD risk factor in primary care.

Objective: We sought to determine whether previous hypoglycemia was associated with incident CAD, and whether this association differed in patients of different underlying vascular risk.

Design, setting and participants: This is a longitudinal cohort study of diabetes patients without CAD before January 1, 2006 (n = 9173) followed at an academic network of 13 primary care practices from January 1, 2006 to June 30, 2012. Hypoglycemic events before January 1, 2006 were identified via International Classification of Diseases Ninth Revision codes from emergency department, inpatient and outpatient visits.

Main outcome measure: Patients were followed until incident CAD or June 30, 2012. Cox regression with time interaction was used to determine the association between hypoglycemia and CAD (significance set at P ≤ .05). We then tested the association among high vascular risk patients (age ≥ 55 y, hemoglobin A1c ≥ 7.5%, ≥2 risk factors [dyslipidemia, hypertension or obesity]), a subset of high vascular risk patients aged 65 years or older, and the remaining patients with lower vascular risk.

Results: Three percent of patients (n = 285) had previous hypoglycemia. Hypoglycemia was associated with a 2-fold CAD risk (hazard ratio [HR] 2.15; 95% confidence interval [95%CI] 1.24-3.74), adjusting for time interaction and vascular risk factors. Among high vascular risk patients, the risk was 3-fold (HR 3.01 [95%CI 1.15-7.91], n = 1823 [20% of cohort]), and over 4-fold (HR 4.62 [95%CI 1.65-12.9], n = 996) in the subset aged more than or equal to 65 years. No association was found in the remaining 80% of the cohort with lower vascular risk.

Conclusions: Previous hypoglycemia was associated with CAD among high vascular risk patients. Hypoglycemia may not be a CAD risk factor for the majority of primary care patients with lower underlying vascular risk.

Figure 1.

Hazard ratios of hypoglycemia on incident CAD in the entire cohort and in different vascular risk groups. The univariable model included hypoglycemia and a time varying covariate. The CAD risk factor (CAD RF)-adjusted model additionally included age, sex, race/ethnicity, educational attainment, hypertension, dyslipidemia, diabetes duration, BMI, and HbA1c. The fully adjusted model additionally adjusted for LDL, HDL, eGFR, retinopathy, neuropathy and renal failure, cancer, dementia, dysrhythmias, insulin, and sulfonylurea exposure, 3 or more classes of antidiabetic agents, chronic medication count, more than or equal to 5% weight loss within a year, hospitalizations, and 2 or more HbA1c measurements per year.

Figure 2.

Cumulative hazard estimates of hypoglycemia on incident CAD in the entire cohort and in different vascular risk groups. Log rank test was statistically significant for patients age 65 years or older, high vascular risk subgroup (P = .022). Log rank tests were not statistically significant for the entire cohort, P = .450, low vascular risk group, P = .928, and high vascular risk group, P = .095.