An Equation to Estimate the Concentration of Serum Apolipoprotein B

Background: Several large prospective studies have demonstrated that apolipoprotein B (apoB) has greater value in predicting cardiovascular risk than any other lipid measurements. Currently, however, serum apoB levels are not routinely measured, because of the additional cost. The aim of this study was to develop an equation to estimate apoB from conventional lipid measurements including total cholesterol, HDL cholesterol, and triglycerides. Methods: Data from a total of 78,127 subjects (47,057 men and 31,070 women), aged 15 to 88 years (mean age 41.8 years) were reviewed to develop an apoB equation. Additional datasets from the same institution and the NHANES obtained in 2007-2008 were used for internal (n = 73,445) and external validation (n = 3,097), respectively. Results: We developed an apoB equation based on a linear regression model that contains total cholesterol, triglycerides, and HDL cholesterol as terms (model 1). To more precisely estimate the serum apoB level, we adjusted mode1 1 using a cutoff serum triglyceride value of 270 mg/dl (model 2). Model 2 showed more randomly distributed residuals in patients with diabetes, atherogenic dyslipidemia, and those taking lipid-lowering agents than model 1. The residuals in the development, internal validation, and external validation datasets were also randomly distributed around 0 with no clear trends. Conclusion: The new equation we developed to estimate serum apoB concentrations is accurate and can be used in diverse subgroups of patients including those with diabetes, atherogenic dyslipidemia, and those taking lipid-lowering agents.