Cardiovascular disease (CVD) risk equations are useful to guide treatment decisions for blood pressure and lipid-lowering medications because they identify patients who are at high risk of CVD but do not have either blood pressure or cholesterol measurements above the levels when considering treatment as individual risk factors. National guideline groups can then set thresholds that prioritise the use of these medications to those at high risk of CVD based on this global, or absolute, risk assessment. For example, the National Institute for Health and Care Excellence guidelines in the UK recommend considering use of lipid-lowering measures when the estimated risk is ≥10% over 10 years,1 and the American College of Cardiology/American Heart Association guidelines recommend initiating a discussion regarding lipid-lowering medication when risk is ≥5% over 10 years.2 As shown by the variation across different regions, these thresholds are somewhat arbitrary, but are based on assessments of local resources, costs and values. For both medications, the relative risk reduction has been shown to be approximately constant across strata of baseline risk based on analyses of individual patient data from randomised controlled trials.3 4 This means that benefit is linearly related to baseline risk.

An increasing problem when developing and validating CVD risk equations is how to account for …