The Framingham Heart Study is a population-based cohort study wherein subjects have been evaluated biennially for cardiovascular risk factors and cardiovascular endpoints since 1948 . Over the years, additional data have been accumulated on sociodemographic and life-style factors and the cohort members have been screened for a variety of novel risk factors and non-cardiac disease conditions such as dementia, osteoporosis, cancer, visual loss and hearing impairment. Of the original 5209 subjects, 920 subjects are alive; their current mean age is 86 years. Thus we have a well-characterized cohort of 'old-old' subjects, traditionally defined as subjects over the age of 80 or 85 years. This is the fastest growing segment of the U.S. population and the study of the incidence of dementia and risk factors associated with dementia in this population is of enormous public health importance.
The incidence of disease is estimated in medical and public health applications using a variety of different techniques. Most of these techniques are discussed in detail in books on survival analysis [2-7], epidemiologic methods [8, 9] or biostatistical methods [10,11], Other techniques have been presented in the statistical or epidemiologic literature [12-17], or have simply been applied in the medical or public health literature . Many of these methods have not yet made their way to popular statistical software packages and their application requires custom programming.
We present a macro written in the SAS macro language that produces several estimates of disease incidence for use in the analysis of prospective cohort data. This work was motivated by research in Alzheimer's disease (AD) in the Framingham Study in which the development of AD has been prospectively assessed over an observation period of 24 years. Our goal is to use these data to estimate: (i) crude and age group-specific yearly incidence of AD; (ii) age-adjusted yearly incidence of AD within selected subgroups; and (iii) the future risk of developing AD conditional on survival dementia-free to selected ages. We estimate future risk for predefined periods and the remaining lifetime risk, using traditional unadjusted cumulative incidence (UCI), and cumulative incidence adjusted for the competing risk of death (ACI).
Was this article helpful?