OBJECTIVES: Accounting for changing demography and diabetes prevalence rates, to project the number of people with diagnosed diabetes in US through 2050. METHODS: Our model proceeds in three steps using inverse probability weighting and raking.Created initial sampling weights, defined as the inverse of the probability of selection, plays a pivotal role in desing-based inference in yielding estimates that are designed unbiased and consistent. Last, by applying procedure, known as raking, we adjust our initial weights so that marginal total of adjusted weight on specified characteristics agrees with the corresponding totals for the population. RESULTS: The total number of people with diabetes will rise to almost 26 million in 2025. This is projected at 200% increase over the 2000 levels. Note that these projections imply steady increase in the overall prevalence of diabetes. The largest increases in the number of people with diabetes likely to occur in the older age. The number of women 75 years or greater of age with diabetes will increase almost 380% from 2000 levels. It is demographic changes that account for the largest share of the increase. Twenty percent of the overall projected growth will be due to population growth, 35% will be due to increase in prevalence rate and 45% will be due to changes in demographic compositions. CONCLUSIONS: Diabetes is already recognized as publich health problem of pandemic proportions. Our projection of diabetes burden in US indicate that the situtation may be more alarming than previously recognized. Advances in primary prevention may help reduce the number of people with diabetes. The economic burden of diabetes is already staggering, and future increase in the number of people with the disease will increase the burden. Worldwide surveillance of diabetes is a necessary first step toward its prevention and control.