摘要：Objectives. We assessed diabetes-related mortality for American Indians and Alaska Natives (AI/ANs) and Whites. Methods. Study populations were non-Hispanic AI/AN and White persons in Indian Health Service (IHS) Contract Health Service Delivery Area counties; Hispanics were excluded. We used 1990 to 2009 death certificate data linked to IHS patient registration records to identify AI/AN decedents aged 20 years or older. We examined disparities and trends in mortality related to diabetes as an underlying cause of death (COD) and as a multiple COD. Results. After increasing between 1990 and 1999, rates of diabetes as an underlying COD and a multiple COD subsequently decreased in both groups. However, between 2000 and 2009, age-adjusted rates of diabetes as an underlying COD and a multiple COD remained 2.5 to 3.5 times higher among AI/AN persons than among Whites for all age groups (20–44, 45–54, 55–64, 65–74, and ≥ 75 years), both sexes, and every IHS region except Alaska. Conclusions. Declining trends in diabetes-related mortality in both AI/AN and White populations are consistent with recent improvements in their health status. Reducing persistent disparities in diabetes mortality will require developing effective approaches to not only control but also prevent diabetes among AI/AN populations. In 2010, 18.8 million Americans had diagnosed diabetes and 7.0 million had undiagnosed diabetes, about 8.3% of the population. 1 Diabetes prevalence is increasing in the United States. 2,3 It disproportionately affects US minority groups, including American Indians and Alaska Natives (AI/ANs). Generally, age-adjusted diabetes prevalence rates (standardized to the 2000 US Standard Million) among AI/AN persons are at least twice those of Whites or the total US population. 1,4–9 Diabetes is more prevalent among AI/AN persons, and they develop diabetes at a younger age, 10 leaving them more vulnerable to the complications of diabetes. Not surprisingly, diabetes ranked as the fourth leading cause of death for AI/AN persons in 2009, whereas it was the seventh leading cause among Whites. 11 In the United States, 637 counties in 35 states are designated by the Indian Health Service (IHS) as Tribal Service Delivery Area or Contract Health Service Delivery Area (CHSDA) counties. In these counties, the IHS provides health care to AI/AN communities directly or through contract health care providers. Of those who self-report that they are AI/AN persons, 64% reside in CHSDA counties. 12 Much of what is known about the disproportionate burden of diabetes on AI/AN mortality is derived from death certificate data, in which AI/AN race is underreported. 11,13–15 A previous study 15 indicated less underreporting for AI/AN race occurred in CHSDA counties. Thus, in terms of racial classification ascertainment, mortality analyses restricted to CHSDA counties may be most appropriate for examining AI/AN disparities in diabetes mortality. The AI/AN Mortality Database (AMD) links death certificate data from the US National Death Index for 1990 to 2009 to records in the IHS patient registration database. 12 The AMD identified and corrected racial misclassification of AI/AN decedents. The AMD may be the best data with which to examine diabetes-related mortality differences between AI/AN and White populations. Therefore, we feel that using the AMD to examine diabetes-related mortality differences between AI/AN and White populations could be the most suitable option.
