Site of death among nursing home residents in the United States: changing patterns, 2003-2007

Abstract

Context: The proportion of US deaths occurring in nursing homes (NHs) has been increasing in the past 2 decades and is expected to reach 40% by 2020. Despite being recognized as an important setting in the provision of end-of-life (EOL) care, little is known about the quality of care provided to dying NH residents. There has been some, but largely anecdotal evidence suggesting that many US NHs transfer dying residents to hospitals, in part to avoid incurring the cost of providing intensive on-site care, and in part because they lack resources to appropriately serve the dying residents. We assessed longitudinal trends and geographic variations in place of death among NH residents, and examined the association between residents' characteristics, treatment preferences, and the probability of dying in hospitals.

Methods: We used the Minimum Data Set (NH assessment records), Medicare denominator (eligibility) file, and Medicare inpatient and hospice claims to identify decedent NH residents. In CY2003-2007, there were 2,992,261 Medicare-eligible NH decedents from 16,872 US Medicare- and/or Medicaid-certified NHs. Our outcome of interest was death in NH or in a hospital. The analytical strategy included descriptive analyses and multiple logistic regression models, with facility fixed effects, to examine risk-adjusted temporal trends in place of death.

Findings: Slightly more than 20% of decedent NH residents died in hospitals each year. Controlling for individual-level risk factors and for facility fixed effects, the likelihood of residents dying in hospitals has increased significantly each year between 2003 through 2007.

Conclusions: This study fills a significant gap in the current literature on EOL care in US nursing homes by identifying frequent facility-to-hospital transfers and an increasing trend of in-hospital deaths. These findings suggest a need to rethink how best to provide care to EOL nursing home residents.

Keywords: Nursing homes; hospitalization; place of death.

Figure 1

Percent of deaths occurring in hospitals and nursing homes –all decedents, long and short stay: CY2003–2007 The dots represent the percentage of deaths that occurred either in hospitals or nursing homes each year. The curved line represents the temporal trend in the percentage of deaths, estimated by the best fitting fractional polynomial model. The shaded area indicates the 95% confidence interval.

Figure 2

Percent of decedent nursing home residents with DNR and DNH orders and using hospice in the last 30 days of life: CY2003–2007

Figure 3

Distribution of in-hospital deaths among decedent nursing home residents, by state (CY2003–2007)