Geographic Variation of Hospice Use Patterns at the End of Life

Abstract

Background: Little is known about state-level variation in patterns of hospice use, an important indicator of quality of care at the end of life. Findings may identify states where targeted efforts for improving end-of-life care may be warranted.

Objective: Our aim was to characterize the state-level variation in patterns of hospice use among decedents and to examine state, county, and individual factors associated with these patterns.

Methods: We conducted a retrospective analysis of Medicare fee-for-service decedents. The primary outcome measures were state-level hospice use during the last 6 months of life and the state's proportion of hospice users with very short hospice enrollment (≤7 days), very long hospice enrollment (≥180 days), and hospice disenrollment prior to death.

Results: In 2011, the percentage of decedents who used hospice in the last 6 months of life nationally was 47.1%, and varied across states from 20.3% in Alaska to 60.8% in Utah. Hospice utilization patterns also varied by state, with the percentage of hospice users with very short hospice enrollment ranging from 23.0% in the District of Columbia to 39.9% in Connecticut. The percentage of very long hospice use varied from 5.7% in Connecticut to 15.9% in Delaware. The percentage of hospice disenrollment ranged from 6.2% in Hawaii to 19.0% in the District of Columbia. Nationally, state-level hospice use among decedents was positively correlated with the percentage of potentially concerning patterns (including very short hospice enrollment, very long hospice enrollment, and hospice disenrollment) among hospice users (the Pearson correlation coefficient=0.52, p value<0.001). Oregon was the only state in the highest quartile of hospice use and the lowest quartiles of both very short and very long hospice enrollment.

Conclusions: The percentage of decedents who use hospice may mask important state-level variation in these patterns, including the timing of hospice enrollment, a potentially important component of the quality of end-of-life care.

FIG. 1.

Hospice use among decedents and potentially concerning patterns of hospice use across states. (Pearson correlation coefficient=0.516, p<0.001. Dash lines indicate median values.)

FIG. 2.

Quartiles of potentially concerning patterns of hospice use across states (lighter color signifies higher quartile).