Site of Death, Place of Care, and Health Care Transitions Among US Medicare Beneficiaries, 2000-2015

Abstract

Importance: End-of-life care costs are high and decedents often experience poor quality of care. Numerous factors influence changes in site of death, health care transitions, and burdensome patterns of care.

Objective: To describe changes in site of death and patterns of care among Medicare decedents.

Design, setting, and participants: Retrospective cohort study among a 20% random sample of 1 361 870 decedents who had Medicare fee-for-service (2000, 2005, 2009, 2011, and 2015) and a 100% sample of 871 845 decedents who had Medicare Advantage (2011 and 2015) and received care at an acute care hospital, at home or in the community, at a hospice inpatient care unit, or at a nursing home.

Exposures: Secular changes between 2000 and 2015.

Main outcomes and measures: Medicare administrative data were used to determine site of death, place of care, health care transitions, which are changes in location of care, and burdensome patterns of care. Burdensome patterns of care were based on health care transitions during the last 3 days of life and multiple hospitalizations for infections or dehydration during the last 120 days of life.

Results: The site of death and patterns of care were studied among 1 361 870 decedents who had Medicare fee-for-service (mean [SD] age, 82.8 [8.4] years; 58.7% female) and 871 845 decedents who had Medicare Advantage (mean [SD] age, 82.1 [8.5] years; 54.0% female). Among Medicare fee-for-service decedents, the proportion of deaths that occurred in an acute care hospital decreased from 32.6% (95% CI, 32.4%-32.8%) in 2000 to 19.8% (95% CI, 19.6%-20.0%) in 2015, and deaths in a home or community setting that included assisted living facilities increased from 30.7% (95% CI, 30.6%-30.9%) in 2000 to 40.1% (95% CI, 39.9%-30.3% ) in 2015. Use of the intensive care unit during the last 30 days of life among Medicare fee-for-service decedents increased from 24.3% (95% CI, 24.1%-24.4%) in 2000 and then stabilized between 2009 and 2015 at 29.0% (95% CI, 28.8%-29.2%). Among Medicare fee-for-service decedents, health care transitions during the last 3 days of life increased from 10.3% (95% CI, 10.1%-10.4%) in 2000 to a high of 14.2% (95% CI, 14.0%-14.3%) in 2009 and then decreased to 10.8% (95% CI, 10.6%-10.9%) in 2015. The number of decedents enrolled in Medicare Advantage during the last 90 days of life increased from 358 600 in 2011 to 513 245 in 2015. Among decedents with Medicare Advantage, similar patterns in the rates for site of death, place of care, and health care transitions were observed.

Conclusions and relevance: Among Medicare fee-for-service beneficiaries who died in 2015 compared with 2000, there was a lower likelihood of dying in an acute care hospital, an increase and then stabilization of intensive care unit use during the last month of life, and an increase and then decline in health care transitions during the last 3 days of life.

Figure.. Patterns in Site of Death for Medicare Fee-for-Service and Medicare Advantage Decedents Between 2000 and 2015

Site of death reported as an assisted living facility can only be reported when the service code captured that site of care. The denominators are reported in Table 2 with exception of the analyses of assisted living facilities. Data on assisted living facilities were only available for 2009, 2011, and 2015. The denominators for Medicare fee-for-service assisted living facilities includes persons who died while receiving hospice services and were as follows: n = 120 750 for 2009; n = 121 706 for 2011; and n = 126 510 for 2015. The denominators for Medicare Advantage assisted living facilities includes persons who died while receiving hospice services and were as follows: n = 186 810 for 2011 and n = 273 705 for 2015. Categories are not mutually exclusive because patients in the assisted living facility category may also be represented in the home or community category.