Critical care at the end of life: a population-level cohort study of cost and outcomes

Abstract

Background: Despite the high cost associated with ICU use at the end of life, very little is known at a population level about the characteristics of users and their end of life experience. In this study, our goal was to characterize decedents who received intensive care near the end of life and examine their overall health care use prior to death.

Methods: This was a retrospective cohort study that examined all deaths in a 3-year period from April 2010 to March 2013 in Ontario, Canada. Using population-based health administrative databases, we examined healthcare use and cost in the last year of life.

Results: There were 264,754 individuals included in the study, of whom 18% used the ICU in the last 90 days of life; 34.5% of these ICU users were older than 80 years of age and 53.0% had more than five chronic conditions. The average cost of stay for these decedents was CA$15,511 to CA$25,526 greater than for those who were not admitted to the ICU. These individuals also died more frequently in hospital (88.7% vs 36.2%), and spent more time in acute-care settings (18.7 days vs. 10.5 days).

Conclusions: We showed at a population level that a significant proportion of those with ICU use close to death are older, multi-morbid individuals who incur significantly greater costs and die largely in hospital, with higher rates of readmission, longer lengths of stay and higher rates of aggressive care.

Keywords: Costs and cost analysis; Palliative care; Terminal care.

Fig. 1

Healthcare costs in the last 90 days of life. Average healthcare cost per decedent in the last 90 days of life when distributed across healthcare sectors (continuing care, acute care and outpatient care), ICU use and burden of disease (represented by the first and fourth aggregated diagnosis group (ADG) quartiles). Patients in the first ADG quartile have the lowest burden of disease and those in the fourth ADG quartile have the highest burden of disease