Geographic variation of inpatient care costs at the end of life

Background: costs incurred at the end of life are a main contributor to healthcare expenditure. Urban-rural inequalities in health outcomes have been demonstrated. Issues around geographical patterning of the association between time-to-death and expenditure remain under-researched. It is unknown whether differences in outcomes translate into differences in costs at the end of life. Methods: we used a large representative sample of the Scottish population obtained from death records linked to acute inpatient care episodes. We performed retrospective analyses of costs and recorded the most frequent reasons for the last hospital admission. Using a two-part model, we estimated the probability of healthcare utilisation and costs for those patients who incurred positive costs. Results: effects of geography on costs were similar across diagnoses. We did not observe a clear gradient for costs, which were lower in other urban areas compared with large urban areas. Patients from remote and very remote areas incurred higher costs than patients from large, urban areas. The main driver of increased costs was increased length of stay. Conclusions: our results provide evidence of additional costs associated with remote locations. If length of stay and costs are to be reduced, alternative care provision is required in rural areas. Lower costs in other urban areas compared with large urban areas may be due to urban centres incurring higher costs through case-mix and clinical practice. If inequalities are driven by hospital admission, for an end of life scenario, care delivered closer to home or home-based care seems intuitively attractive and potentially cost-saving.