Hospitalization of nursing home residents in an acute-care geriatric department: Direct versus emergency room admission

Background: Transfer to an emergency room and hospitalization of nursing home residents is a growing problem that is poorly defined and reported. Objectives: To assess the clinical effectiveness of a pilot project involving hospitalization of nursing home residents directly to an acute-care geriatric department. Methods: We retrospectively compared the hospitalization in an acute-care geriatric unit of 126 nursing home residents admitted directly to the unit and 80 residents admitted through the emergency room. The variables measured included length of stay, discharge disposition, mortality, cause of hospitalization, chronic medical condition, cognitive state, functional status at admission, and change of functional status during the hospital stay. Follow-up data were obtained from medical records during the 2 year study. Results: No significant differences between the groups were found for length of stay, mortality, discharge disposition and most characteristics of the hospital stay. The only significant difference was in patients' mean age, as emergency room patients were significantly older (86 vs. 82.9 years). The most common condition among nursing home patients admitted via the emergency room was febrile disease (36.9%), while functional decline was the most common in those coming directly from the nursing home (32.5%). The prevalence of functional dependence and dementia were similar in both groups. Functional status did not change throughout the hospital stay in most patients. Conclusions: Treatment of selected nursing home residents admitted directly from the nursing home to an acute-care geriatric unit is feasible, medically effective, results in the safe discharge of almost all such patients and provides an alternative to transfer to an emergency room. This study suggests that quality gains and cost-effective measures may be achieved by such a project, although a randomized controlled trial is necessary to support this hypothesis.