Objectives To create a risk prediction rule for delirium in elderly adults in the emergency department (ED) and to compare mortality and resource use of elderly adults in the ED with and without delirium. Design Prospective observational study. Setting Urban tertiary care ED. Participants Individuals aged 65 and older presenting for ED care (N = 700). Measurements A trained research assistant performed a structured mental status assessment and attention tests, after which delirium was determined using the Confusion Assessment Method. Data were collected on participant demographics, comorbidities, medications, ED course, hospital and intensive care unit (ICU) admission, length of stay, hospital charges, 30‐day rehospitalization, and mortality. Results Nine percent of elderly study participants had delirium. Using logistic regression, a delirium prediction rule consisting of older age, prior stroke or transient ischemic attack, dementia, suspected infection, and acute intracranial hemorrhage was created had good predictive accuracy (area under the receiver operating characteristic curve = 0.77). Admitted participants with ED delirium had longer median lengths of stay (4 vs 2 days) and were more likely to require ICU admission (13% vs 6%) and to be discharged to a new long‐term care facility (37% vs 9%) than those without. In all participants, ED delirium was associated with higher 30‐day mortality (6% vs 1%) and 30‐day readmission (27% vs 13%). Conclusion This risk prediction rule may help identify a group of individuals in the ED at high risk of developing delirium who should undergo screening, but it requires external validation. Identification of delirium in the ED may enable physicians to implement strategies to decrease delirium duration and avoid inappropriate discharge of individuals with acute delirium, improving outcomes.