Dementia is an important risk factor for delirium, but the optimal strategy for incorporating cognitive impairment into delirium risk assessment at the time of hospital admission is unknown. We compared 2 informant-based screening tools for dementia and mild cognitive impairment [AD8 and D=(MC)] to the Mini Mental State Examination (MMSE) and Mini-cog in predicting hospital-acquired delirium. This prospective cohort study at an academic medical center consisted of 162 medical inpatients over age 50 years without delirium upon admission. Each participant was evaluated using the MMSE, Mini-cog, AD8, and D=(MC) upon admission and was assessed daily for delirium. An MMSE≤24 carried a 5.5 [95% confidence intervals (CI), 2.7-11.1] relative risk for delirium, whereas cognitive impairment detected by the Mini-cog, D=(MC), or AD8 carried a 2-fold risk. Adding the D=(MC) to the MMSE increased the sensitivity for predicting delirium from 52% (range, 32% to 73%) for the MMSE alone to 65% (range, 46% to 85%) if either test was positive. If both were positive, specificity was maximized at 97% (range, 94% to 100%), but sensitivity was 17% (range, 2% to 33%). The MMSE and Mini-cog identify a large proportion of patients at risk for hospital-acquired delirium, but the combination of performance-based and an informant-based screens may maximize specificity and sensitivity.