There are currently more than 5 million people in the USA living with Alzheimer's disease and other forms of dementia, and prevalence is expected to triple over the next 40 years. As new strategies for prevention and treatment are developed, it will be critically important to be able to identify older adults who do not currently have dementia but have a high risk of developing symptoms within a few years so that they can be targeted for monitoring, prevention and early treatment. In other fields, prognostic models and risk indices are often used to identify high-risk individuals (e.g., Framingham Heart Index and Breast Cancer Risk Assessment Tool). The objective of this paper is to describe the development of Dementia Risk Indices and to discuss the potential for these tools to be incorporated into clinical and research settings for the identification of individuals with a high risk of dementia.