Abstract
Computerized administration of neuropsychological tests can be an objective, sensitive and efficient way to screen for and monitor cognitive changes in the elderly. However, current computer software still suffers from limitations in both the administration of those tests and the interpretation of their results, which might severely hamper their usability. In this paper qualitative aspects of current methods and their use in the prediction of dementia are discussed, guidelines for correct design and usage of computerized methods are suggested and a solution that overcomes several of the methodological limitations is proposed.
Keywords: Computerized neuropsychological test, human-computer interaction, mild cognitive impairment, dementia, neuropsychological tests, Alzheimer prediction