Computerized diagnosis of mild cognitive impairment

We previously described software that we have developed for use in the evaluation of mild cognitive impairment (MCI). Our previous study included an aged nondemented population with memory complaints (n = 41) that was relatively homogenous in terms of education, clinical history, neurological examination, and Mini-Mental Status Examination (MMSE) scores. Performance patterns in the computerized tests separated the subjects into two groups, and we hypothesized that one group might have had incipient dementia.

In the present study we report a follow-up of 35 of the subjects 2 years later. Eight subjects who were thought to have incipient dementia at baseline could be evaluated in the follow-up, and six of them have deteriorated according to both MMSE and neurologists' evaluations and have now fulfilled clinical diagnostic criteria of dementia. The other two deteriorated only according to their computer performance. Of the 27 remaining subjects, only one now fulfilled clinical diagnostic criteria for dementia, although the present computerized examinations identified 10 subjects whose performance has deteriorated compared with the previous session.

The follow-up examination thus supported our hypothesis that human-computer interaction features can contribute to the detection of incipient dementia.