Spoken Language Derived Measures for Detecting Mild Cognitive Impairment

A representation and interpretation of the area under a receiver operating characteristic (ROC) curve obtained by the "rating" method, or by mathematical predictions based on patient characteristics, is presented. It is shown that in such a setting the area represents the probability that a randomly chosen diseased subject is (correctly) rated or ranked with greater suspicion than a randomly chosen non-diseased subject. Moreover, this probability of a correct ranking is the same quantity that is estimated by the already well-studied nonparametric Wilcoxon statistic. These two relationships are exploited to (a) provide rapid closed-form expressions for the approximate magnitude of the sampling variability, i.e., standard error that one uses to accompany the area under a smoothed ROC curve, (b) guide in determining the size of the sample required to provide a sufficiently reliable estimate of this area, and (c) determine how large sample sizes should be to ensure that one can statistically detect differences in the accuracy of diagnostic techniques.

To estimate the age-specific incidence rate of mild cognitive impairment (MCI) according to sex and educational level and to explore the course of MCI, particularly its progression to AD, in a population-based cohort. A community-based cohort of nondemented elderly people (Personnes Agées QUID [PAQUID]) was followed longitudinally for 5 years. MCI was defined as memory complaints with objective memory impairment, without dementia, impairment of general cognitive functioning, or disability in activities of daily living. Incidence rates were calculated using the person-years method. A descriptive analysis at the different follow-up times was performed to study the course of MCI. At baseline, there were 58 prevalent cases of MCI (2.8% of the sample). During a 5-year follow-up, 40 incident cases of MCI occurred in 1,265 subjects at risk. The global incidence rate of MCI was 9.9/1,000 person-years. MCI was a good predictor of AD with an annual conversion rate of 8.3% and a good specificity, but it was very unstable over time: Within 2 to 3 years, only 6% of the subjects continued to have MCI, whereas >40% reverted to normal. Conventionally defined MCI has reasonable predictive value and specificity for AD. However, MCI was very unstable across time in this study. Furthermore, the definition of MCI seems to be too restrictive and should probably be extended to other categories of individuals also at high risk of developing AD.