Multi-granular Computing Can Predict Prodromal Alzheimer's Disease Indications in Normal Subjects.

The processes of neurodegeneration related to Alzheimer’s disease (AD) begin several decades before the first symptoms. We have used multi-granular computing (MGC) to classify cognitive data from BIOCARD study that have been started over 20 years ago with 354 normal subjects. Patients were evaluated every year by a team of neuropsychologists and neurologists and classified as normal, with MCI (mild cognitive impairments), or with dementia. As the decision attribute, we have used CDRSUM (Clinical Dementia Rating Sum of Boxes) as a more quantitative measure than the above classification. Based on 150 stable subjects with different stages of AD, and on the group of 40 AD, we have found sets of different granules that classify cognitive attributes with CDRSUM as the disease stage. By applying these rules to normal ( CDRSUM = 0 ) 21 subjects we have predicted that one subject might get mild dementia ( CDRSUM > 4.5), one very mild dementia ( CDRSUM > 2.25), four might get very mild dementia or questionable impairment and one other might get questionable impairment ( CDRSUM > 0.75). AI methods can find, invisible for neuropsychologists, patterns in cognitive attributes of normal subjects that might indicate their pre-dementia stage, also in longitudinal testing.