Early detection of Alzheimer's disease (AD) increases the treatment benefits. However, it is still a challenging question which biomarkers are useful for early diagnosis. Then, we aimed to classify cognitively normal elderly regarding the possibility to develop AD based on resting-state cerebral vasoreactivity (CVR) values and neuropsychological (NP) scores. We used supervised machine learning algorithms. Our results suggest that Random Forest and K-Nearest Neighbors classifiers trained with CVR values of the vermis.7 (part of the cerebellum), and left parahippocampal gyrus, and Mini-Mental State Examination (MMSE), and Trail Making Test A scores can be useful on the early detection of AD.
This abstract and the presentation materials are available to members only; a login is required.