Detecting the effect of Alzheimer's disease on everyday motion behavior

• Published in: Journal of Alzheimer's disease Vol. 38; no. 1; p. 121
• Main Authors: Kirste, Thomas, Hoffmeyer, André, Koldrack, Philipp, Bauer, Alexandra, Schubert, Susanne, Schröder, Stefan, Teipel, Stefan
• Format: Journal Article
• Language: English
• Published: Netherlands 01.01.2014
• Subjects: Accelerometry; Activities of Daily Living; Aged; Aged, 80 and over; Alzheimer Disease - complications; Behavioral Symptoms - diagnosis; Behavioral Symptoms - etiology; Discriminant Analysis; Female; Humans; Male; Mental Status Schedule; Middle Aged; Movement Disorders - diagnosis; Movement Disorders - etiology; Predictive Value of Tests; ROC Curve; Statistics as Topic; discriminant analysis; Cohen-Mansfield Agitation Inventory; chronobiology phenomena; circadian rhythm disorders; Actigraphy; Fourier analysis; psychomotor agitation; Alzheimer's disease; linear models; principal component analysis
• ISSN: 1875-8908
• DOI: 10.3233/JAD-130272

Early detection of behavioral changes in Alzheimer's disease (AD) would help the design and implementation of specific interventions. The target of our investigation was to establish a correlation between diagnosis and unconstrained motion behavior in subjects without major clinical behavior impairments. We studied everyday motion behavior in 23 dyads with one partner suffering from AD dementia and one cognitively healthy partner in the subjects' home, employing ankle-mounted three-axes accelerometric sensors. We determined frequency features obtained from the signal envelopes computed by an envelope detector for the carrier band 0.5 Hz to 5 Hz. Based on these features, we employed quadratic discriminant analysis for building models discriminating between AD patients and healthy controls. After leave-one-out cross-validation, the classification accuracy of motion features reached 91% and was superior to the classification accuracy based on the Cohen-Mansfield Agitation Inventory (CMAI). Motion features were significantly correlated with MMSE and CMAI scores. Our findings suggest that changes of everyday behavior are detectable in accelerometric behavior protocols even in the absence of major clinical behavioral impairments in AD.