2692 The future is in our hands: screening for preclinical alzheimer’s disease at home using automated analysis of hand movements

ObjectivesThere are no low-cost population-level tests to help identify preclinical Alzheimer’s disease (AD); this hinders drug development and targeted dementia prevention. New evidence suggests that hand movements change in preclinical AD. We evaluated the predictive accuracy of TAS Test (new online hand movement analysis website) for detecting preclinical AD biomarkers (plasma ptau181 and subtle episodic memory impairment) in cognitively asymptomatic adults.MethodsParticipants completed TAS Test online at home: 10–30 second finger-tapping tests recorded with a keyboard and/or webcam. Movement features (frequency, rhythm, pauses etc) were extracted. Participants also completed online episodic memory tests (CANTAB) and some provided blood samples for ptau181 analysis. Linear regression models comprising hand movement features to predict CANTAB scores and ptau181 levels, adjusted for confounding, was compared to null models (with only confounders: age, gender, education level, anxiety and depression) using R2adj and AIC. ΔAIC > 2 denotes statistical difference.Results1,228 adults (mean (SD) age, 65.8 (7.4) years; 73.0% female) completed TAS Test and CANTAB; 459 underwent ptau181 analysis. The 3 step-key and alternate-key tapping tests improved prediction of asymptomatic episodic memory impairment; (ΔAICs=11.2 and 3.3; R2adjs=8.1% and 7.5% respectively) and ptau181 (3 step ΔAIC=7.0; R2adj=17.8%; alternate key ΔAIC=3.4; R2adj=17.4%). The highest performing webcam tests were dominant hand tapping (CANTAB ΔAIC= 2.9; R2adj=8.2%; ptau181 ΔAIC=2.4; R2adj=12.9%) and both hands dual-task tapping (CANTAB ΔAIC=3.0; R2adj=6.8%; ptau181 ΔAIC=8.7; R2adj=11.9%).ConclusionsTAS Test provides a home-based test for identifying preclinical AD risk and holds potential as a pre-screening tool for identifying cohorts for further investigation.