Brief webcam test of hand movements predicts episodic memory, executive function, and working memory in a community sample of cognitively asymptomatic older adults.

Abstract

Low-cost simple tests for preclinical Alzheimer's disease are a research priority. We evaluated whether remote unsupervisedwebcam recordings of finger-tapping were associated with cognitive performance in older adults. A total of 404 cognitively-asymptomatic participants (64.6 [6.77] years; 70.8% female) completed 10-second finger-tapping tests (Tasmanian [TAS] Test) and cognitive tests (Cambridge Neuropsychological Test Automated Battery [CANTAB]) online at home. Regression models including hand movement features were compared with null models (comprising age, sex, and education level); change in Akaike Information Criterion greater than 2 (ΔAIC > 2) denoted statistical difference. Hand movement features improved prediction of episodic memory, executive function, and working memory scores (ΔAIC > 2). Dominant hand features outperformed nondominant hand features for episodic memory (ΔAIC = 2.5), executive function (ΔAIC = 4.8), and working memory (ΔAIC = 2.2). This brief webcam test improved prediction of cognitive performance compared to age, sex, and education. Finger-tapping holds potential as a remote language-agnostic screening tool to stratify community cohorts at risk for cognitive decline.