Geometry of navigation identifies genetic-risk and clinical Alzheimer's disease
Lim, U.; Leal-Cervantes, R.; Coughlan, G.; Lambiotte, R.; Spiers, H.; Hornberger, M.; Harrington, H.
Show abstract
Recent research evidence demonstrates that the inability to orient oneself and navigate space is an early indicator of Alzheimers Disease. The video game Sea Hero Quest (SHQ) was designed to assess the players navigation ability, and several research works analysed the SHQ data using simple metrics such as length and time of navigation paths. Expanding these analyses, we propose new performance metrics that capture the geometry of paths, and analyse datasets of more than 60,000 navigators. The metrics identify players who failed the navigation task, the dementia patients, and carriers of the at-risk allele of the Apolipoprotein-E [APOE]. Furthermore the metrics detect weak navigation ability when only a fraction of navigation paths are used, with superior performance to baseline methods. Our findings demonstrate that the proposed performance metrics pave the way to a comprehensive pre-clinical screening toolbox for Alzheimers Disease. TEASERWe propose geometric methods to capture decline in navigation ability from dementia.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.