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.
Similar papers in this journal
- Identifying factors that contribute to collision avoidance behaviours while walking in a natural environment 93%
- Selecting the most important self-assessed features for predicting conversion to Mild Cognitive Impairment with Random Forest and Permutation-based methods 93%
- Hypergraph Clustering for Analyzing Chronic Disease Patterns in Mild Cognitive Impairment Reversion and Progression 93%
Similar papers in this journal
Similar papers in this journal
- System level analyses of motor-related neural activities in larval Drosophila 88%
- Discriminating between sleep and exercise-induced fatigue using computer vision and behavioral genetics 86%
- Analysis of 470,000 exome-sequenced UK Biobank participants identifies genes containing rare variants which confer dementia risk 83%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.