We can’t show the full text here under this license. Use the link below to read it at the source.
Eye tracking as a diagnostic tool in Alzheimer's disease, mild cognitive impairment, and related dementias: a systematic review
Using eye tracking to help diagnose Alzheimer's, mild memory problems, and related dementias
AI simplified
Abstract
Seventy-one studies were evaluated, revealing that antisaccade tasks consistently distinguish Alzheimer's disease and from healthy controls.
- Impaired accuracy, longer latencies, and reduced gain were observed in antisaccade tasks for individuals with Alzheimer's disease and mild cognitive impairment.
- Non-saccadic tasks indicated reduced exploratory behavior in Alzheimer's disease, while findings for mild cognitive impairment were mixed.
- A significant limitation was the absence of cohorts defined by current biological criteria, which may affect clinical applications.
- Machine-learning models and deep neural networks demonstrated accuracies ranging from 0.72 to 0.97 in a subset of studies.
AI simplified
Key numbers
71
Study Count
Total studies included in the systematic review.
0.72 to 0.97
Range
Reported accuracies of classical machine-learning models using eye tracking metrics.
$818 billion
Cost of Care
Estimated global economic toll of in 2015.