Project Summary/Abstract Dementia represents one of the most important public health concerns in the coming decades. Among the most important research goals will be to identify the earliest, most reliable and easily obtainable biomarkers of degeneration, because early identification of individuals most likely to decline now represents the most promising window for therapeutic interventions. The main objective of this project is to develop an Alzheimer’s disease (AD) screening solution based completely on a smartphone application that converts the phone’s facial recognition IR camera into a mobile pupillometer. Our scientific premise, demonstrated by our recent clinical findings, is that pupillary responses provide a biomarker of cognitive effort required to perform tasks before overt performance declines are manifest. Pupil size during cognitive tasks (e.g., digit span recall) increases in response to increased demands, is inversely related to cognitive ability (individuals with lower ability show greater dilation/compensatory effort), and pupil size decreases and performance declines when task demands exceed abilities and compensatory capacity. Someone requiring more effort to achieve the same score as another person is likely to be closer to maximum compensatory capacity and, therefore, at higher risk for decline. We have found that individuals with mild cognitive impairment (MCI), who are at greater risk for AD, show greater dilation (effort) on the digit span task, and that greater dilation is associated with greater polygenic risk for AD and neuroimaging indicators of locus coeruleus (LC) dysfunction. This is important because pupillary responses reflect LC functioning, and postmortem studies implicate the LC as an early site of AD pathogenesis and degenerative changes with disease progression. Thus, pupillary responses may serve as a specific biomarker of functional alterations in a brain system affected by the earliest manifestations of AD. Currently, pupillary responses can be measured in as little as 5 minutes using minimally invasive, but expensive and complicated office-based devices. To increase the scalability of pupillometry screening in AD, we propose to develop a smartphone assessment that older adults can administer themselves at home that tracks small changes in pupil dilation during cognitive tasks. We will further develop and evaluate different machine learning algorithms that use the pupillary response biomarker measured by the phone to perform automated risk assessment of severity of mild cognitive impairment at the early stages of AD. Because the project would be carried out in the context of a larger NIA-funded RF1 affiliated with the UC San Diego Alzheimer’s Disease Research Center (ADRC), it will be possible to validate mobile pupillometry assessments against gold-standard in-lab pupillometry in older adults with MCI, early AD, and healthy controls. Our translational goal is to provide access to low-cost at-home screenin...