Remote Cognitive Aging and Alzheimer’s Disease REsearch (R-CARE) Toolbox
In-person administration is the current “gold-standard” for assessment of cognition and function in studies of Alzheimer’s disease and other dementia (ADRD). Remote neuropsychological assessment has been advocated to overcome various access barriers and decrease costs of neuropsychological services. Moreover, due to unpredictable situations such as what happened during the COVID-19 pandemic, there is an urgent need for robust methods for assessing and monitoring cognitive and functional status through remote assessments. The overall goal of the current project is to validate, refine, and calibrate the Remote Cognitive Aging and Alzheimer’s Disease REsearch (R-CARE) Toolbox for the assessment and monitoring of cognition and function in a diverse sample of initially dementia-free older adults. This study will enable researchers and clinicians to accurately and reliably assess cognition and function of older adults who are at risk of ADRD when in-person assessments are not feasible or safe. Remote assessment will facilitate more frequent evaluations at lower cost, potentially improving sensitivity, reliability, and validity of cognitive assessment for observational studies, clinical trials and clinical practice.
Interactions between SARS-CoV2 infection and ancestral genomic variations in the risk of Alzheimer’s Disease
Our goal in this project t is to study interaction between exposure to an environmental event (COVID infection) and genomic variation on the occurrence of cognitive decline and Alzheimer’s Disease (AD) in large cohorts of older adults from underrepresented minorities in the USA and ancestral groups in Africa and South America. We will investigate the interactions between whole genome sequence genetic variations and COVID-19 infection and disease on the risk of cognitive decline and risk of AD. Participant’s data include neurological evaluation, cognitive tests, brain imaging and blood-based biomarker.
Predictive analytics for cognitive decline and Alzheimer’s disease
Alzheimer’s disease (AD), the most common cause of dementia in the elderly, is a major global healthcare burden. However, there is still no effective disease modifying therapy for AD and clinical trials with the aim of preventing or stabilizing cognitive impairment have largely failed. Decision making in both clinical practice and research is highly dependent on practical predictive tools, which can effectively predict cognitive or functional outcomes in individuals. Such models could be potentially used in clinical research to boost the power of trials by enrollment of participants who are most likely to show disease progression during the trial’s timeframe. In this project, we aim to provide a framework for practical prediction of cognitive decline with aging and prodromal AD, by applying a novel ML framework to multiple dimensions of data including demographics, genetic risk scores, neuropsychological measures, brain MRI, and amyloid imaging. This approach will lead to predictive tools that can be effectively used in research as well as clinical decision making for patients in prodromal stages of Alzheimer’s disease or individuals with normal cognition and high-risk of developing Alzheimer’s Disease.
Bioinformatics Platform for Modeling Alzheimer’s Progression
Alzheimer’s disease varies widely in how it affects individuals and progresses over time, posing challenges in predicting who is at higher risk, understanding disease progression, and recognizing its diverse forms among older adults. To address these challenges, we propose using artificial intelligence techniques and data from multiple long-term studies on aging and dementia. By integrating demographics, clinical information, cognitive scores, brain scans, and genetic data, we aim to develop machine learning models that predict how Alzheimer’s may unfold over periods ranging from six months to ten years. Our ultimate objective is to establish a platform called Bioinformatics Platform for Modeling Alzheimer’s Progression (MAP-AD Platform), where these models can be accessed online and immediately by researchers as well as clinicians. This platform will facilitate collaboration among researchers and enable doctors to provide personalized predictions about Alzheimer’s disease to their patients. Ultimately, this initiative aims to deepen our understanding of the disease pathology, improve diagnostics and prognostics, and lead to more personalized healthcare approaches for all individuals who are at risk of Alzheimer’s disease.