Pilot AS3-03S2 – Lin

Publication: Passive Measures of Physical Activity and Cadence as Early Indicators of Cognitive Impairment: Observational Study

Authors: Huitong Ding, Stefaniya Brown, David R Paquette, Taylor A Orwig, Nicole Spartano, Honghuang Lin Abstract Background: Emerging research shows regular physical activity reduces cognitive decline risk, but most studies rely on self-reported measures, which are limited by recall bias, subjectivity, and a lack of continuous monitoring capability. Objective: This study aimed to explore passive physical activity measures as early indicators of cognitive impairment by examining their association with cognitive impairment incidence and neuropsychological (NP) test performance. Methods: We included participants from the Framingham Heart Study (FHS), a community-based cohort with longitudinal cognitive impairment surveillance. Participants wore an Actical accelerometer for at least 3 days, excluding bathing. Thirty physical activity measures were grouped into intensity-specific durations, step and cadence summaries, and peak cadence. Cox proportional hazard models were applied to assess their associations with incident…

Continue ReadingPublication: Passive Measures of Physical Activity and Cadence as Early Indicators of Cognitive Impairment: Observational Study

Grant Funding: U01: Assessing Alzheimer disease risk and heterogeneity using multimodal machine learning approaches

PROJECT SUMMARY/ABSTRACT Alzheimer's disease (AD) is the most common form of dementia characterized by progressive loss of cognitive function. Unfortunately, currently there is no effective treatment for AD and clinical interventions of AD have largely failed despite enormous efforts. For the current application, we seek to develop multimodal machine learning models by leveraging the rich collection of AD-related omics data and phenotypical data recently generated from large-scale collaborative projects such as Alzheimer Disease Neuroimaging Initiative (ADNI), Accelerating Medicines Partnership-AD (AMP-AD) and the Alzheimer's Disease Sequencing Project (ADSP). Three aims will be pursued in the current application. Aim 1. We will build an expandable multimodal unsupervised machine learning framework to investigate AD heterogeneity. Given the multifactorial nature of AD, we will perform AD subtyping by harnessing the rich information across multiple spectrum of data. Aim 2.…

Continue ReadingGrant Funding: U01: Assessing Alzheimer disease risk and heterogeneity using multimodal machine learning approaches