Document text
Principal Investigator: Zita Oravecz
Organization: PENNSYLVANIA STATE UNIVERSITY, THE
Fiscal Year: 2024
Award: $778,936
Funding agency: National Institute on Aging
Project Summary
Sensitive and accurate measurement of change in cognitive performance is necessary for the detection of
subtle cognitive decline in the preclinical phase of Alzheimer’s disease and related dementias (ADRD). It is
also required to evaluate outcomes of early interventions aimed at mitigating advanced cognitive decline.
However, this is a difficult task as these changes are subtle; not only in terms of magnitude, but also in terms
of the latent processes through which they manifest. Although researchers and clinicians are often interested in
detecting long-timescale patterns of change (i.e., normative aging vs. disease progression), learning processes
on short and long-timescales confound such effects.
To address these challenges, we will develop a modern statistical toolset designed for use with data from high-
frequency repeated assessments. For this, we will combine longitudinal measurement “burst” designs with a
novel Bayesian computational toolkit to simultaneously capture multi-timescale learning processes together
with cognitive change and decline. These tools will provide interpretable features (e.g., change in peak
performance, probability of decline, caution in decision making, etc.) that can then be deployed as digital
markers of subtle cognitive decline. The Bayesian approach will also provide for a principled framework to
communicate individual-specific dementia risks towards clinicians.
Our specific aims are to:
1. Separate multi-timescale learning processes from cognitive changes related to aging and
neurodegeneration and extract key digital cognitive markers to identify digital computational phenotypes of
ADRD risk.
2. Disentangle cognitive processes in task performance by developing novel statistical tools that quantify
latent processes to enrich our set of novel digital cognitive markers.
3. Identify which combination of digital cognitive markers and test interval between measurement bursts
carries the most power for predicting ADRD risk.
For Aim 1 we will analyze two measurement burst design data sets. To further refine the framework in Aims 2
and 3, we develop novel statistical tools and collect data with fine-tuned, novel feature binding tasks known to
be sensitive for preclinical AD. We will evaluate the predictive power of the identified novel digital cognitive
markers by linking them to AD biomarkers levels and ADRD risk scores.
Terms: <21+ years old><AD detection><AD related dementia><ADRD><Address><Adult><Adult Human><Age><Aging><Alzheimer disease detection><Alzheimer's and related dementias><Alzheimer's detection><Alzheimer's disease and related dementia><Alzheimer's disease and related disorders><Alzheimer's disease or a related dementia><Alzheimer's disease or a related disorder><Alzheimer's disease or related dementia><Alzheimer's disease related dementia><Bayesian Analysis><Bayesian Method><Bayesian Methodology><Bayesian Modeling><Bayesian Statistical Method><Bayesian adaptive designs><Bayesian adaptive models><Bayesian approaches><Bayesian belief network><Bayesian belief updating model><Bayesian classification method><Bayesian classification procedure><Bayesian computation><Bayesian framework><Bayesian hierarchical model><Bayesian inference><Bayesian network analysis><Bayesian network model><Bayesian nonparametric models><Bayesian posterior distribution><Bayesian spatial analysis><Bayesian spatial data model><Bayesian spatial image models><Bayesian spatial models><Bayesian statistical analysis><Bayesian statistical inference><Bayesian statistical models><Bayesian statistics><Bayesian tracking algorithms><Binding><Biological Markers><Blood><Blood Reticuloendothelial System><Cell Communication and Signaling><Cell Phone><Cell Signaling><Cellular Phone><Cellular Telephone><Characteristics><Clinical><Clinical Trials><Code><Coding System><Cognitive><Cognitive Disturbance><Cognitive Impairment><Cognitive aging><Cognitive decline><Cognitive function abnormal><Communication><Computational toolkit><Computer Models><Computerized Models><Data><Data Collection><Data Set><Decision Making><Degenerative Neurologic Disorders><Detection><Diffusion><Digital biomarker><Disease Progression><Disturbance in cognition><Early Diagnosis><Early Intervention><Face><Frequencies><Genetic Risk><Goals><Health protection><Hereditary><Immediate Memory><Impaired cognition><Individual><Individual Differences><Inherited><Intervention><Intervention Strategies><Intracellular Communication and Signaling><Investigators><Knowledge><Learning><Life><Link><Long-Term Effects><Longitudinal Studies><Longterm Effects><Maps><Measurement><Methodology><Mission><Mobile Phones><Modeling><Modernization><Molecular Interaction><Monitor><NIH><National Institutes of Health><Nerve Degeneration><Nervous System Degenerative Diseases><Neural Degenerative Diseases><Neural degenerative Disorders><Neurodegenerative Diseases><Neurodegenerative Disorders><Neurologic Degenerative Conditions><Neuron Degeneration><Outcome><Pattern><Performance><Persons><Phase><Phenotype><Probability><Procedures><Process><Prospective Studies><Public Health><Publishing><Research><Research Design><Research Personnel><Researchers><Risk><Sampling><Short-Term Memory><Shortterm Memory><Signal Transduction><Signal Transduction Systems><Signaling><Study Type><Task Performances><Testing><Time><United States National Institutes of Health><Visual><Visuospatial><Work><adulthood><ages><aging process><bio-markers><biologic marker><biological signal transduction><biomarker><causal allele><causal gene><causal mutation><causal variant><causative mutation><causative variant><cognitive assessment><cognitive change><cognitive dysfunction><cognitive loss><cognitive performance><cognitive process><cognitive task><cognitive testing><computational modeling><computational models><computational toolbox><computational tools><computational toolset><computer based models><computerized data processing><computerized modeling><computerized tools><data processing><degenerative diseases of motor and sensory neurons><degenerative neurological diseases><dementia risk><design><designing><diffused><diffuses><diffusing><diffusions><digital><digital marker><disease prognosis><disease prognostication><early detection><faces><facial><forgetting><iPhone><information processing><innovate><innovation><innovative><interest><interventional strategy><long-term study><longitudinal outcome studies><longterm study><mid life><mid-life><middle age><middle aged><midlife><natural aging><neural degeneration><neurodegeneration><neurodegenerative><neurodegenerative illness><neurological degeneration><neuronal degeneration><normal aging><normative aging><novel><pre-clinical><preclinical><predictive biomarkers><predictive marker><predictive molecular biomarker><processing speed><risk factor for dementia><risk for dementia><smart phone><smartphone><study design><time interval><time use><tool><visual spatial><working memory>