Predictive analytics for cognitive decline and Alzheimer’s disease (NIA K23 AG063993):
We are developing ML4AD, a machine-learning framework that integrates demographics, genetics, neuropsychology, MRI, and amyloid PET to predict individual trajectories of cognitive decline and prodromal Alzheimer’s disease. By focusing enrollment on those most likely to progress, these models can boost trial power now and, down the road, identify candidates for preventive interventions once therapies exist. Under Dr. Ali Ezzati’s K23 award—with mentorship in neurobiology (Lipton), computational neuroscience (Davatzikos), and biostatistics (Hall)—we’ll leverage rich international cohorts to build cost-effective, high-performance tools that will both inform secondary prevention trials and establish a foundation for future predictive research in AD and related disorders.
List of Publications
Genetic and Clinical Correlates of AI-Based Brain Aging Patterns in Cognitively Unimpaired Individuals. – https://www.ncbi.nlm.nih.gov/pmc/articles/10867779
MRI-guided clustering of patients with mild dementia due to Alzheimer’s disease using self-organizing maps. – https://www.ncbi.nlm.nih.gov/pmc/articles/11781377
Plasma Biomarkers as Predictors of Progression to Dementia in Individuals with Mild Cognitive Impairment. – https://www.ncbi.nlm.nih.gov/pmc/articles/11044769
CSF inflammatory cytokines as prognostic indicators for cognitive decline across Alzheimer’s disease spectrum. – https://www.ncbi.nlm.nih.gov/pmc/articles/11601771
Discovering Subtypes with Imaging Signatures in the Motoric Cognitive Risk Syndrome Consortium using Weakly-Supervised Clustering. – https://www.ncbi.nlm.nih.gov/pmc/articles/11482983
Association of Alcohol Consumption with Cognition in Older Population: The A4 Study. – https://www.ncbi.nlm.nih.gov/pmc/articles/10392870
Tracking cognition with the T-MoCA in a racially/ethnically diverse older adult cohort. – https://www.ncbi.nlm.nih.gov/pmc/articles/10026378
Association of Stages of Objective Memory Impairment With Incident Symptomatic Cognitive Impairment in Cognitively Normal Individuals. – https://www.ncbi.nlm.nih.gov/pmc/articles/10259282
Associations of Stages of Objective Memory Impairment with Cerebrospinal Fluid and Neuroimaging Biomarkers of Alzheimer’s Disease. – https://www.ncbi.nlm.nih.gov/pmc/articles/9841119
Impact of sex and APOE ε4 on the association of cognition and hippocampal volume in clinically normal, amyloid positive adults. – https://www.ncbi.nlm.nih.gov/pmc/articles/8828988
Predicting Amyloid Positivity in Cognitively Unimpaired Older Adults: A Machine Learning Approach Using A4 Data. – https://www.ncbi.nlm.nih.gov/pmc/articles/9231843
Association of Depressive Symptoms and Cognition in Older Adults Without Dementia Across Different Biomarker Profiles. – https://www.ncbi.nlm.nih.gov/pmc/articles/9723980
Associations of Stages of Objective Memory Impairment With Amyloid PET and Structural MRI: The A4 Study. – https://www.ncbi.nlm.nih.gov/pmc/articles/8967421
Comparing Performance of Different Predictive Models in Estimating Disease Progression in Alzheimer Disease. – https://www.ncbi.nlm.nih.gov/pmc/articles/8847534
Application of predictive models in boosting power of Alzheimer’s disease clinical trials: A post hoc analysis of phase 3 solanezumab trials. – https://www.ncbi.nlm.nih.gov/pmc/articles/8919041
Neuroimaging correlates of Stages of Objective Memory Impairment (SOMI) system. – https://www.ncbi.nlm.nih.gov/pmc/articles/8719429
White matter hyperintensities and cognition across different Alzheimer’s biomarker profiles. – https://www.ncbi.nlm.nih.gov/pmc/articles/8456365
Leveraging machine learning predictive biomarkers to augment the statistical power of clinical trials with baseline magnetic resonance imaging. – https://www.ncbi.nlm.nih.gov/pmc/articles/8600962
Predictive value of ATN biomarker profiles in estimating disease progression in Alzheimer’s disease dementia. – https://www.ncbi.nlm.nih.gov/pmc/articles/8842842
Detecting biological heterogeneity patterns in ADNI amnestic mild cognitive impairment based on volumetric MRI. – https://www.ncbi.nlm.nih.gov/pmc/articles/7203761
Machine Learning Predictive Models Can Improve Efficacy of Clinical Trials for Alzheimer’s Disease. – https://www.ncbi.nlm.nih.gov/pmc/articles/7201366
Predicting Amyloid-β Levels in Amnestic Mild Cognitive Impairment Using Machine Learning Techniques. – https://www.ncbi.nlm.nih.gov/pmc/articles/7376527
We’re creating and validating the Remote Cognitive Aging and Alzheimer’s Disease REsearch (R-CARE) Toolbox—a tablet-based, remotely administered battery built from the UDSNB-3.0 and common preclinical AD tests—to overcome access barriers and pandemic-related safety concerns. In a randomized, counterbalanced study of 600 dementia-free adults (≥65 years; ~1/3 non-Hispanic Black, Hispanic, and White), participants will complete both in-person and remote assessments at baseline, 18 months, and 36 months. We’ll (1) evaluate the psychometric properties and validity of remote tests against gold-standard in-person measures, (2) compare longitudinal change across assessment modes overall and by sex and race/ethnicity, and (3) explore novel digital and blood-based biomarkers for enhanced detection of early cognitive decline. Ultimately, the project will deliver an open-source, reliable toolbox to enable inclusive, remote evaluation of cognition and function in aging and ADRD research and clinical practice.
List of Publications
Development of Simple Risk Scores for Prediction of Brain β-Amyloid and Tau Status in Older Adults With Mild Cognitive Impairment: A Machine Learning Approach. – https://pubmed.ncbi.nlm.nih.gov/40326513/
Genetic and Clinical Correlates of AI-Based Brain Aging Patterns in Cognitively Unimpaired Individuals. – https://www.ncbi.nlm.nih.gov/pmc/articles/10867779
Plasma Biomarkers as Predictors of Progression to Dementia in Individuals with Mild Cognitive Impairment. – https://www.ncbi.nlm.nih.gov/pmc/articles/11044769
CSF inflammatory cytokines as prognostic indicators for cognitive decline across Alzheimer’s disease spectrum. – https://www.ncbi.nlm.nih.gov/pmc/articles/11601771
Discovering Subtypes with Imaging Signatures in the Motoric Cognitive Risk Syndrome Consortium using Weakly-Supervised Clustering. – https://www.ncbi.nlm.nih.gov/pmc/articles/11482983
Linking self-perceived cognitive functioning questionnaires using item response theory: The subjective cognitive decline initiative. – https://www.ncbi.nlm.nih.gov/pmc/articles/10564559