Official websites use .gov

A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS

A lock ( 🔒 ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Need Help

Computational Models to Aid Personalized Stroke Decision-Making in AD/ADRD

Award Number: K23AG097999
ORGANIZATION: NATIONAL INSTITUTE ON AGING
OPDIV: NIH
AWARD CLASS: DISCRETIONARY
AWARD ACTIVITY TYPE: TRAINING/TRAINEESHIP
PERIOD OF PERFORMANCE START DATE: 09/10/2026
PERIOD OF PERFORMANCE END DATE: 05/31/2031

Group Awards By:

View Award Description

Computational Models to Aid Personalized Stroke Decision-Making in AD/ADRD - PROJECT SUMMARY Alzheimer’s disease (AD) and acute ischemic stroke (AIS) are common and disabling diseases in older adults and frequently co-occur. Yet patients with AD have been systematically excluded from clinical trials of stroke reperfusion therapies (IV thrombolysis (IVT) and endovascular therapy (EVT)), leaving clinicians without data to guide treatment. Observational studies suggest these therapies may be safe and potentially beneficial, but results are inconsistent and rarely distinguish AD from other dementias. This represents a critical gap in stroke and aging research: existing data sources and analytic frameworks are insufficient to evaluate outcomes and treatment effects of stroke therapies in patients with AD, limiting evidence-based and goal-concordant care. The long-term objective of this research is to improve precision and safety in stroke treatment for older adults with AD. The central hypothesis is that complementary computational approaches—machine learning (ML)- based incident phenotyping to accurately identify AD and its onset, and causal modeling to reveal determinants of outcomes and treatment effects—can together overcome current data limitations and generate the evidence needed to guide stroke care in this understudied population. Aim 1 will develop and validate ML-based incident phenotyping methods to identify AD and determine when it was first diagnosed in a longitudinal EMR dataset of well-defined AIS cases. This will yield scalable, efficient tools for reproducible AD identification that can be applied across real-world EMR systems and used to accelerate large-scale, multi-institutional research in stroke and dementia. Aim 2 will use causal modeling in a well-characterized stroke dataset with detailed clinical, imaging, and outcome data to identify causal factors influencing outcomes and estimate the effects of IVT and EVT in patients with AD. This project is innovative in uniting complementary computational methods to address treatment-effect questions in a population historically excluded from clinical trials. Its significance is in producing validated analytic tools, high-quality datasets of AD patients with AIS, and foundational evidence to inform clinical decision-making. Expected outcomes include a scalable incident phenotyping framework, reproducible causal models, and durable infrastructure for future R01-level studies extending these methods to other dementias and therapeutic areas. This K23 award will also provide critical career development through advanced training in machine learning, causal modeling, and informatics, supporting Dr. McCullough-Hicks’ transition to an independent investigator advancing precision medicine and goal-concordant stroke care for older adults with dementia. This work directly supports the National Institute on Aging’s mission to improve understanding of AD and to develop interventions that enhance health and quality of life in aging populations.


Issue Date FY	Funding FY	Legal Entity Name	Legal Entity Address	Legal Entity City	Legal Entity State	Legal Entity Zip Code	Legal Entity COUNTY	Legal Entity COUNTRY	Assistance Listing	Award Code	Budget Year	Action Date	Action Type	Action Amount

Issue Date FY: 2026 ( Subtotal = $174,288 )
2026	2026	REGENTS OF THE UNIVERSITY OF MINNESOTA	2221 UNIVERSITY AVE SE STE 100	MINNEAPOLIS	MN	55414	HENNEPIN	USA	Aging Research	000	1	9/9/2026	NEW	$174,288
														Subtotal = $174,288

Grand Total All Awards = $174,288

Top

All Categories

About

Search

Reports

Data Submission

Award Information

Computational Models to Aid Personalized Stroke Decision-Making in AD/ADRD

Award Number: K23AG097999

ORGANIZATION: NATIONAL INSTITUTE ON AGING

OPDIV: NIH

AWARD CLASS: DISCRETIONARY

AWARD ACTIVITY TYPE: TRAINING/TRAINEESHIP

PERIOD OF PERFORMANCE START DATE: 09/10/2026

PERIOD OF PERFORMANCE END DATE: 05/31/2031

Federal Websites

Department of Health & Human Services

HHS Operating Divisions

HHS Staff Divisions

Download A Document Viewer