Personalized stroke risk prediction for atrial fibrillation patients using advanced data and models
Official title: Personalized Stroke Risk Stratification in Atrial Fibrillation: Integrating Probabilistic Graphical Models and High-dimensional EHR Data for Interpretable Prognosis
Funded at Denver Health and Hospital Authority · NIH-11314478 · Data updated 2026-11-12
Aims to create a personalized, easy-to-use tool that predicts stroke risk for people with atrial fibrillation using big health data and transparent machine-learning methods.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Denver Health and Hospital Authority NIH-funded |
| Lab location | 1 site (Denver, United States) |
| Project start | April 7, 2025 |
| Project end | March 31, 2030 |
| Funding year | 2026 |
| Award (this year) | $536,484 |
| NIH project number | 5R01HL177105-02 |
| Project ID | NIH-11314478 on NIH RePORTER |
Who could benefit from this research
✓Could help
Patients with atrial fibrillation who are considering stroke prevention therapies and are treated across multiple health systems.
✕Less likely to help
Patients whose AF is not managed with risk-based prevention strategies or who are not connected to electronic health record systems may see limited direct benefit.
What this research studies
This project seeks to combine millions of health records with new risk factors to tailor stroke prevention for people with atrial fibrillation. It will use a novel comorbidity discovery approach and machine-learning to uncover and explain how different factors interact to affect stroke risk. The team plans to develop, deploy, and test a portable risk-stratification tool across diverse health systems so clinicians can make better prevention choices for their patients. The work is designed to be interpretable and transferable across settings to improve real-world care.
Why it matters
Potential benefit: If successful, patients with atrial fibrillation could receive more personalized prevention strategies that reduce stroke risk.
How similar studies have gone: Previous efforts show promise for risk stratification with large datasets, but this project aims to expand and operationalize a portable, highly interpretable tool.
Where this research is happening
-
Denver Health and Hospital Authority
Denver, United States Active
Researchers
- Principal investigator: Steinberg, Benjamin Adam — Denver Health and Hospital Authority
- Study coordinator: Steinberg, Benjamin Adam
Related research
Other NIH-funded projects on the same topics.
-
Improving stroke risk prediction for patients with atrial fibrillation.
This study is working on a new tool to help predict stroke risk for people with atrial fibrillation by looking at both health and social factors, so that doctors can better tailor prevention strategies just for you.
-
Atrial fibrillation, clots, and stroke: the heart’s JNK2 as a target
This NIH grant explores how a heart protein called JNK2 may drive atrial fibrillation, blood clots, and stroke, and whether it could serve as a biomarker and new treatment approach.
-
DECIDE-AF: a shared decision tool in your health portal to help prevent strokes in atrial fibrillation
A patient-friendly tool in your electronic health record helps you and your doctor choose the right way to prevent strokes if you have atrial fibrillation.
-
Advancing Shared Decision Making for Stroke Prevention in Atrial Fibrillation
Aims to combine data from three big trials to understand how decision aids help people with atrial fibrillation choose anticoagulation to prevent stroke, in a patient-centered way.
-
Precursors of Stroke Incidence and Prognosis
This grant explores how life-long vascular risk factors and stroke-related brain changes influence the risk of cognitive problems, including Alzheimer’s-type dementia, in diverse adults.
-
New AI approach to detect and predict atrial fibrillation after stroke
A patient-friendly AI-based method is being developed to spot atrial fibrillation early in people who have had a stroke, using wearable heart-rate signals.
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page.