Using advanced imaging and AI to predict stroke recovery outcomes
Official title: Fused Imaging and Large Language Foundational Model for 90-day Stroke Outcome Prediction
Funded at Stanford University · NIH-11033519 · Data updated 2026-11-12
This study is looking to help doctors better predict how well patients will recover after a stroke by using a mix of different health information, so they can choose the best treatments for each person.
Quick facts
| Grant type | Career grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Stanford University NIH-funded |
| Lab location | 1 site (Stanford, United States) |
| Project start | February 1, 2025 |
| Project end | January 31, 2027 |
| Funding year | 2025 |
| Award (this year) | $124,485 |
| NIH project number | 1K99NS140547-01 |
| Project ID | NIH-11033519 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates for this research are individuals who have experienced an acute ischemic stroke and are being considered for endovascular therapy.
✕Less likely to help
Patients who have not experienced a stroke or those with other unrelated medical conditions may not benefit from this research.
What this research studies
This research focuses on improving the prediction of long-term outcomes for patients who have suffered an acute ischemic stroke. By integrating various data sources, including neuroimaging, clinical notes, and structured clinical data, the study aims to develop a novel model that enhances patient selection for endovascular therapy. The approach utilizes advanced deep learning techniques and large language models to analyze comprehensive patient information, which could lead to better treatment decisions and improved recovery prospects. Patients will be evaluated based on a more holistic view of their medical history and lifestyle factors, rather than solely on imaging results.
Why it matters
Potential benefit: If successful, this research could lead to more accurate predictions of recovery outcomes for stroke patients, ultimately improving treatment strategies and patient care.
How similar studies have gone: Other research has shown promise in using AI and comprehensive data integration for improving patient outcomes in various medical fields, suggesting that this approach could be effective in stroke care as well.
Where this research is happening
-
Stanford University
Stanford, United States Active
Researchers
- Principal investigator: Liu, Yongkai — Stanford University
- Study coordinator: Liu, Yongkai
Related research
Other NIH-funded projects on the same topics.
-
Stroke prevention with hydroxyurea for children with sickle cell anemia in Nigeria
A multinational, patient-facing study tests whether hydroxyurea can safely prevent first strokes in Nigerian children with sickle cell anemia.
-
Music-powered tools to boost blood pressure and stroke prevention for Nigerian youth and their older caregivers
This project uses popular music to help Nigerian youths and their older family members start and stick to blood pressure and stroke prevention habits.
-
Determinants of Post-Stroke Cognitive Outcomes and Vascular Effects on Recovery
A large, multi-site effort aims to understand why some stroke survivors develop long-term cognitive problems and dementia, and how vascular health and pre-existing brain changes influence recovery.
-
LRP1 controls NSC movement and stroke recovery
This NIH grant studies how a brain receptor called LRP1 helps neural stem cells move to stroke injuries and support recovery in adults.
-
BBB Dysfunction after Stroke and Risk for Dementia
A study at Stanford will look at whether inflammation after a stroke leads to leaky blood vessels and later dementia, by following stroke survivors and comparing them with people without stroke.
-
Improving blood flow after stroke by breaking down NETs
Aims to see if breaking down neutrophil extracellular traps (NETs) after an ischemic stroke can improve blood flow and reduce brain injury in patients.
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.