Federated learning to improve genetic risk prediction for Alzheimer's disease and related dementias
Official title: Federated Transfer Learning Framework to Improve Genetic Risk Prediction for Alzheimer's Disease and Related Dementias
Funded at Cedars-Sinai Medical Center · NIH-11450878 · Data updated 2026-11-12
A new project uses privacy-preserving AI to tailor genetic risk scores for Alzheimer's and related dementias to diverse groups, helping with early planning and care decisions.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Cedars-Sinai Medical Center NIH-funded |
| Lab location | 1 site (Los Angeles, United States) |
| Project start | September 1, 2026 |
| Project end | May 31, 2031 |
| Funding year | 2026 |
| Award (this year) | $809,487 |
| NIH project number | 1R01AG094962-01A1 |
| Project ID | NIH-11450878 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates are older adults whose genetic data are part of biobank or EHR-linked resources and who are at risk for ADRD.
✕Less likely to help
Individuals without access to biobank or EHR-linked genetic data may see limited direct benefit.
What this research studies
This project aims to improve how we predict who might develop Alzheimer's disease and related dementias by adapting existing genetic risk models to work across different patient groups while protecting privacy. Researchers will use federated transfer learning to fine-tune polygenic risk scores on biobank-linked electronic health records without sharing raw data. The approach combines artificial intelligence, statistical genetics, and secure data practices to create more accurate, generalizable risk predictions that clinicians can use in aging-related care planning. The work focuses on aging populations and seeks to translate genetic risk into practical information for patients and families.
Why it matters
Potential benefit: If successful, it could lead to earlier and more accurate risk prediction, enabling proactive health decisions and better planning for patients and caregivers.
How similar studies have gone: Previous ADRD risk models have limited generalizability; this project aims to improve accuracy across cohorts through federated learning, which is a relatively novel approach.
Where this research is happening
-
Cedars-Sinai Medical Center
Los Angeles, United States Active
Researchers
- Principal investigator: Li, Ruowang — Cedars-Sinai Medical Center
- Study coordinator: Li, Ruowang
Related research
Other NIH-funded projects on the same topics.
-
Understanding how brain activity changes may drive Alzheimer’s disease progression in a mouse model
Researchers are testing how changes in brain signals and protein cleanup processes affect the development of Alzheimer’s disease in mice.
-
Thiamine-boosting therapy for Alzheimer’s: understanding how benfotiamine may reduce harmful AGE in DP patients
A medication-based approach using high-dose vitamin B1 (benfotiamine) is studied to help people with Alzheimer's by reducing harmful sugar-related molecules.
-
Non-invasive tears biomarker for early Alzheimer's in LMICs
A low-cost, tear-based biomarker approach aims to detect early Alzheimer’s disease in older adults in Peru and similar settings.
-
Turning APOE4 into protective APOE2 or APOE3Christchurch to help with Alzheimer’s
A patient-facing explanation of a treatment idea that aims to change a genetic risk factor for Alzheimer's disease in the brain.
-
Telomerase in Alzheimer’s Disease: how aging biology could influence memory and brain health
Researchers are exploring a new brain-aging mechanism linked to telomerase, with potential to slow or modify Alzheimer’s disease in people and improve cognitive function.
-
Biomarkers of Alzheimer’s Disease: Sensory, Motor, and Cognitive Clues
Researchers are testing simple sensory and movement tasks to find early signs of Alzheimer’s disease so they can diagnose and treat people sooner.
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.