AI-powered collaborative data sharing for diabetes research (dkNET Coordinating Unit)
Official title: dkNET Coordinating Unit: Harnessing the Power of AI and Data Science forCollaborative Discovery and Sharing in the DK Community
Funded at University of California, San Diego · NIH-11586007 · Data updated 2026-11-12
A national effort to build a privacy-preserving, federated AI platform that lets researchers train diabetes-focused AI models across many institutions without sharing patient data.
Quick facts
| Grant type | NIH-funded research |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of California, San Diego NIH-funded |
| Lab location | 1 site (La Jolla, United States) |
| Project start | August 15, 2026 |
| Project end | February 28, 2029 |
| Funding year | 2026 |
| Award (this year) | $300,000 |
| NIH project number | 3U24DK097771-13S2 |
| Project ID | NIH-11586007 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal participants are individuals with diabetes or those contributing relevant clinical and genomic data to federated analyses, under appropriate consent.
✕Less likely to help
Patients whose data topics are outside diabetes or who opt out of data sharing may not directly benefit.
What this research studies
This project creates a scalable, privacy-first system that allows multiple sites to train AI models on sensitive clinical and genomic data without moving the raw information. By integrating federated learning into the dkNET Texera platform, researchers can access diverse datasets from different institutions to improve AI model accuracy and generalizability in diabetes research. The approach aims to lower barriers to collaboration, enabling smaller centers to contribute to large-scale analyses while protecting patient privacy. The ultimate goal is to accelerate discoveries in diabetes prevention, diagnosis, and treatment by leveraging secure, distributed data resources.
Why it matters
Potential benefit: If successful, patients with diabetes could benefit from faster advances in personalized diagnosis and treatment informed by broader, more representative data.
How similar studies have gone: Federated learning approaches have shown promise in enabling multi-institutional AI research while preserving privacy, with growing adoption in biomedical fields.
Where this research is happening
-
University of California, San Diego
La Jolla, United States Active
Researchers
- Principal investigator: Grethe, Jeffrey S. — University of California, San Diego
- Study coordinator: Grethe, Jeffrey S.
Related research
Other NIH-funded projects on the same topics.
-
Improved MRI guidance for pediatric heart catheterization using autonomous multi-beat image synthesis
Aiming to make MRI-guided pediatric heart catheterizations safer and more reliable by using smart, multi-beat data fusion to produce clearer real-time MRI images.
-
Adapting a combination approach to reduce heavy drinking and boost HIV care and prevention among young men
A pilot project tests a proven program that helps young men cut down on heavy drinking and improves HIV treatment and prevention outcomes.
-
How specific anti-NMDAR1 antibodies in the blood may affect memory and brain protection
This research is exploring whether natural or abnormal anti-NMDAR1 antibodies in the blood influence memory, behavior, and brain protection in humans.
-
Screening and treatment of Chlamydia infection in pregnancy to help prevent preterm birth
This grant studies whether screening pregnant people for Chlamydia trachomatis and treating those who are positive can reduce the risk of preterm birth.
-
Pharmacometrics Core at UC San Diego
A pharmacometrics core is funded to support researchers in analyzing drug data to improve how medicines work for patients.
-
Milk Analytics Core for Precision Dairy Research
A core facility at UC San Diego will provide specialized milk analysis services to support research on dairy biology and human health.
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.