Ethical Multimodal AI for Obesity, Diabetes and Digestive Disease
Official title: Ethical Multimodal AI Development for Obesity, Diabetes and Digestive Disease
Funded at University of Pennsylvania · NIH-11556715 · Data updated 2026-11-12
A Penn team is building safe, multimodal AI tools using medical data to help care for obesity, diabetes, and digestive diseases.
Quick facts
| Grant type | NIH-funded research |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of Pennsylvania NIH-funded |
| Lab location | 1 site (Philadelphia, United States) |
| Project start | September 1, 2025 |
| Project end | August 31, 2027 |
| Funding year | 2026 |
| Award (this year) | $1,682,880 |
| NIH project number | 3OT2OD038048-01S1 |
| Project ID | NIH-11556715 on NIH RePORTER |
Who could benefit from this research
✓Could help
Patients with obesity, diabetes, or digestive diseases whose clinical data could be incorporated into AI tools and who are engaged in shared decision-making about digital health interventions.
✕Less likely to help
Individuals without these conditions or those who do not contribute or access digital health tools may not directly benefit.
What this research studies
This project aims to create foundational multimodal AI models that can handle images, videos, EHR data, biospecimens, and genetic information while prioritizing ethical use. It will encode diverse data into a shared representation and include a virtual ethics critic to guide model behavior. The team will gather input from clinicians, patients, and other stakeholders through iterative co-design and interviews to shape governance and deployment in real clinical settings. The work will also focus on scalable compute infrastructure to ensure the models can be used in practice. The Penn Medicine BioBank, with a large patient cohort, will serve as a key data source for developing and testing these models.
Why it matters
Potential benefit: If successful, patients could receive more personalized and ethically designed AI-powered tools to assist in managing obesity, diabetes, and digestive diseases.
How similar studies have gone: Prior multimodal AI efforts show promise, but this project emphasizes ethical design and real-world deployment in healthcare.
Where this research is happening
-
University of Pennsylvania
Philadelphia, United States Active
Researchers
- Principal investigator: Witschey, Walter R.t. — University of Pennsylvania
- Study coordinator: Witschey, Walter R.t.
Related research
Other NIH-funded projects on the same topics.
-
DHRS9's role in diet-induced obesity and diabetes
A study investigates how DHRS9 affects obesity-related diabetes in mice, to understand whether vitamin A or inflammatory lipid signals drive insulin resistance.
-
Ksr2 and obesity-related hearing loss in a mouse model: what it means for veterans
This project studies how obesity and type 2 diabetes affect hearing using a mouse model to identify ways to protect hearing in people with metabolic problems.
-
Low-cost, heat-stable GLP-1 and GIP receptor agonists produced in maize for diabetes and obesity
This project aims to make affordable, heat-stable versions of diabetes and obesity medicines using corn plants.
-
Epitranscriptomics in obesity and type 2 diabetes
Researchers are studying how gene activity changes in fat tissue and other organs to better understand obesity and type 2 diabetes, with the goal of finding new ideas for treatment.
-
LAUNCHED: Advancing early-career scientists in health, nutrition, obesity, and diabetes research
A national program helps new researchers in diabetes and related digestive diseases build careers through mentoring, training, and funding support.
-
SPLENDOR-NC: Expanding Nutrition, Diabetes, and Obesity Research in North Carolina
A program to help early-career scientists in North Carolina launch and grow nutrition, diabetes, and obesity research that aligns with NIDDK goals.
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.