Multimodal AI to Accelerate Precision Medicine for Type 1 Diabetes (U01- Clinical Trials Not Allowed)

About This Grant

Type 1 diabetes (T1D) is a complex disease involving interactions among many different cell types, tissues, organs and biological processes. Genetics, the environment, and lifestyle all play a role in disease development and progression. Over the past two decades, the National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK) has supported major T1D research consortia covering basic, translational, and clinical research. Each consortium has focused on different aspects of T1D, such as specific organs, stages of disease or clinical outcomes. Together, these consortia have collected large longitudinal and multimodal datasets using standardized protocols and coordinated studies. While individual consortia have improved our understanding of specific areas, combining their work offers a rare opportunity to see how different biological processes interact to drive T1D development and progression. This integrated view can answer fundamental questions about T1D biology that cannot be answered using individual datasets or studies alone.

Recent advances in artificial intelligence (AI) now make it possible to integrate these complementary datasets and study T1D across various tissues, disease stages, and biological levels. Building on these resources, NIDDK will support a coordinated, milestone-driven research project to answer fundamental questions about T1D biology and accelerate the development of personalized medicine.

The project will combine multimodal human pancreas and clinical datasets to better understand how biological processes interact as T1D develops and progresses. The research will generate new insights into T1D biology, help us understand the different forms and stages of T1D, identify biomarkers, and inform new approaches for disease prevention, intervention, and treatment. To support the research, the project will develop and test advanced multimodal AI models. It will also develop AI-enabled research workflows, new methods to integrate data, and privacy-preserving synthetic datasets.