C-BRAIN and NVIDIA Use Open Source AI to Speed Up Dementia Research

A research bottleneck of data and synthesis

According to NVIDIA, 57 million people worldwide live with dementia, and over 10 million new cases are diagnosed each year. NIH funding has risen 7x in the last 15 years to $3.9 billion annually, yet no treatment has been found to stop, prevent or reverse the disease.

The source names three bottlenecks: too few high impact scientific findings, too much data held in institutional silos, and a pace of synthesis too slow to keep up with published research.

C-BRAIN is led by Dr. Randall Bateman and includes 18 member institutions across academic, philanthropic, pharma and research organizations. It launched in November 2025. Bateman, founder and director of C-BRAIN, said: "We have a window of opportunity with artificial intelligence to do research fundamentally different than we've ever done before, in a way that accelerates discoveries to help patients."

Tapping "dark data" without moving it

The consortium focuses on datasets that have never been publicly accessible to AI tools or human researchers, including unpublished findings, negative results and governed proprietary data from member institutions. C-BRAIN calls this "dark data." Chief technology officer Dr. Ade Ojewole said: "A lot of life sciences data doesn't make its way into the frontier models."

To protect patient privacy and institutional governance, C-BRAIN uses a hybrid centralized and federated approach, in which AI models learn from data at each institution without the data leaving it. Some dark data is also deposited directly into secure computer systems.

On the infrastructure side, C-BRAIN currently runs 64 NVIDIA data center GPUs on premises alongside cloud-based nodes on Microsoft Azure. More NVIDIA GPU capacity, including NVIDIA Blackwell systems, is on the horizon. The group is also working with NVIDIA to incorporate the NVIDIA BioNeMo open developer platform and the MONAI framework into its research pipelines.

OpenScientist and InsightEngine

Researchers have already built two tools:

• OpenScientist, built with Lawrence Berkeley National Laboratory in an effort led by research scientist Justin Reese. It is an open source agentic AI co-scientist that takes a research question and dataset, then semi-autonomously generates hypotheses, runs analyses and produces verifiable, auditable insights.
• InsightEngine, built with 387 Labs. This open source platform uses agentic AI to test hypotheses against the scientific literature, analyze user-supplied datasets, explore a biomedical knowledge graph and check every claim against evidence to catch hallucinations before researchers commit to costly experiments.

In published case studies, OpenScientist completed analyses in minutes that domain scientists estimated would take weeks to months, at a cost of under $10 per run. With C-BRAIN's current reach of over 200 research groups, NVIDIA says this could release capacity potentially exceeding one million hours annually at scale.

Next goal: a multimodal foundation model

C-BRAIN aims to build a multimodal biological foundation model trained on neuroimaging, multi-omics, fluid biomarkers and longitudinal clinical measures. By year three, it aims to discover new causal mechanisms of brain aging and Alzheimer's disease.

Ojewole said that pushing the limits of what today's spatial omics machine learning architectures can model will require "a great deal of optimization," and that NVIDIA software is expected to play a role there. Bateman said AI that can think and reason "has the potential to accelerate discoveries that will lead to powerful and implementable preventions and treatments for the entire population."

For researchers, the immediate relevance is the availability of two open source tools aimed at shortening the path from question to verified insight. The larger goals, including new causal mechanisms, remain targets rather than results.