AI-READI consortium launches groundbreaking diabetes data study

Researchers today (November 8, 2024) released the key dataset from an ambitious study into biomarkers and environmental factors that may influence the development of type 2 diabetes. Because the study participants include people who do not have diabetes and others with varying stages of the condition, the initial findings indicate a range of information that differs from previous research.

For example, data from a custom-made environmental sensor in participants’ homes shows a clear link between disease state and exposure to small pollution particles. The data collected also included survey responses, depression scales, eye scans, and traditional measures of glucose and other biological variables.

All this data is intended to be collected by artificial intelligence for new insights about risks, preventive measures and pathways between disease and health.

We see data supporting the heterogeneity among patients with type 2 diabetes; that people are not all dealing with the same thing. And because we’re getting such large, detailed data sets, researchers will be able to explore this in depth.”

Dr. Cecilia Lee, professor of ophthalmology, University of Washington School of Medicine

She expressed her enthusiasm about the quality of the data collected, which covered 1,067 people, just 25% of the total number of expected study participants.

Lee is program director of AI-READI (Artificial Intelligence Ready and Equitable Atlas for Diabetes Insights). The National Institutes of Health-backed initiative aims to collect and share AI-ready data so global scientists can analyze it for new clues about health and disease.

The first data release is highlighted in an article published in the journal on November 8 Nature metabolism. The authors reiterated their goal to collect health information from a more racially and ethnically diverse population than previously measured, and to make the resulting data technically and ethically ready for AI mining.

“This discovery process has been stimulating,” said Dr. Aaron Lee, professor of ophthalmology at UW Medicine and principal investigator of the project. “We are a consortium of seven institutions and multidisciplinary teams that have never worked together before. But we have shared goals: harnessing unbiased data and protecting the security of that data, while making it accessible to colleagues around the world. “

At research sites in Seattle, San Diego and Birmingham, Alabama, recruiters are collectively enrolling 4,000 participants, with inclusion criteria promoting balance:

• race/ethnicity (1,000 each – white, black, Hispanic, and Asian)
• severity of disease (1,000 each – no diabetes, prediabetes, medicated/non-insulin controlled and insulin controlled type 2 diabetes)
• gender (equal distribution male/female)

“Conventionally, scientists investigate pathogenesis -; how people get sick -; and risk factors,” said Aaron Lee. “We want our datasets to also be examined for salutogenesis, or factors that contribute to health. So if your diabetes is getting better, what factors might contribute to that? We expect the flagship dataset to lead to new discoveries about type 2 diabetes in health care.” both ways.”

By collecting more deeply characterization data from many people, he added, the researchers hope to create pseudo-health histories of how a person can progress from illness to full health and from full health to disease.

The data is hosted on a custom online platform and produced in two sets: a controlled access set that requires a user agreement, and a registered, publicly available version without HIPAA protected information.

The pilot data publication (summer 2024) with 204 participants has been downloaded by more than 110 research organizations worldwide. Researchers must verify their identity and agree to ethical terms of use. (Read more about accessing the data at aireadi.org.)

The AI-READI Consortium consists of the University of Washington School of Medicine, University of Alabama at Birmingham, University of California San Diego, California Medical Innovations Institute, Johns Hopkins University, Native Biodata Consortium, Stanford University and Oregon Health & Science University.

The project is based at UW Medicine’s Angie Karalis Johnson Retina Center in Seattle. Cecilia Lee holds the Klorfine Family Endowed Chair. Aaron Lee holds the Dan and Irene Hunter Endowed Professorship.

This work was supported by the NIH (grants OT2OD032644 and P30 DK035816). The authors’ conflict of interest statements are in the published article, which will be provided upon request.