• The AI-READI initiative has released a flagship dataset featuring comprehensive health information to advance type 2 diabetes research using AI.
  • The dataset currently has data from 1,067 participants.
  • Researchers aim to enrol 4,000 participants for AI analysis.

The flagship dataset from a study analysing biomarkers and environmental factors that could influence the development of type 2 diabetes is being released.

The data includes survey responses, depression scales, eye-imaging scans, glucose measures and information from environmental sensors.

The results are ready to be analysed by artificial intelligence (AI) in the hope of gaining innovative insights about risks, preventative measures and pathways between disease and health.

Dr Cecilia Lee is program director of AI-READI (Artificial Intelligence Ready and Equitable Atlas for Diabetes Insights), an initiative supported by The National Institutes of Health that aims to gather and share AI-ready data that scientists around the world can study for insights into health and disease.

She is excited about the excellence of this collected data from 1,067 participants, which is 25% of the expected number of study participants.

Dr Lee, who is also Professor of Ophthalmology at the University of Washington School of Medicine, said: “We see data supporting heterogeneity among type 2 diabetes patients — that people aren’t all dealing with the same thing. And because we’re getting such large, granular datasets, researchers will be able to explore this deeply.”

Researchers are aiming to enrol a more racially and ethnically diverse participant pool compared to previous studies to ensure the health data collected will be technically and ethically ready for AI analysis.

Dr Aaron Lee, principal investigator of the project and Professor of Ophthalmology at the University of Washington School of Medicine, said: “This process of discovery has been invigorating. We’re a consortium of seven institutions and multidisciplinary teams that had not worked together before. But we have shared goals of drawing on unbiased data and protecting the security of that data as we make it accessible to colleagues everywhere.”

Recruiters are looking for a total of 4,000 participants at the study sites of Seattle, San Diego, and Birmingham, Alabama, with equal numbers across race/ethnicity (1,000 each – white, Black, Hispanic and Asian), disease severity (1,000 each – no diabetes, prediabetes, medication/non-insulin-controlled and insulin-controlled type 2 diabetes) and sex (2,000 each – male and female).

Dr Lee explained: “Conventionally, scientists are examining pathogenesis — how people become diseased — and risk factors.

“We want our datasets to also be studied for salutogenesis, or factors that contribute to health. So, if your diabetes gets better, what factors might be contributing to that? We expect that the flagship dataset will lead to novel discoveries about type 2 diabetes in both of these ways.”

Dr Lee added that he hopes this data will create pseudo-health histories of how people progress from full health to disease and vice versa.

There are two options available to access the data; a controlled-access requiring users to have a usage agreement and a version available to the public which excludes HIPAA-protected information.

Researchers must verify their identity and agree to ethical-usage terms before accessing any of the data.

For further information, visit https://aireadi.org

Get our free newsletters

Stay up to date with the latest news, research and breakthroughs.