Version 2 of the AI-READI dataset is released

AI-READI Dataset v2

We are extremely excited to announce the release of the second version of the AI-READI dataset! It can be downloaded from the FAIRhub platform at https://doi.org/10.60775/fairhub.2. This version of the dataset contains over 165,000 files and 2TB of data from 1067 study participants (about 25% of the study’s total expected enrollees).

The AI-READI Project

AI-READI (Artificial Intelligence Ready and Equitable Atas for Diabetes Insights) is one of the Data Generating Projects funded by Bridge2AI, an NIH Common Fund program aimed at setting the stage for the wider use of AI to solve pressing challenges in human health. Using type 2 diabetes as its model disease, the project aims to ultimately collect data from 4,000 participants. To ensure the data is population-representative, the 4,000 participants will be balanced for three factors: disease severity, race/ethnicity, and sex. Various data types are being collected from each participant, including vitals, electrocardiograms, glucose monitoring, physical activity, ophthalmic evaluation, and more. The data is intended to be made broadly available to researchers for gaining novel insights into risks, preventive measures, and pathways between disease and health in type 2 diabetes. The study is specifically designed to enable novel discoveries in the salutogenesis of type 2 diabetes, i.e. how and why someone with diabetes evolves toward health. More details about the project is provided in a paper published today in the journal Nature Metabolism.

Role of the FAIR Data Innovations Hub

Our team at the FAIR Data Innovations Hub is contributing to different aspects of the project. We are co-leading the development of FAIRhub, a novel platform for easily managing, preparing, and sharing FAIR and AI-ready clinical research datasets. We are contributing to the development of standards and guidelines for making clinical research FAIR and AI-ready, particularly through developing the Clinical Dataset Structure (CDS), establishing recommendations for AI-ready datasets, and investigating documentation of datasets through datasheets-like methods. We are also developing and maintaining the project website aireadi.org and the dataset documentation website docs.aireadi.org. We are contributing to the development of the next-generation AI task force by mentoring interns from the AI-ready internship program.

Funding and collaborators

This project is supported by the National Institutes of Health (OT2OD032644). In addition to the FAIR Data Innovations Hub (California Medical Innovations Institute), the AI-READI Consortium comprises the University of Washington School of Medicine, University of Alabama at Birmingham, University of California San Diego, Johns Hopkins University, Native Biodata Consortium, Stanford University, and Oregon Health & Science University.