AI READI all combined d4d

The AI-READI flagship dataset consists of multimodal data collected from individuals with and without Type 2 Diabetes Mellitus (T2DM), harmonized across three data collection sites. The study design targeted approximately equal distribution of participants across diabetes severity strata and implemented a protocol spanning multiple domains (e.g., survey data, physical measurements, clinical data, imaging, wearable device data) to enable downstream AI/ML analyses not feasible with many existing sources (e.g., claims or EHRs). Publicly available components (under a Health Data License) include survey data, blood and urine lab results, fitness activity levels, clinical measurements (e.g., monofilament and cognitive function testing), retinal images, ECG, blood glucose levels, and environmental variables (e.g., home air quality). Controlled-access components (requiring a data use agreement) include 5-digit ZIP code, sex, race, ethnicity, genetic sequencing data, past health records, medications, and traffic and accident reports. Enrollment is ongoing; early releases (e.g., pilot) may not achieve fully balanced distributions across groups. Dataset versions include v1.0.0 (2024-05-03) and v2.0.0 (2024-11-08). Size reported on FAIRhub: ~2.01 TB comprising ~165,051 files.