id: https://fairhub.io/datasets/2
name: AI-READI
title: Artificial Intelligence Ready and Equitable Atlas for Diabetes Insights (AI-READI)
description: 'The AI-READI is a flagship dataset consisting of multimodal data collected from 4,000 individuals with and without Type 2 Diabetes Mellitus (T2DM), harmonized across 3 data collection sites (Birmingham, Alabama; San Diego, California; Seattle, Washington). The dataset was designed with future AI/Machine Learning studies in mind, including recruitment sampling procedures aimed at achieving approximately equal distribution of participants across diabetes severity (triple-balanced by race/ethnicity, biological sex, and T2DM severity), as well as a multi-domain data acquisition protocol (survey data, physical measurements, clinical data, imaging data, wearable device data, environmental sensors, biospecimens) to enable downstream AI/ML analyses that may not be feasible with existing data sources such as claims or electronic health records data. The goal is to better understand salutogenesis (the pathway from disease to health) in T2DM. The study follows FAIR principles and incorporates ethical and equitable data collection and management practices. '
page: https://fairhub.io/datasets/2
language: en
license: CC BY-NC 4.0
doi: 10.57895/fairhub.2
keywords: - Type 2 Diabetes Mellitus - T2DM - AI-READI - Machine Learning - Artificial Intelligence - multimodal dataset - harmonized data - multi-site study - salutogenesis - FAIR principles - retinal imaging - continuous glucose monitoring - wearable devices - biorepository - biospecimens - triple-balanced sampling - health equity - Bridge2AI - cross-sectional study
is_tabular: false
purposes:
- id: aireadi:purpose:1
name: Understanding T2DM salutogenesis
description: 'Better understand salutogenesis (the pathway from disease to health) in Type 2 Diabetes
Mellitus using a hypothesis-agnostic, harmonized, multi-domain dataset designed specifically for AI/ML
research. The dataset aims to provide critical insights into how individuals can transition from diabetes
toward health resilience through pseudotime manifold analysis.
'
- id: aireadi:purpose:2
name: Establishing AI/ML data standards
description: 'Establish standards, best practices, and guidelines for collection, preparation, and sharing
of medical/health data sets targeted for AI/ML applications. This includes guidance from bioethicists
on ethical and equitable data collection and management practices, with adherence to FAIR principles.
'
- id: aireadi:purpose:3
name: Addressing demographic inequities in T2DM research
description: 'Address the lack of racial and ethnic diversity in T2DM research by creating a dataset
that is triple-balanced across race/ethnicity (Asian, Black, Hispanic, White), biological sex (male,
female), and diabetes severity (no diabetes, pre-diabetes/lifestyle-controlled, medication-controlled,
insulin-controlled).
'
tasks:
- id: aireadi:task:1
name: Enable multi-domain AI/ML analyses for T2DM
description: 'Enable downstream AI/ML analyses across survey, clinical, imaging, wearable device, environmental,
and biospecimen domains related to T2DM that may not be feasible with existing data sources such as
claims or electronic health records data alone. The multimodal nature of the data supports complex
machine learning model development.
'
- id: aireadi:task:2
name: Develop unbiased AI/ML models
description: 'Support the development of unbiased machine learning models through balanced data collection
across demographic groups and diabetes severity levels. The triple-balanced design is critical for
preventing algorithmic bias in AI/ML applications.
'
- id: aireadi:task:3
name: Study T2DM disease trajectories
description: 'Study disease trajectories and salutogenesis pathways in T2DM through cross-sectional
analysis of participants at different disease stages, enabling pseudotime manifold analysis to predict
disease progression and paths to health resilience.
'
addressing_gaps:
- id: aireadi:gap:1
name: Lack of multimodal T2DM datasets
description: 'Provide a large-scale, harmonized, multi-site, multi-domain dataset enabling AI/ML analyses
not feasible with existing sources (e.g., claims or EHR alone). With 4,000 participants and over 10
variable domains, this is the largest publicly accessible dataset of its kind for T2DM research.
'
- id: aireadi:gap:2
name: Demographic underrepresentation
description: 'Address demographic inequities in T2DM research by recruiting equal proportions across
four race/ethnic groups (Asian, Black, Hispanic, White) and both biological sexes, improving upon
many previous epidemiological studies and clinical trials that lacked diversity.
'
- id: aireadi:gap:3
name: AI-readiness of medical datasets
description: 'Create a model for future AI-ready medical datasets through comprehensive metadata, standardized
data formats, FAIR compliance, and ethical data governance practices that can be replicated for other
health conditions.
'
creators:
- id: aireadi:creator:1
name: Aaron Lee
description: Contact PI/Project Leader, University of Washington, Department of Ophthalmology, Assistant
Professor
- id: aireadi:creator:2
name: Cynthia Owsley
description: Principal Investigator, University of Alabama at Birmingham, Department of Ophthalmology
and Visual Sciences
- id: aireadi:creator:3
name: Sally L. Baxter
description: Co-Investigator, University of California San Diego, Department of Ophthalmology
- id: aireadi:creator:4
name: Christopher G. Chute
description: Co-Investigator, AI-READI Consortium
- id: aireadi:creator:5
name: Megan E. Collins
description: Co-Investigator, AI-READI Consortium
- id: aireadi:creator:6
name: Jeffrey C. Edberg
description: Co-Investigator, University of Alabama at Birmingham, Department of Medicine
- id: aireadi:creator:7
name: Kadija Ferryman
description: Co-Investigator, AI-READI Consortium (Bioethics)
- id: aireadi:creator:8
name: Michelle Hribar
description: Co-Investigator, AI-READI Consortium
- id: aireadi:creator:9
name: Samantha Hurst
description: Co-Investigator, AI-READI Consortium
- id: aireadi:creator:10
name: Hiroshi Ishikawa
description: Co-Investigator, AI-READI Consortium
- id: aireadi:creator:11
name: Cecilia S. Lee
description: Co-Investigator, University of Washington, Department of Ophthalmology
- id: aireadi:creator:12
name: Alvin Y. Liu
description: Co-Investigator, AI-READI Consortium
- id: aireadi:creator:13
name: Gerald McGwin
description: Co-Investigator, University of Alabama at Birmingham, Departments of Ophthalmology and
Epidemiology
- id: aireadi:creator:14
name: Shannon K. McWeeney
description: Co-Investigator, AI-READI Consortium
- id: aireadi:creator:15
name: Camille Nebeker
description: Co-Investigator, AI-READI Consortium
- id: aireadi:creator:16
name: Bhavesh Patel
description: Co-Investigator, AI-READI Consortium
- id: aireadi:creator:17
name: Sara Jean Singer
description: Co-Investigator, AI-READI Consortium
- id: aireadi:creator:18
name: Michael P. Snyder
description: Co-Investigator, AI-READI Consortium
- id: aireadi:creator:19
name: Joseph Manuel Yracheta
description: Co-Investigator, AI-READI Consortium
- id: aireadi:creator:20
name: Linda M. Zangwill
description: Co-Investigator, University of California San Diego, Department of Ophthalmology
funders:
- id: aireadi:funder:1
name: NIH Common Fund Bridge2AI Program
description: 'Funded through National Institutes of Health grant OT2OD032644, administered by NIH Office
of the Director. Additional support from grants P30DK035816 (Nutrition and Obesity Research Center),
UL1TR003096, and Research to Prevent Blindness. Total funding in 2022: $5,026,499. Opportunity Number:
OTA-21-008. Project dates: September 1, 2022 to August 31, 2025.
'
instances:
- id: aireadi:instance:1
name: Individual participants
description: 'Individual participants aged 40 and older with and without Type 2 Diabetes Mellitus (T2DM).
Target enrollment is 4,000 people, triple-balanced by self-reported race/ethnicity (Asian, Black,
Hispanic, White), T2DM severity (no diabetes, pre-diabetes/lifestyle-controlled diabetes, diabetes
treated with oral medications or non-insulin injections, insulin-controlled diabetes), and biological
sex (male, female). Participants must speak, read, and understand English. Exclusion criteria include
pregnancy and type 1 diabetes.
'
subpopulations:
- id: aireadi:subpop:1
name: Asian participants
description: Self-reported Asian race/ethnicity, target approximately 1,000 participants (25% of sample)
- id: aireadi:subpop:2
name: Black participants
description: Self-reported Black race/ethnicity, target approximately 1,000 participants (25% of sample)
- id: aireadi:subpop:3
name: Hispanic participants
description: Self-reported Hispanic ethnicity, target approximately 1,000 participants (25% of sample)
- id: aireadi:subpop:4
name: White participants
description: Self-reported White race/ethnicity, target approximately 1,000 participants (25% of sample)
- id: aireadi:subpop:5
name: No diabetes
description: Participants without diabetes diagnosis, target approximately 1,000 participants (25% of
sample)
- id: aireadi:subpop:6
name: Pre-diabetes and lifestyle-controlled diabetes
description: Participants with pre-diabetes or lifestyle-controlled diabetes, target approximately 1,000
participants (25% of sample)
- id: aireadi:subpop:7
name: Medication-controlled diabetes
description: Participants with diabetes treated with oral medications or non-insulin injections, target
approximately 1,000 participants (25% of sample)
- id: aireadi:subpop:8
name: Insulin-controlled diabetes
description: Participants with insulin-controlled diabetes, target approximately 1,000 participants
(25% of sample)
sensitive_elements:
- id: aireadi:sensitive:1
name: Genetic and biospecimen data
description: 'Genomic DNA extracted from buffy coats, blood derivatives, and urine samples stored with
potential for future genetic analyses. Available in controlled access dataset only. Includes genetic
sequencing data from buffy coats, PBMCs, and PAXgene RNA.
'
- id: aireadi:sensitive:2
name: Geographic and demographic identifiers
description: '5-digit zip code, detailed race, ethnicity, and sex information available in controlled
access dataset only. Public dataset contains de-identified data.
'
- id: aireadi:sensitive:3
name: Medical history and records
description: 'Past health records, medications with RxNorm codes, traffic and accident reports available
in controlled access dataset only.
'
confidential_elements:
- id: aireadi:confidential:1
name: Controlled access dataset
description: 'A controlled access subset requires a separate data use agreement and includes 5-digit
zip code, sex, race, ethnicity, genetic sequencing data (from buffy coats), past health records, medications,
and traffic and accident reports. Access requirements are managed by the Data Access Committee.
'
collection_mechanisms:
- id: aireadi:collection:1
name: In-person data collection visits
description: 'Single study encounter per participant at one of three data collection sites (Birmingham,
San Diego, Seattle). Multi-domain protocol containing over 10 data collection domains performed during
the visit lasting between 2.5 and 4 hours.
'
- id: aireadi:collection:2
name: Electronic health record screening
description: 'Source population identified by screening electronic health records for patients aged
40+ who had medical encounters between 2020-2025. ICD-10 codes used to identify T2DM (E11.X) and pre-diabetes
(R73.09) cases.
'
- id: aireadi:collection:3
name: Wave-based recruitment
description: 'Participants recruited in waves to facilitate efficient sampling. Composition and size
of each wave influenced by observed participation characteristics to maintain balance across race/ethnicity,
sex, and diabetes severity. Enrollment began July 18, 2023 and continues until November 30, 2026.
'
- id: aireadi:collection:4
name: Home-based wearable monitoring
description: 'Continuous glucose monitoring (Dexcom G6, 5-minute intervals), physical activity monitoring
(Garmin VivoSmart 5), and environmental sensor monitoring (temperature, humidity, air quality) conducted
at participants'' homes over 10-day monitoring periods.
'
- id: aireadi:collection:5
name: Biospecimen collection and biobanking
description: 'Blood (53 mL) and urine collected during study visit. Local processing for plasma, serum,
buffy coats at all sites. Centralized biobanking at UAB CCTS. Standardized operating procedures ensure
consistent handling.
'
acquisition_methods:
- id: aireadi:acquisition:1
name: Survey and questionnaire data
description: 'Self-reported data collected via REDCap interfaces including demographics, medical history,
social determinants of health, depression screening (CES-D-10), diabetes-related emotional distress
(PAID scale), diabetes self-care score, dietary assessment, ophthalmic survey, substance use (smoking,
alcohol, vaping, marijuana), general health conditions, and current medications with RxNorm codes.
'
- id: aireadi:acquisition:2
name: Physical measurements and vital signs
description: 'Height, weight, waist and hip circumference (waist-hip ratio and BMI calculated), blood
pressure (systolic and diastolic, measured twice separated by 2 minutes), and heart rate collected
during in-person visit using standardized protocols.
'
- id: aireadi:acquisition:3
name: Retinal imaging
description: 'Multi-device retinal imaging protocol capturing data from Aurora IQ (Optomed), EIDON widefield
truecolor confocal fundus system (iCare), Spectralis HRA OCT and OCTA (Heidelberg Engineering), Maestro2
3D OCT-1 (Topcon), Triton DRI OCT (Topcon), Cirrus 5000 (Carl Zeiss), and Fluorescence Lifetime Imaging
Ophthalmoscopy (FLIO, Heidelberg Engineering). Both eyes imaged under dilated conditions (except Aurora
IQ). Output formats include DICOM, with proprietary formats (.fda, .sdt) converted to DICOM.
'
- id: aireadi:acquisition:4
name: Visual function testing
description: 'Visual acuity and contrast sensitivity under photopic (daylight) and mesopic (dim light)
conditions using Electronic Visual Acuity tester (M&S Technology) and Mars chart (Mars Perceptrix).
Autorefraction data collected using Topcon KR 800.
'
- id: aireadi:acquisition:5
name: Clinical laboratory testing
description: 'Complete blood count (CBC) from fresh whole blood at local CLIA-certified labs. Central
lab testing at UW Nutrition and Obesity Research Center (NORC) for EDTA plasma tests (NT-proBNP, Troponin-T,
C-peptide, insulin), serum tests (CRP-HS, lipid panel, glucose, kidney and liver function markers),
whole blood tests (HbA1c), and urine tests (creatinine, albumin, other markers).
'
- id: aireadi:acquisition:6
name: Electrocardiogram (ECG)
description: '12-lead ECG data collected using Philips Pagewriter TC30 Cardiograph during study visit
with participant sitting in reclining chair or lying supine at recorded position (0 degrees, 30 degrees,
60 degrees, or 90 degrees relative to supine).
'
- id: aireadi:acquisition:7
name: Cognitive function testing
description: 'Montreal Cognitive Assessment (MoCA) administered electronically on iPad using MoCA Duo
Application (total score, section subscores, Memory Index Score, task completion times). Total possible
score is 30, with higher numbers representing better performance.
'
- id: aireadi:acquisition:8
name: Peripheral neuropathy assessment
description: 'Monofilament testing performed to assess peripheral neuropathy using 10g filament at three
locations on each foot (10 times per location) with participant''s eyes closed, responding yes/no
whether they feel the filament.
'
- id: aireadi:acquisition:9
name: Continuous glucose monitoring
description: 'Dexcom G6 Continuous Glucose Monitor capturing blood glucose measurements (mg/dL) every
5 minutes for 10 days. Data exported in CSV format.
'
- id: aireadi:acquisition:10
name: Physical activity monitoring
description: 'Garmin VivoSmart 5 wearable device capturing number of steps, heart rate, sleep duration
(circadian and diurnal rhythm), and oxygen saturation for 10 days. Data exported in .FIT format and
converted to mHealth standard.
'
- id: aireadi:acquisition:11
name: Environmental monitoring
description: 'Custom-designed environmental sensor (Karalis Johnson Retina Center, UW) capturing ambient
temperature, relative humidity, nitrogen oxides (NO and NO2), volatile organic compounds, particulate
matter (PM1.0, PM2.5, PM4, PM10), and multi-spectral light intensity (11 measurements) for 10 days.
Data in CSV format.
'
- id: aireadi:acquisition:12
name: Biospecimen collection
description: 'Non-fasting blood (53 mL) and urine collection. Processing includes whole blood for CBC,
EDTA plasma, serum, buffy coats for genomic DNA extraction, peripheral blood mononuclear cells (PBMCs)
from CPT tubes, and PAXgene RNA vacutainers. Samples stored at UAB CCTS biorepository at appropriate
temperatures.
'
collection_timeframes:
- id: aireadi:timeframe:1
name: Study enrollment period
description: 'Enrollment began July 18, 2023 (pilot phase) and continues until November 30, 2026. Each
participant completes a single study encounter. Data released periodically: pilot data released May
2024; v1.0.0 data through July 31, 2024 released November 2024; subsequent versions (v2.0.0, v3.0.0)
released with additional participants. Final dataset expected after completion of 4,000 participant
enrollment by November 2026.
'
data_collectors:
- id: aireadi:datacollector:1
name: AI-READI Study Coordinators
description: 'Trained and certified study coordinators at three data collection sites (University of
Alabama at Birmingham, University of California San Diego, University of Washington). Coordinators
follow a standardized Manual of Procedures (MOP) and complete a certification process before enrolling
participants. Practice subjects required before beginning participant enrollment.
'
sampling_strategies:
- id: aireadi:sampling:1
name: Triple-balanced recruitment
description: 'Recruitment sampling procedures aimed at achieving approximately equal distribution of
participants across three dimensions: (1) race/ethnicity (Asian, Black, Hispanic, White), (2) T2DM
severity (no diabetes, pre-diabetes/lifestyle-controlled, medication-controlled, insulin-controlled),
and (3) biological sex (male, female). This balanced design is critical for developing unbiased machine
learning models.
'
is_sample: true
is_random: false
is_representative: false
why_not_representative:
- 'The triple-balanced design intentionally over-samples racial/ethnic minority groups and specific
diabetes severity groups relative to their population prevalence, to enable unbiased AI/ML model development.
Participants are volunteers, introducing volunteer selection bias that may limit generalizability
to non-volunteer populations.
'
strategies:
- Targeted recruitment to balance demographics across race/ethnicity, sex, and diabetes severity
- Wave-based recruitment with monitoring and adjustment through under- and oversampling
- Recruitment from electronic health records screening using ICD-10 codes (E11.X for T2DM, R73.09 for
pre-diabetes)
- Personalized invitation letters and emails with REDCap recruitment interface
preprocessing_strategies:
- id: aireadi:preproc:1
name: Data standardization and harmonization
description: 'Data harmonized across three collection sites (Birmingham, San Diego, Seattle) using standardized
operating procedures, common protocols, and centralized data management through REDCap. Ensures consistency
and comparability across sites.
'
- id: aireadi:preproc:2
name: Image format conversion
description: 'Retinal imaging data converted from proprietary formats (.fda, .sdt) to DICOM standard
for the dataset. Wearable device data converted from .FIT format to mHealth standard.
'
- id: aireadi:preproc:3
name: Biospecimen processing
description: 'Standardized local processing for plasma, serum, and buffy coats using consistent protocols.
Centralized processing of CPT tubes for PBMC isolation at UAB CCTS. Batch shipping of biospecimens
for central clinical lab analyses.
'
- id: aireadi:preproc:4
name: Quality control and validation
description: 'Multiple quality control measures including standardized training of study coordinators,
equipment calibration, duplicate measurements, and data validation checks in REDCap system. Data managers
at each site oversee quality control before uploading to FAIRhub.
'
- id: aireadi:preproc:5
name: Data mapping to standards
description: 'All data mapped to applicable data standard formats such as Observational Medical Outcomes
Partnership Common Data Model for clinical data and DICOM format for retinal imaging. Data stored
and shared as AI-ready enabling immediate AI/ML research without reformatting.
'
cleaning_strategies:
- id: aireadi:cleaning:1
name: Multi-site harmonization
description: 'Standardized protocols and procedures across all three data collection sites ensure data
consistency and quality. Common equipment, training, and REDCap data management system used to maintain
FAIR principles compliance.
'
intended_uses:
- id: aireadi:use:1
name: AI/ML model development for T2DM
description: 'Primary intended use is development and training of artificial intelligence and machine
learning models to study Type 2 Diabetes Mellitus, disease trajectories, and salutogenesis (pathways
to health resilience). Designed for pseudotime manifold analysis to predict disease progression.
'
- id: aireadi:use:2
name: Multi-modal T2DM research
description: 'Research leveraging multiple data domains (imaging, clinical, genomic, wearable, environmental,
survey) to understand complex interactions and relationships in T2DM progression and management.
'
- id: aireadi:use:3
name: Health equity research
description: 'Studies examining racial and ethnic disparities in T2DM outcomes, social determinants
of health effects, and development of equitable AI/ML applications for diverse populations.
'
- id: aireadi:use:4
name: Biomarker discovery
description: 'Discovery of novel biomarkers for T2DM progression, complications, and salutogenesis using
biospecimens from the biorepository.
'
- id: aireadi:use:5
name: Model dataset for AI-ready data standards
description: 'Use as an exemplar for future AI-ready medical dataset development, demonstrating best
practices in data collection, preparation, sharing, and ethical governance.
'
discouraged_uses:
- id: aireadi:discouraged:1
name: Uses during ongoing enrollment without awareness of limitations
description: 'As enrollment is ongoing until November 2026, pilot data releases and periodic updates
may not have achieved balanced distribution across all groups. Early versions should be used with
awareness of this limitation.
'
- id: aireadi:discouraged:2
name: Clinical decision-making without validation
description: 'Dataset is for research purposes. Any AI/ML models developed should undergo appropriate
clinical validation before use in patient care or clinical decision-making.
'
- id: aireadi:discouraged:3
name: Re-identification attempts
description: 'Attempts to re-identify participants from de-identified data violate ethical principles
and data use agreements. The license explicitly prohibits attempts to identify or contact individual
data subjects or groups.
'
prohibited_uses:
- id: aireadi:prohibited:1
name: Clinical treatment decisions
description: 'The AI-READI Data License Agreement explicitly prohibits using the data to make clinical
treatment decisions for individual patients. The dataset is intended for research purposes only and
has not been validated for direct clinical use.
'
- id: aireadi:prohibited:2
name: Re-identification of participants
description: 'Attempting to re-identify individual data subjects or groups from the de-identified public
dataset is explicitly prohibited by the data use agreement and violates ethical principles.
'
- id: aireadi:prohibited:3
name: Sharing with non-licensed parties
description: 'Sharing data with parties who have not entered into the applicable license agreement (CC
BY-NC 4.0 for public data; separate data use agreement for controlled access data) is prohibited.
'
distribution_formats:
- id: aireadi:format:1
name: DICOM for imaging
description: 'Retinal imaging data distributed in DICOM format (converted from proprietary .fda and
.sdt formats for standardization).
'
- id: aireadi:format:2
name: CSV for tabular and time-series data
description: 'Survey data, clinical lab results, continuous glucose monitoring, environmental sensor
data, and other tabular/time-series data provided in CSV format.
'
- id: aireadi:format:3
name: mHealth standard for wearable data
description: 'Physical activity monitoring data (from Garmin VivoSmart 5) converted from .FIT format
to mHealth standard for interoperability.
'
- id: aireadi:format:4
name: XML for ECG data
description: 'Electrocardiogram data from Philips Pagewriter TC30 exported in .xml format.
'
distribution_dates: - id: aireadi:distdate:1 name: Pilot data release description: Pilot data released May 2024 as an early access release. - id: aireadi:distdate:2 name: v1.0.0 release description: Version 1.0.0 data (through July 31, 2024) released November 2024. - id: aireadi:distdate:3 name: v2.0.0 and v3.0.0 releases description: Versions 2.0.0 and 3.0.0 released with additional participants following v1.0.0. - id: aireadi:distdate:4 name: Final dataset release description: Final dataset expected after completion of 4,000 participant enrollment by November 2026.
distributions:
- id: aireadi:dist:1
name: Public access dataset (ZIP archive)
description: 'Public access subset of the AI-READI dataset available at https://fairhub.io/datasets/2
upon agreement with the CC BY-NC 4.0 license. Contains non-sensitive data including survey data, blood
and urine lab results, fitness activity levels, clinical measurements, retinal images, ECG, blood
glucose levels, and environmental variables. Distributed as a ZIP archive containing DICOM, CSV, mHealth,
and XML files.
'
format: ZIP
media_type: application/zip
- id: aireadi:dist:2
name: Controlled access dataset (ZIP archive)
description: 'Controlled access subset requiring a data use agreement. Contains sensitive data including
5-digit zip code, sex, race, ethnicity, genetic sequencing data, past health records, medications,
and traffic and accident reports. Distributed as a ZIP archive containing DICOM, CSV, mHealth, and
XML files.
'
format: ZIP
media_type: application/zip
maintainers:
- id: aireadi:maintainer:1
name: AI-READI Consortium
description: 'Multidisciplinary consortium managing dataset maintenance including data collection sites,
coordinating centers, and data governance committees. Contact through the University of Washington
as lead institution and data coordination center. Documentation maintained at https://docs.aireadi.org/
with version-specific guides for each data release.
'
updates:
id: aireadi:updates:1
name: Periodic data releases
description: 'Dataset updated periodically as enrollment progresses toward target of 4,000 participants
by November 2026. Version-specific documentation maintained for each release. Pilot data released
May 2024. Data through July 31, 2024 released November 2024 as v1.0.0. Subsequent versions v2.0.0
and v3.0.0 released with additional participants. Final dataset expected after completion of enrollment
by November 2026.
'
retention_limit:
id: aireadi:retention:1
name: Data and biospecimen retention
description: 'Digital data maintained according to NIH data sharing policies. Biospecimen retention
subject to institutional policies and consent agreements at UAB CCTS. Finite number of biospecimen
samples available for distribution to researchers. Procedures for reviewing and prioritizing biospecimen
requests are under development.
'
version_access:
id: aireadi:versionaccess:1
name: Version-specific documentation
description: 'All prior versions of the dataset are maintained with version-specific documentation at
https://docs.aireadi.org/. Each version includes a changelog and data dictionary. Dataset versioning
uses semantic versioning (e.g., v1.0.0, v2.0.0, v3.0.0).
'
extension_mechanism:
id: aireadi:extension:1
name: Ancillary study process
description: 'Researchers may apply to access biospecimens for future ancillary studies according to
procedures and policies being developed by the AI-READI Consortium. Requests are reviewed and prioritized
by designated committees.
'
ethical_reviews:
- id: aireadi:ethics:1
name: University of Washington IRB Approval
description: 'Study approved by Institutional Review Board (IRB) of University of Washington (approval
number STUDY00016228), with reliance agreements from IRBs of University of Alabama at Birmingham and
University of California, San Diego. Written informed consent provided by all participants.
'
human_subject_research:
id: aireadi:hsr:1
name: AI-READI Human Subjects Research
description: 'Study involves human subjects research with IRB approval and written informed consent
from all participants. Bioethics guidance integrated throughout study design. Community Advisory Board
of 11 persons with diversity in race and ethnicity contributes to protocol development. Ethical and
equitable data collection and management practices implemented across all three data collection sites.
IRB approval number STUDY00016228 from University of Washington with reliance agreements from University
of Alabama at Birmingham and University of California San Diego.
'
involves_human_subjects: true
informed_consent:
- id: aireadi:consent:1
name: Written informed consent
description: 'Written informed consent provided by all participants prior to study enrollment. Consent
process conducted in English. Participants must be able to speak, read, and understand English. The
consent process was developed with bioethics guidance and reviewed by the Community Advisory Board.
Participants may withdraw at any time.
'
at_risk_populations:
id: aireadi:atrisk:1
name: At-risk population protections
description: 'The dataset focuses on individuals with and without Type 2 Diabetes Mellitus (T2DM), with
intentional inclusion of historically underrepresented racial and ethnic minority groups. The study
design incorporates bioethics guidance from co-investigators specializing in bioethics and community
engagement. A Community Advisory Board of 11 persons with diversity in race and ethnicity provides
oversight. Exclusion criteria include pregnancy (protecting pregnant individuals from research burden).
De-identification procedures protect participant privacy. Controlled access requirements protect sensitive
data for populations at higher re-identification risk.
'
is_deidentified:
id: aireadi:deidentified:1
name: De-identification status
description: 'The public access dataset is de-identified, with sensitive personal health information
(5-digit zip code, detailed race/ethnicity, genetic data, past health records) moved to the controlled
access dataset. The AI-READI Data License Agreement prohibits re-identification attempts. De-identification
procedures follow applicable regulations and guidelines.
'
license_and_use_terms:
id: aireadi:license:1
name: Creative Commons Attribution Non-Commercial and AI-READI Data License
description: 'Public access data distributed under Creative Commons Attribution Non-Commercial (CC BY-NC
4.0) license. Permits others to distribute, remix, adapt, build upon this work non-commercially, and
license their derivative works on different terms, provided the original work is properly cited, appropriate
credit is given, any changes made indicated, and the use is non-commercial. Controlled access data
requires a separate data use agreement with the University of Washington as Licensor. The AI-READI
Data License Agreement prohibits clinical treatment decisions based on the data, re-identification
attempts, and sharing data with non-licensed parties. See http://creativecommons.org/licenses/by-nc/4.0/
for full CC BY-NC 4.0 license terms and https://docs.aireadi.org/ for the AI-READI specific license
terms.
'
ip_restrictions:
id: aireadi:ip:1
name: Non-commercial use restriction
description: 'The CC BY-NC 4.0 license restricts use to non-commercial purposes. Controlled access data
requires a separate data use agreement with the University of Washington. No third-party IP restrictions
beyond the licensing terms have been identified.
'
regulatory_restrictions:
id: aireadi:regulatory:1
name: HIPAA and NIH data sharing compliance
description: 'Dataset collection and sharing complies with HIPAA regulations and NIH data sharing policies
(NIH grant OT2OD032644). IRB oversight ensures compliance with human subjects research regulations
(45 CFR 46). Controlled access requirements protect sensitive health information. No export control
restrictions identified.
'
external_resources: - id: aireadi:resource:1 name: AI-READI Project Website description: Official project website with overview and resources at https://aireadi.org/ - id: aireadi:resource:2 name: AI-READI Dataset Documentation description: Comprehensive dataset documentation with version-specific guides at https://docs.aireadi.org/ - id: aireadi:resource:3 name: FAIRhub Dataset Landing Page description: Dataset repository and download portal for AI-READI data at https://fairhub.io/datasets/2 - id: aireadi:resource:4 name: Bridge2AI Program description: Parent NIH Common Fund program supporting AI-ready biomedical datasets at https://bridge2ai.org/ - id: aireadi:resource:5 name: NIH RePORTER Project Details description: Federal grant information and project details for grant 1OT2OD032644-01 at https://reporter.nih.gov/project-details/10471118 - id: aireadi:resource:6 name: Data Sharing Information description: Policies and procedures for data access and sharing at https://aireadi.org/goals/data-sharing - id: aireadi:resource:7 name: Zenodo Archive description: Additional dataset documentation and resources at https://doi.org/10.5281/zenodo.10642459 - id: aireadi:resource:8 name: Protocol Publication (BMJ Open) description: BMJ Open publication describing study design and protocol (Owsley et al. 2025) at https://doi.org/10.1136/bmjopen-2024-097449 - id: aireadi:resource:9 name: Nature Metabolism Commentary description: Overview of AI-READI approach and significance published in Nature Metabolism at https://doi.org/10.1038/s42255-024-01165-x