Abstract

The ability to understand and affect the course of complex, multi-system diseases like diabetes has been limited by a lack of well-designed, high-quality and large multimodal datasets. The NIH Bridge2AI AI-READI project (aireadi.org) aims to address this shortfall by generating an AI-ready dataset to support AI discoveries in type 2 diabetes mellitus (T2DM). This manual of procedures provides a detailed description of the AI-READI protocol.

Competing Interest Statement

All authors have completed the ICMJE uniform disclosure form at www.icmje.org/coi_disclosure.pdf and declare: All authors had financial support from the NIH for the submitted work; DSM, GM, JCE, and JPO, report no competing interests; AYL has received funding from the NIH and Research to Prevent Blindness, personal fees from Astellas, Genentech, Johnson and Johnson, Alcon and Apellis, and non-financial support from iCareWorld, Topcon, Carl Zeiss Meditec, Optomed, Heidelberg Engineering, Microsoft, Amazon and Meta; CO has received funding from NIH, Roche and Boehringer Ingelheim and consultant fees from Johnson & Johnson, Sanofi and Roche; CSL has received funding from NIH, Alzheimers Disease Drug Discovery Foundation, Gates Ventures and Research to Prevent Blindness; LMZ has received funding from NEI, NIH, The Glaucoma Foundation, Heidelberg Engineering, DRCR Retina Network/JAEB Center for Health Research and The Krupp Foundation, non-financial support from Optomed, ICare, Topcon, Heidelberg Engineering, Carl Zeiss Meditec and Optovue/Visionix, travel support from EssilorLuxottica, and is co-founder, inventor, board member and equity holder for AISight Health, Inc.; SLB has received funding from NIH, University of California Office of the President and Research to Prevent Blindness, consultant fees from Topcon, and non-financial support from Optomed.

Funding Statement

This work was supported by the National Institutes of Health (NIH) grants OT2OD032644, P30DK035816 and UL1TR003096 and Research to Prevent Blindness.

Author Declarations

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

The details of the IRB/oversight body that provided approval or exemption for the research described are given below:

IRB of the University of Washington, Seattle, gave ethical approval for this work (FWA #00006878).

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.

Yes

Data Availability

The data collected in this study is available to researchers through a public access or a controlled access database, depending on the variables requested. A licensing process is required for access and is described at https://aireadi.org/

https://aireadi.org/

16. Abbreviation GlossaryAIArtificial IntelligenceAPIApplication Programming InterfaceBCVABest-Corrected Visual AcuityBEDBrowser Extensible Data format:BIDS (Brain Imaging Data Structure)standards used for organizing neuroimaging (mRIs) and behavioral data.CES-D-10Center of Epidemiologic Studies Depression Scale, 10-item versionCRCClinical Research CoordinatorCRUClinical Research UnitCGMContinuous Glucose MonitoringDICOMDigital Imaging and Communications in Medicine: standards used for communication and management of medical imaging information and data. Will be used for retinal imaging.EHRElectronic Health Record:EKG/ECGElectrocardiogram: Device that records electrical signals from the heart, shown as wavesETDRSEarly Treatment Diabetic Retinopathy Study: test used for visual acuity; based on Sloan lettersEVAElectronic Visual AcuityFAIRFindable, Accessible, Interoperable, Reusable Data: High level principles for making digital research objects reusable for humans and machines. Progressively adopted by all stakeholders. Fairhub.io: open-source, cloud-based free platform for preparing, sharing, and accessing AI-READI datasets.FLIOFluorescence Lifetime Imaging OphthalmoscopyIRBInstitutional Review Board:LOINCLogical Observation Identifiers, Names and Codes: International standard for identifying health measurements, observations and documents. It is one of several designated standards for use in the U.S. Federal Government system for the electronic exchange of clinical health information.MLMachine LearningMoCAMontreal Cognitive Assessment: A brief, 30-question test that helps detect mild cognitive impairmentNIHNational Institute of HealthOCTOptical Coherence Tomography: cross-sectional pictures of the retina, allowing for the analysis of retina layers and retinal thickness. Used to view anatomical structure.OCTA (Optical Coherence Tomography Angiography)sequential scans that detect and illustrate movement of blood/particles in the posterior eye. Used to view vascular structure.ODRight eyeOMOPObservational Medical Outcomes Partnership Data Model: standards used for clinical information, research visits, and serological data.ONHOptic Nerve HeadOSLeft eyeOUBoth eyesPAID-5Problem Areas In Diabetesicense-free collection of standardized measuremvalidated questionnaire that queries for diabetes-related impact on lifestylePhenX Toolkita license-free collection of standardized measurement protocols for enhancing biomedical and clinical research.PHIHIPAA protected Personal Health InformationREDCapResearch Electronic Data Capture: a secure, web-based platform for managing surveys and research dataSDOHSocial Determinants of HealthT2DMType 2 Diabetes MellitusUABUniversity of Alabama at BirminghamUCSDUniversity of California San DiegoUWUniversity of Washington