Diabetic Retinopathy Screening Point-of-Care Artificial Intelligence

NCT06721351 | Active Not Recruiting FDA Device

• 2 other identifiers: RHP-091323-159212825-SYH-04
• Study Type: interventional
• Target: 548
• Locations: 1 country
• Sites: 3

Brief Summary

This research study is being conducted to improve eye care by using artificial intelligence (AI) to make diabetic eye screenings faster and more accessible. AI technology mimics human decision-making, enabling computers and systems to analyze medication information. Specifically for this screening, AI examines digital images of the eye and based on that information, may identify if a participant has diabetic retinopathy. It can assist doctors in making decisions about a participant's diagnosis, treatment or care plans to improve patient care. This is a collaboration between San Ysidro Health (SYHealth), University of California, San Diego (UC San Diego), and Eyenuk. The Kaiser Permanente Augmented Intelligence in Medicine and Healthcare Initiative (AIM-HI) awarded SYHealth funds to demonstrate the value of AI technologies in diverse, real-world settings.

Conditions

Diabetic Retinopathy (DR)

Keywords

Point-of-care (POC) artificial intelligence (AI) technology for DR screening; Diabetic Retinopathy (DR) Screening; Diabetes

Outcome Measures

Primary Outcomes (8)

• DR screening completion and result

  1. Completion of DR screening. Data obtained through EHR at the time of the enrollment (baseline) and through study completion, an average of 1 year. 2. Results of DR screening: usual care specific diagnosis; intervention group defined as normal, mild-to-moderate DR), visual threatening DR or ungradable. Referral to specialist completion status and final diagnosis.

  the enrollment (baseline) and through study completion, an average of 1 year

• DR screening efficiency

  EyeArt system impact and efficiency data, number of orders submitted, screenings completed (images), number of ungradable and time of attempts, time (minutes) the participant spent in front of the camera.

  the enrollment (baseline) and through study completion, an average of 1 year

• Knowledge and attitudes about DR

  5 min-survey at baseline and 6 months. Assessment of participant knowledge and attitudes about DR (10 multiple choice question survey).

  Baseline survey at study visit and follow up survey 6-months after.

• DM self-efficacy

  5 min-survey at baseline and 6 months. Assessment of participant DM self-efficacy (seven questions using a 5-point scale from "Strongly disagree" to "Strongly agree).

  Baseline survey at study visit and follow up survey 6-months after.

• DM self-management

  5 min-survey at baseline and 6 months. Assessment of participant DM self-management ( 5-point scale from "Very difficult: I couldn't do it at all" to "Not difficult: I could do all of I).

  Baseline survey at study visit and follow up survey 6-months after.

• DR Screening Satisfaction Survey (Intervention Group)

  5 min-survey at baseline and 6 months. Assessment of participant satisfaction with POC DR screening (three questions using a 5-point scale from "Strongly disagree" to "Strongly agree, three multiple choice questions, and one open text field).

  Baseline survey at study visit and follow up survey 12-months after (at next DR screening).

• Demographic and Clinical Data

  Participant level demographics (e.g., sex assigned at birth, gender, age, race, ethnicity, marital status, employment status, insurance type etc.) and clinical data will be extracted from the electronic health record to obtain participant level information on comorbidities, medication use and compliance with quality methods and as applicable selected patient visit history.

  Intake at study 1 day visit.

• Social Determinants of Health

  Participant information on non-medical factors (e.g., socioeconomic status, employment, housing stability, food insecurity, education, social support networks, living environment, alcohol/tobacco consumption) that could influence health outcomes will be collected.

  Intake at study 1 day visit.

Study Arms (2)

Usual care

NO INTERVENTION

The usual care group will complete the DR screening with an eye care provider on a different day and at a different location. The study staff will facilitate this process for participants in the usual care group by assisting them in scheduling appointments for their routine retinal screening.

Diabetic Retinopathy Screening

EXPERIMENTAL

The intervention group will complete the DR screening using a special camera and the AI system (EyeArt®), the same day of the study visit. Participants assigned to the intervention group will also receive a retinal screening without dilation using the EyeArt® AI system; the DR screening will be completed before their medical provider visits. The results will be available immediately after the screening, allowing participants to learn about and discuss their eye health with their care provider.

Diagnostic Test: Diabetic Retinopathy screening Point of Care Artificial Intelligence

Interventions

Diabetic Retinopathy screening Point of Care Artificial Intelligence DIAGNOSTIC_TEST

Random assignment of participants to intervention and control groups minimizes confounding variables. This ensures that any observed differences in outcomes are likely due to the intervention itself and not pre-existing differences between the groups. Participants of the DRES-POCAI study will be randomized into two groups: usual care (receive a retinal screening by an optometrist) or intervention group (receive a retinal screening using a special camera and EyeArt® system, an autonomous AI-based DR screening). The randomization will occur after consenting and completing the surveys, prior to conducting the DR screening process (for those randomized to the intervention group).

Diabetic Retinopathy Screening

Eligibility Criteria

• Age: 22 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Capacity to provide informed consent. Individuals must have the capacity to understand the study information, risks, and benefits and voluntarily provide informed consent.
• Stated willingness to comply with all study procedures and availability for the duration of the study.
• Established and active patient of SYHealth-CV and KC (having a medical appointment in the last 18 months).
• Person aged 22 and older.
• Established diagnosis of DM.
• Medical appointment(s) (in-person or telehealth) scheduled during the intervention period.
• Has not completed a dilated eye exam or retinal exam in the last 11months.

You may not qualify if:

• have a prior diagnosis of DR, macular edema, or retinal vascular occlusion;
• have persistent visual Impairment in one or both eyes;
• history of ocular injections, laser treatment of the retina, or intraocular surgery (excluding cataract surgery);
• pregnant women; and
• diagnosis of mental or degenerative disease that prevents self-consent for the study.

Sponsors & Collaborators

• Centro De Salud La Comunidad De San Ysidro Inc DBA: San Ysidro Health: lead
• Eyenuk, Inc.: collaborator
• University of California, San Diego: collaborator

Study Sites (3)

San Ysidro Health Chula Vista

Chula Vista, California, 91910, United States

Location

San Ysidro Health - Comprehensive Health Center - Ocean View

San Diego, California, 92113, United States

Location

San Ysidro Health King-Chavez Health Center

San Diego, California, 92114, United States

Location

Related Publications (1)

• Diaz EA, Seifert ML, Gruning V, Stadnick NA, Lugo-Butler E, Servin AN, Rodriguez-Rosales CI, Geremia C, Ramachandra C, Bhaskaranand M, Howard D, Solis O, Velasquez S, Snook B, Tucker S, Munoz FA. Diabetic Retinopathy Screening Among Federally Qualified Health Center Patients Using Point-of-Care AI: DRES-POCAI: A Trial Protocol. JAMA Netw Open. 2025 Oct 1;8(10):e2538114. doi: 10.1001/jamanetworkopen.2025.38114.

  PMID: 41118165 DERIVED

MeSH Terms

Conditions

Diabetic Retinopathy; Diabetes Mellitus

Condition Hierarchy (Ancestors)

Retinal Diseases; Eye Diseases; Diabetic Angiopathies; Vascular Diseases; Cardiovascular Diseases; Diabetes Complications; Endocrine System Diseases; Glucose Metabolism Disorders; Metabolic Diseases; Nutritional and Metabolic Diseases

Study Officials

• Fatima Muñoz, MD, MPH

  San Ysidro Health

  PRINCIPAL INVESTIGATOR

• Nicole Stadnick, PhD

  University of California, San Diego

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: NONE
• Purpose: SCREENING
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Associate Vice President Health Support Services

Model Details: The DRES-POCAI study uses a randomized controlled, open-label, parallel superiority trial. Randomization: Participants will be randomized into two groups: usual care (receive a retinal screening by an optometrist) or intervention group (receive a retinal screening using a special camera and FDA-cleared EyeArt® system, an autonomous AI-based DR screening). Open-label Design: Blinding participants and providers to the autonomous DR screening is logistically difficult. The intervention's immediate results and potential impact on the workflow necessitate an open-label approach. Parallel Design: The parallel design allows for a clear, side-by-side comparison of outcomes between the intervention and usual care groups over time. Superiority Evaluation: The primary objective is to determine if the multi-component DRES-POCAI intervention is superior to usual care in increasing DR screenings, early detection, referrals, and patient knowledge/self-efficacy.

Study Record Dates

• First Submitted: November 20, 2024
• First Posted: December 6, 2024
• Study Start: July 27, 2024
• Primary Completion: December 31, 2025
• Study Completion: April 30, 2026
• Last Updated: November 6, 2025

Record last verified: 2025-11

Data Sharing

• IPD Sharing: Will not share

Locations

US (3)