Leveraging Artificial Intelligence to Prevent Vision Loss From Diabetes

Multicenter National Parallel Cluster Randomized Controlled Superiority Trial Comparing an Artificial Intelligence-Based Screening Strategy to Usual Care for Improving Eye-Care Follow-Up Among Patients With Diabetes (AI-BRIDGE Trial)

This pragmatic clinical trial is being conducted to test the effectiveness of AI-BRIDGE (Artificial Intelligence-Based point of caRe, Incorporating Diagnosis, SchedulinG, and Education), in improving screening and follow-up eye care compared to usual-care among patients with diabetes across 8 primary care clinics. AI-BRIDGE is an implementation program which includes an autonomous AI-based protocol that provides screening for diabetic retinopathy (DR) disease at primary care visits, as well as patient education on disease and, if a patient screens positive for referable DR or has insufficient quality image, or image unobtainable due to other technical issues, or does not get AI-screening for any reason, assistance with scheduling an in-person, follow-up eye-care visit.

Study Overview

• Status: Not yet recruiting
• Conditions: Diabetes Mellitus; Diabetic Retinopathy
• Intervention / Treatment: Other: Educational Materials; Other: AI-BRIDGE

Detailed Description

This study is a parallel cluster randomized clinical trial to determine whether AI-BRIDGE, an autonomous AI-based protocol of screening for DR, improves DR screening and follow-up rates compared to usual care. In this study, DR screening refers to the detection of DR either via referral of patients for an eye-care appointment with an eye-care provider in usual-care or via point-of-care AI-based DR screening for patients in AI-BRIDGE. The trial will be conducted across 8 clinics from four health systems that are Federally Qualified Health Centers. Each clinic will be randomly assigned to either usual care or the AI-BRIDGE intervention.

Randomization is done at the clinic level in this study. One of the two clinics within each of the four health systems will be randomly selected to be in the AI-BRIDGE arm (i.e., a total of four clinics will use AI-BRIDGE during the intervention period) and the other clinics will be in the control arm (i.e., a total of four clinics will be in usual care).

Primary Objective:

Compare the proportion of patients who follow-up with recommended eye care in the AI-BRIDGE and usual-care arms within 6 months of the recommendation.

Secondary Objective:

Compare the proportion of patients who complete DR screening, defined as: (AI-BRIDGE) an AI-interpretable image obtained at the primary care visit; or, for patients who did not complete AI screening or did not start AI-screening, an in-person screening eye care visit completed within 6 months of the primary care visit; (Usual-care) an in-person screening eye care visit completed within 6 months of the primary care visit.

• Study Type: Interventional
• Enrollment (Estimated): 6900
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Mozhdeh Bahrainian; Phone Number: 608-262-9955; Email: bahrainian@wisc.edu
• Study Contact Backup: Name: Roomasa Channa; Email: rchanna@wisc.edu

Study Locations

• United States
  • Wisconsin
    • Madison, Wisconsin, United States, 53792
      • UW School of Medicine and Public Health

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

Description

Clinics Inclusion Criteria:

• Clinic must be from a health system with at least two clinics that meet eligibility criteria and will agree to join.
• Number of unique patients with diabetes should be >550 over any continuous 15-month period prior to the clinic providing a letter of support to participate in the trial.
• No point-of-care screening system in use for DR.
• Have an electronic health record to track patient data and agree to share limited data set as requested.
• Have a member of the clinical team who can commit to serving as the clinic champion for this study.
• Have the IT infrastructure to deploy an artificial-intelligence-based eye camera in the clinic.

Patient Inclusion Criteria:

• Diagnosis of type 1 or 2 diabetes
• No known diabetic retinopathy
• No diabetic retinopathy screening in the past 12 months

Patient Exclusion Criteria:

• Have a documented DR screening in the electronic health record within 12 months of the date of the primary care visit
• Contraindication includes diagnosed with macular edema, severe non-proliferative retinopathy, proliferative retinopathy, radiation retinopathy, or retinal vein occlusion
• Pregnant

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Health Services Research
• Allocation: Randomized
• Interventional Model: Sequential Assignment
• Masking: None (Open Label)

Number of Arms

8

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Active Comparator: Health System 1: Usual Care plus Education; 4 month period of usual care screening then randomized to a 15-month period of usual care. Participants in usual care will receive educational material about diabetic retinopathy.	Other: Educational Materials; Participants in the Usual Care arm will receive educational materials about diabetic retinopathy during the intervention period.
Experimental: Health System 1: AI-BRIDGE Clinic; 4 month period of usual care screening then randomized to a 15-month period of AI-based eye screening program called AI-Based point of caRe, Incorporating Diagnosis, SchedulinG, and Education (AI-BRIDGE).	Other: AI-BRIDGE; AI-BRIDGE intervention includes (1) acquisition of eye photos and autonomous (i.e. without human oversight) AI-based identification of referable or non-referable DR or insufficient image at the primary care clinic, (2) provision of patient educational material identical to that provided to the usual-care group, and (3) clinic champion-led assistance with scheduling eye-care follow-up visits for patients with referable DR or has insufficient quality image, or image unobtainable due to other technical issues, or does not get AI-screening for any reason.; Other Names: Artificial Intelligence-Based point of caRe, Incorporating Diagnosis, SchedulinG, and Education
Active Comparator: Health System 2: Usual Care plus Education; 4 month period of usual care screening then randomized to a 15-month period of usual care. Participants in usual care will receive educational material about diabetic retinopathy.	Other: Educational Materials; Participants in the Usual Care arm will receive educational materials about diabetic retinopathy during the intervention period.
Experimental: Health System 2: AI-BRIDGE Clinic; 4 month period of usual care screening then randomized to a 15-month period of AI-based eye screening program called AI-Based point of caRe, Incorporating Diagnosis, SchedulinG, and Education (AI-BRIDGE).	Other: AI-BRIDGE; AI-BRIDGE intervention includes (1) acquisition of eye photos and autonomous (i.e. without human oversight) AI-based identification of referable or non-referable DR or insufficient image at the primary care clinic, (2) provision of patient educational material identical to that provided to the usual-care group, and (3) clinic champion-led assistance with scheduling eye-care follow-up visits for patients with referable DR or has insufficient quality image, or image unobtainable due to other technical issues, or does not get AI-screening for any reason.; Other Names: Artificial Intelligence-Based point of caRe, Incorporating Diagnosis, SchedulinG, and Education
Active Comparator: Health System 3: Usual Care plus Education; 4 month period of usual care screening then randomized to a 15-month period of usual care. Participants in usual care will receive educational material about diabetic retinopathy.	Other: Educational Materials; Participants in the Usual Care arm will receive educational materials about diabetic retinopathy during the intervention period.
Experimental: Health System 3: AI-BRIDGE Clinic; 4 month period of usual care screening then randomized to a 15-month period of AI-based eye screening program called AI-Based point of caRe, Incorporating Diagnosis, SchedulinG, and Education (AI-BRIDGE).	Other: AI-BRIDGE; AI-BRIDGE intervention includes (1) acquisition of eye photos and autonomous (i.e. without human oversight) AI-based identification of referable or non-referable DR or insufficient image at the primary care clinic, (2) provision of patient educational material identical to that provided to the usual-care group, and (3) clinic champion-led assistance with scheduling eye-care follow-up visits for patients with referable DR or has insufficient quality image, or image unobtainable due to other technical issues, or does not get AI-screening for any reason.; Other Names: Artificial Intelligence-Based point of caRe, Incorporating Diagnosis, SchedulinG, and Education
Active Comparator: Health System 4: Usual Care plus Education; 4 month period of usual care screening then randomized to a 15-month period of usual care. Participants in usual care will receive educational material about diabetic retinopathy.	Other: Educational Materials; Participants in the Usual Care arm will receive educational materials about diabetic retinopathy during the intervention period.
Experimental: Health System 4: AI-BRIDGE Clinic; 4 month period of usual care screening then randomized to a 15-month period of AI-based eye screening program called AI-Based point of caRe, Incorporating Diagnosis, SchedulinG, and Education (AI-BRIDGE).	Other: AI-BRIDGE; AI-BRIDGE intervention includes (1) acquisition of eye photos and autonomous (i.e. without human oversight) AI-based identification of referable or non-referable DR or insufficient image at the primary care clinic, (2) provision of patient educational material identical to that provided to the usual-care group, and (3) clinic champion-led assistance with scheduling eye-care follow-up visits for patients with referable DR or has insufficient quality image, or image unobtainable due to other technical issues, or does not get AI-screening for any reason.; Other Names: Artificial Intelligence-Based point of caRe, Incorporating Diagnosis, SchedulinG, and Education

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Proportion of Participants Who Follow Up With Recommended Eye Care	Proportion of patients who follow-up with recommended eye care in the AI-BRIDGE and usual-care arms within 6 months of the recommendation.	up to 6 months

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Proportion of patients who complete DR screening	Proportion of patients who complete DR screening, defined as: (AI-BRIDGE) an AI-interpretable image obtained at the primary care visit; or, for patients who did not complete AI screening or did not start AI-screening, an in-person screening eye care visit completed within 6 months of the primary care visit; (Usual-care) an in-person screening eye care visit completed within 6 months of the primary care visit.	up to 6 months

Other Outcome Measures

Outcome Measure	Measure Description	Time Frame
Level of Diabetic Retinopathy	The rate of diabetic retinopathy, count of unique diabetic retinopathy diagnosis divided by count of all enrolled patients, stratified by intervention, intervention and race and ethnicity groups, and intervention, race and ethnicity group, and clinic.	up to 6 months

Collaborators and Investigators

• Sponsor: University of Wisconsin, Madison
• Collaborators: National Eye Institute (NEI)
• Investigators: Principal Investigator: Roomasa Channa, UW School of Medicine and Public Health

Study record dates

Study Major Dates

• Study Start (Estimated): October 1, 2026
• Primary Completion (Estimated): May 1, 2030
• Study Completion (Estimated): May 1, 2030

Study Registration Dates

• First Submitted: December 26, 2024
• First Submitted That Met QC Criteria: January 7, 2025
• First Posted (Actual): January 8, 2025

Study Record Updates

• Last Update Posted (Actual): September 1, 2026
• Last Update Submitted That Met QC Criteria: August 27, 2026
• Last Verified: August 1, 2026

More Information

Terms related to this study

• Keywords: Artificial Intelligence; pragmatic trial; AI; cluster randomized trial; diabetic eye disease; eye screening
• Additional Relevant MeSH Terms: Endocrine System Diseases; Vascular Diseases; Cardiovascular Diseases; Metabolic Diseases; Glucose Metabolism Disorders; Eye Diseases; Diabetic Angiopathies; Diabetes Complications; Retinal Diseases; Nutritional and Metabolic Diseases; Diabetic Retinopathy; Diabetes Mellitus; Organization and Administration; Health Services Administration; Socioeconomic Factors; Population Characteristics; Educational Status; Appointments and Schedules
• Other Study ID Numbers: 2026-0446; A536000 (Other Identifier: UW Madison); 2024-0030 (Other Identifier: UW Madison); 1R01EY035994 (U.S. NIH Grant/Contract); Protocol Version 6/12/26 (Other Identifier: UW Madison)

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: YES

IPD Plan Description

The trial protocol and SAP will be publicly accessible through the Harvard Dataverse, where study protocols, analysis code, and related project documentation will be deposited and assigned DOIs.

In addition, summary protocol information, and aggregate trial data, along with related metadata, will be available on ClinicalTrials.gov in accordance with clinical trial reporting requirements.

• IPD Sharing Time Frame: Data from this study may be requested from other researchers up to 7 years after the completion of the primary outcome by contacting Dr. Roomasa Channa, the PI of this study.
• IPD Sharing Supporting Information Type: STUDY_PROTOCOL; SAP; ICF

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No