AI-Based Screening for Glaucoma

(AI-RONA Trial)

Overseen By Dawn Matthies, PhD

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: University of Alabama at Birmingham

Disqualifiers: Declines consent, Non-English speakers

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: 3

Duration: 2-3 days

What You Need to Know Before You Apply

What is the purpose of this trial?

This trial explores an AI-based eye screening tool to detect glaucoma and other eye conditions, such as diabetic retinopathy, cataracts, and visual acuity issues. The researchers aim to determine if this new method is effective compared to standard clinical practices. Participants will undergo a simple eye check, and if results suggest potential issues, they will be referred for a full examination. The trial seeks African American or Hispanic adults over 40, non-Hispanic white adults over 50, or anyone over 18 with diabetes, a family history of glaucoma, or existing glaucoma-related issues. As an unphased trial, this study offers participants the chance to contribute to groundbreaking research that could enhance early detection and treatment of eye conditions.

Will I have to stop taking my current medications?

The trial information does not specify whether you need to stop taking your current medications.

What prior data suggests that this AI-based screening tool is safe for detecting eye conditions?

Previous studies have shown promising results for AI-based tools in checking for glaucoma. Research indicates that these computer programs can sometimes surpass humans in identifying individuals at risk for glaucoma. These AI tools quickly analyze eye images to detect high-risk patients. While these studies focus on the diagnostic accuracy of AI, they report no major safety issues, as the AI tool itself doesn't directly impact health. The screening involves taking pictures of the eyes, a simple and non-invasive process. Overall, AI-based screening is safe and well-tolerated by participants. ^{1 2 3 4 5}

Why are researchers excited about this trial?

Researchers are excited about this trial because it explores the use of AI-based screening to detect glaucoma and other eye conditions like diabetic retinopathy and cataracts. Unlike traditional methods that rely on manual eye exams, this AI approach can quickly and accurately analyze eye images, potentially catching issues earlier and more reliably. By implementing this protocol in Federally Qualified Health Centers, the trial aims to improve early detection and treatment in underserved communities, making eye care more accessible and efficient.

What evidence suggests that this AI-based screening is effective for detecting glaucoma?

Research has shown that AI-based tools for checking glaucoma are promising for early detection of eye problems. In this trial, some participants will receive AI-based glaucoma screening at Federally Qualified Health Centers (FQHCs). Studies have demonstrated that this method detects 1.6 times more glaucoma cases than traditional methods, allowing more people to receive help before serious vision impairment occurs. The AI tool also identifies issues approximately 0.8 months sooner. Overall, this suggests that AI screening may surpass regular eye exams in early problem detection. ^{3 6 7 8 9}

Who Is on the Research Team?

Cynthia Owsley, PhD

Principal Investigator

University of Alabama at Birmingham

Are You a Good Fit for This Trial?

This trial is for individuals at clinics where they might have glaucoma or other eye conditions like diabetic retinopathy and cataracts. It's designed to see if AI can help screen these issues effectively. Participants will be screened and possibly referred for further examination.

Inclusion Criteria

I am 18 or older with type 1 or type 2 diabetes.

I am African American or Hispanic and 40 years old or older.

I am over 18 and have a family history of glaucoma.

Exclusion Criteria

I am unable to communicate in English.

I choose not to sign the consent form.

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

2-3 days

1 visit (in-person)

Treatment

Participants undergo an ocular screening using AI-assisted tools to detect glaucoma, diabetic retinopathy, cataract, and visual acuity impairment

2-3 days

1 visit (in-person)

Follow-up

Participants diagnosed with conditions are referred for a comprehensive eye examination by an optometrist or ophthalmologist

up to 4 months

1 visit (in-person)

Satisfaction Survey

Participants and physicians complete a survey on their satisfaction with the screening program

1 day

What Are the Treatments Tested in This Trial?

Interventions

• AI-based Glaucoma Screening

Trial Overview The study tests an AI-assisted screening tool called AI-RONA for detecting glaucoma and other eye conditions in health centers. It compares detection rates, follow-up adherence, referral rates, cost-effectiveness, and satisfaction with traditional methods.

How Is the Trial Designed?

Group I: The Federally Qualified Health Centers (FQHCs) Experimental Treatment 1 Intervention

Eight FQHCs will participate in this project. Four FQHCs will implement a glaucoma screening protocol and a protocol for detecting diabetic retinopathy, cataract, and visual acuity impairment, while the other four will be standard of care without the above screening protocol.

Group II: Primary Standard of Care Active Control 1 Intervention

Primary care provider asks participants if they are having symptoms or problems with their eyes or vision.

Who Is Running the Clinical Trial?

University of Alabama at Birmingham

Lead Sponsor

Trials

1,677

Recruited

2,458,000+

Centers for Disease Control and Prevention

Collaborator

Trials

902

Recruited

25,020,000+

University of California, San Diego

Collaborator

Trials

1,215

Recruited

1,593,000+

Citations

1. clinicaltrials.gov clinicaltrials.gov/study/NCT06629649

Implementing AI-based Glaucoma Screening Within ... Participants will: Undergo an ocular screening whose goal is to detect glaucoma, diabetic retinopathy, cataract, and/or impairment in visual acuity. If the ...

2. valueinhealthjournal.com valueinhealthjournal.com/article/S1098-3015(25)02410-6/fulltext

The Cost-Effectiveness of an Artificial Intelligence-Based ... Results. AI screening identified glaucoma earlier than opportunistic methods, detecting 1.60 times more cases and reducing visual impairment by ...

3. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC11508556/

Artificial Intelligence and Advanced Technology in Glaucoma This review explores the current landscape of AI applications in the personalized management of glaucoma patients, highlighting advancements, challenges, and ...

4. sciencedirect.com sciencedirect.com/science/article/pii/S1098301525024106

The Cost-Effectiveness of an Artificial Intelligence-Based ... Results. AI screening identified glaucoma earlier than opportunistic methods, detecting 1.60 times more cases and reducing visual impairment by 0.8 months per ...

5. nature.com nature.com/articles/s41746-025-01473-w

A hybrid multi model artificial intelligence approach for ... We present an AI-based Glaucoma Screening (AI-GS) network comprising six lightweight deep learning models (total size: 110 MB) that analyze fundus images.

6. aao.org aao.org/newsroom/news-releases/detail/artificial-intelligence-guided-glaucoma-screening-

Artificial Intelligence-Guided Glaucoma Screening Shows ... It shows that a machine learning algorithm was more accurate than trained human graders in identifying patients at risk for glaucoma.

7. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC11946806/

Artificial Intelligence Models to Identify Patients at High Risk ... This study sought to develop artificial intelligence models that use self-reported health data from surveys to prescreen patients at high risk for glaucoma.

8. ophthalmologyscience.org ophthalmologyscience.org/article/S2666-9145(25)00049-1/fulltext

Comparison of Deep Learning and Clinician Performance ... Our findings highlight potential benefits of adopting AI-based strategies to improve the reproducibility, timeliness, and scalability of glaucoma care, which ...

9. sciencedirect.com sciencedirect.com/science/article/pii/S2666914524002070

Artificial Intelligence Models to Identify Patients with High ... Machine and deep learning models were able to use the extensive systematic data within EHR to identify individuals with glaucoma, without the need for ...