Artificial Intelligence for Diabetic Retinopathy

(DRES POCAI Trial)

Recruiting at 1 trial location

Overseen By Sonia Tucker, MD, MBA

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: Centro De Salud La Comunidad De San Ysidro Inc DBA: San Ysidro Health

Disqualifiers: Diabetic retinopathy, Macular edema, Retinal vascular occlusion, others

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

Compensation: Varies

Number of Visits: 8

848 Participants Needed

What You Need to Know Before You Apply

What is the purpose of this trial?

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.

Will I have to stop taking my current medications?

The trial information does not specify whether you need to stop taking your current medications. It seems focused on eye screenings rather than medication changes.

Is the AI-based screening for diabetic retinopathy safe for humans?

The AI-based screening for diabetic retinopathy appears to be safe and well accepted by patients, with high satisfaction rates and no reported safety concerns in the studies reviewed. ^{1 2 3 4 5}

How does the Diabetic Retinopathy Screening Point-of-Care Artificial Intelligence treatment differ from other treatments for diabetic retinopathy?

This treatment uses artificial intelligence to screen for diabetic retinopathy by analyzing images of the retina, offering a high level of accuracy and the ability to predict disease progression, which is different from traditional methods that rely on manual evaluation by eye care professionals. ^{1 6 7 8 9}

What data supports the effectiveness of the treatment Diabetic Retinopathy Screening Point-of-Care Artificial Intelligence?

Research shows that artificial intelligence (AI) can effectively screen for diabetic retinopathy (a diabetes-related eye condition) with high sensitivity, meaning it can accurately identify those who have the condition. However, it also has low specificity, which means it may incorrectly refer some people who don't have the condition for further testing. ^{1 6 9 10 11}

Who Is on the Research Team?

Fatima A Muñoz, MD,MPH

Principal Investigator

San Ysidro Health

Nicole Stadnick, PhD

Principal Investigator

University of California, San Diego

Are You a Good Fit for This Trial?

This trial is for individuals with diabetic retinopathy or herpes simplex retinopathy. Participants will have their eye images analyzed by AI to identify signs of disease. The study aims to make eye screenings quicker and more widely available.

Inclusion Criteria

I have been diagnosed with diabetes.

Established and active patient of SYHealth-CV and KC (having a medical appointment in the last 18 months).

I have a medical appointment scheduled during the study period.

Exclusion Criteria

I do not have a mental condition that prevents me from consenting to the study.

I have had diabetic retinopathy, macular edema, or a blocked blood vessel in my eye.

Pregnant women.

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

1 day

1 visit (in-person)

Intervention

Participants undergo DR screening using the EyeArt® AI system, with results integrated into the EHR for immediate discussion with their primary care provider.

1 day

1 visit (in-person)

Follow-up

Participants are monitored for DR screening completion and results, as well as knowledge and attitudes about DR, DM self-efficacy, and DM self-management.

12 months

Follow-up surveys at 6 and 12 months

What Are the Treatments Tested in This Trial?

Interventions

• Diabetic Retinopathy Screening Point-of-Care Artificial Intelligence

Trial Overview The intervention being tested is an artificial intelligence system that screens for diabetic retinopathy by analyzing digital images of the eyes. This study evaluates the effectiveness of AI in aiding diagnosis and treatment plans.

How Is the Trial Designed?

Group I: Diabetic Retinopathy Screening Experimental Treatment 1 Intervention

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.

Group II: Usual care Active Control 1 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.

Who Is Running the Clinical Trial?

Centro De Salud La Comunidad De San Ysidro Inc DBA: San Ysidro Health

Lead Sponsor

Trials

1

Recruited

850+

University of California, San Diego

Collaborator

Trials

1,215

Recruited

1,593,000+

Eyenuk, Inc.

Industry Sponsor

Trials

6

Recruited

2,200+

Published Research Related to This Trial

The IDx autonomous diabetic retinopathy screening program demonstrated a perfect sensitivity of 100% in detecting referable diabetic retinopathy, but had a lower specificity of 82%, leading to a high rate of unnecessary referrals.

With a positive predictive value of only 19%, the program may overwhelm ophthalmologists and primary care clinics, suggesting a need for improved AI systems that can provide better specificity and detailed lesion annotations to enhance patient management and treatment adherence.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

The Real-World Impact of Artificial Intelligence on Diabetic Retinopathy Screening in Primary Care. Cuadros, J.[2021]

The automated diabetic retinopathy screening tool, DART, demonstrated high sensitivity (94.6%) and a strong negative predictive value (98.1%) in analyzing ocular fundus photographs from 1123 diabetic eye exams, indicating its effectiveness in identifying potential cases of diabetic retinopathy.

With a specificity of 74.3% and an area under the ROC curve of 0.915, DART shows promise for implementation in Chile's national diabetic retinopathy screening program, suggesting it can be a reliable option in diverse healthcare settings.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Clinical validation of an artificial intelligence-based diabetic retinopathy screening tool for a national health system. Arenas-Cavalli, JT., Abarca, I., Rojas-Contreras, M., et al.[2023]

In a study involving 827 participants screened for diabetic retinopathy (DR) using AI, 33.2% were referred for follow-up, demonstrating the AI's effectiveness in identifying cases needing further evaluation.

The AI system showed a high sensitivity of 92% and specificity of 85% for detecting referable DR compared to human grading, indicating that AI can be a reliable tool for DR screening in clinical settings.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Feasibility and acceptance of artificial intelligence-based diabetic retinopathy screening in Rwanda. Whitestone, N., Nkurikiye, J., Patnaik, JL., et al.[2023]

The AI-based screening tool EyeWisdom®DSS demonstrated high sensitivity (91.0%) and good specificity (81.3%) for detecting diabetic retinopathy (DR) in a study of 549 type 2 diabetes patients, indicating its effectiveness as a screening method.

EyeWisdom®MCS was particularly effective at identifying patients without DR, with a specificity of 92.4%, suggesting that AI screening can be a valuable resource in areas with limited access to eye care.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Efficacy of artificial intelligence-based screening for diabetic retinopathy in type 2 diabetes mellitus patients. Pei, X., Yao, X., Yang, Y., et al.[2022]

A study involving 6146 patients showed that using AI for non-mydriatic fundus photography in diabetic retinopathy screening has a high sensitivity of 97.3% and a kappa coefficient of 0.75, indicating strong agreement with ophthalmic diagnoses.

The AI's consistency with fluorescein angiography was moderate, with a kappa coefficient of 0.53 and a coincidence rate of 66.9%, suggesting that AI can effectively assist in early detection of diabetic retinopathy, which is crucial for preventing blindness.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Application and observation of artificial intelligence in clinical practice of fundus screening for diabetic retinopathy with non-mydriatic fundus photography: a retrospective observational study of T2DM patients in Tianjin, China. Hao, Z., Xu, R., Huang, X., et al.[2022]

The EyeArt system, an automated AI technology, demonstrated high diagnostic efficacy for detecting referral-warranted diabetic retinopathy (DR) with a sensitivity of 91.3% and specificity of 91.1% across 850,908 fundus images from 101,710 patient visits.

For encounters with potentially treatable DR, the EyeArt system achieved an impressive sensitivity of 98.5%, indicating its effectiveness in identifying patients who need urgent care, making it a valuable tool for healthcare providers in managing diabetic eye health.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

The Value of Automated Diabetic Retinopathy Screening with the EyeArt System: A Study of More Than 100,000 Consecutive Encounters from People with Diabetes. Bhaskaranand, M., Ramachandra, C., Bhat, S., et al.[2020]

The AI-based screening tool for Diabetic Retinopathy (DR) demonstrated exceptional performance, achieving a sensitivity of 99.21% and specificity of 97.59% on the Kaggle dataset, indicating its high accuracy in identifying referable DR.

In real-world primary care settings, the tool maintained strong performance with a sensitivity of 92.3% and specificity of 94.8%, suggesting it is effective for early detection and could significantly aid in preventing blindness from DR.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Automated diabetic retinopathy screening for primary care settings using deep learning. Bhuiyan, A., Govindaiah, A., Deobhakta, A., et al.[2022]

The global prevalence of diabetes is projected to reach 700 million individuals in the next 25 years, increasing the risk of vision loss from diabetic eye disease and highlighting the need for innovative detection tools.

Artificial intelligence (AI) has shown great promise in detecting diabetic retinopathy (DR) by analyzing fundus photographs, using machine learning to grade DR and potentially predict its progression, which could help alleviate the burden on eye care professionals.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Artificial Intelligence in the assessment of diabetic retinopathy from fundus photographs. Gilbert, MJ., Sun, JK.[2021]

Citations

1. United States pubmed.ncbi.nlm.nih.gov

The Real-World Impact of Artificial Intelligence on Diabetic Retinopathy Screening in Primary Care. [2021]

2. England pubmed.ncbi.nlm.nih.gov

Clinical validation of an artificial intelligence-based diabetic retinopathy screening tool for a national health system. [2023]

3. England pubmed.ncbi.nlm.nih.gov

Feasibility and acceptance of artificial intelligence-based diabetic retinopathy screening in Rwanda. [2023]

4. Ireland pubmed.ncbi.nlm.nih.gov

Efficacy of artificial intelligence-based screening for diabetic retinopathy in type 2 diabetes mellitus patients. [2022]

5. United States pubmed.ncbi.nlm.nih.gov

Application and observation of artificial intelligence in clinical practice of fundus screening for diabetic retinopathy with non-mydriatic fundus photography: a retrospective observational study of T2DM patients in Tianjin, China. [2022]

6. United States pubmed.ncbi.nlm.nih.gov

The Value of Automated Diabetic Retinopathy Screening with the EyeArt System: A Study of More Than 100,000 Consecutive Encounters from People with Diabetes. [2020]

7. England pubmed.ncbi.nlm.nih.gov

Feasibility and patient acceptability of a novel artificial intelligence-based screening model for diabetic retinopathy at endocrinology outpatient services: a pilot study. [2019]

8. United States pubmed.ncbi.nlm.nih.gov

Artificial Intelligence and Diabetic Retinopathy: AI Framework, Prospective Studies, Head-to-head Validation, and Cost-effectiveness. [2023]

9. Australia pubmed.ncbi.nlm.nih.gov

Development of an artificial intelligence system to classify pathology and clinical features on retinal fundus images. [2022]

10. Netherlands pubmed.ncbi.nlm.nih.gov

Automated diabetic retinopathy screening for primary care settings using deep learning. [2022]

11. England pubmed.ncbi.nlm.nih.gov

Artificial Intelligence in the assessment of diabetic retinopathy from fundus photographs. [2021]