Artificial Intelligence for Diagnosing Diabetic Retinopathy in Primary Care

NCT07236879 | Recruiting

• 1 other identifier: 2024-0238
• Study Type: interventional
• Target: 922
• Locations: 1 country
• Sites: 1

Brief Summary

This is a clinical trial to evaluate the effects of universal screening for diabetic retinopathy (DR) and diabetic macular edema (DME) using artificial intelligence (AI) in the interpretation of fundus photographs obtained by trained nursing assistant using a portable fundus camera in a primary care setting, compared with images obtained by the same method, but interpreted by ophthalmologists.

Conditions

Diabetic Retinopathy

Keywords

screening; diabetic retinopathy; artificial intelligence

Outcome Measures

Primary Outcomes (1)

• Number of appropriate referrals to ophthalmologist

  Appropriate referrals: asymptomatic patients with moderate to severe nonproliferative DR, proliferative DR, significant macular edema, and uninterpretable exams. This data will be obtained by reviewing the medical records of ophthalmological in-person consults of included patients.

  Through study completion, an average of 1 year

Secondary Outcomes (3)

• Number of patients referred for laser sessions

  Through study completion, an average of 1 year

• Number of pharmacological intraocular treatment

  Through study completion, an average of 1 year

• Referral failure

  After study completion, an average of 15 months

Study Arms (2)

RDIA group

EXPERIMENTAL

The proposed intervention is the provision of universal screening for DR with retinography performed on a mobile fundus camera under mydriasis supported by a computer program in adults with diabetes mellitus; based on the diagnosis made by the computer program, patients will be classified as having referable DR or not, and referral to a specialist will be based on this classification.

Diagnostic Test: Mobile retinography interpreted by artificial intelligence

RDOF group

ACTIVE COMPARATOR

The proposed control is the provision of universal screening for DR in adults with diabetes mellitus with retinography performed on a mobile fundus camera under mydriasis and with obtained images being interpreted remotely by ophthalmologists; based on the diagnosis made by the ophthalmologist, patients will be classified as having referable DR or not, and referral to a specialist will be based on this classification.

Diagnostic Test: Mobile retinography interpreted by ophthalmologists

Interventions

Mobile retinography interpreted by artificial intelligence DIAGNOSTIC_TEST

All participants will undergo mobile retinal photography in primary care by a trained nursing assistant. If randomized to RDIA group, their photos will be analyzed by artificial intelligence.

RDIA group

Mobile retinography interpreted by ophthalmologists DIAGNOSTIC_TEST

All participants will undergo mobile retinal photography in primary care by a trained nursing assistant. If randomized to RDOF group, their photos will be interpreted remotely by ophthalmologists.

RDOF group

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Adults (\> 18 years old) diagnosed with diabetes mellitus who agree to participate in the study.

You may not qualify if:

• Any contraindication for pharmacological mydriasis (such as knowledge of having closed-angle glaucoma, pregnancy).
• Life expectancy less than 6 months

Sponsors & Collaborators

• Hospital de Clinicas de Porto Alegre: lead
• Fundação de Amparo à Pesquisa do Estado de São Paulo: collaborator
• Fundação de Amparo à Pesquisa do Estado do Rio Grande do Sul, Brazil: collaborator
• TelessaúdeRS / UFRGS: collaborator

Study Sites (1)

Hospital de Clínicas de Porto Alegre

Porto Alegre, Rio Grande do Sul, 90035-903, Brazil

RECRUITING

Related Publications (3)

• Chagas TA, Dos Reis MA, Leivas G, Santos LP, Gossenheimer AN, Melo GB, Malerbi FK, Schaan BD. Prevalence of diabetic retinopathy in Brazil: a systematic review with meta-analysis. Diabetol Metab Syndr. 2023 Mar 2;15(1):34. doi: 10.1186/s13098-023-01003-2.

  PMID: 36864478 BACKGROUND

• Schneiders J, Telo GH, Lavinsky D, Dos Reis MA, Correa BG, Schaan BD. Organizational intervention to improve access to retinopathy screening for patients with diabetes mellitus: health care service improvement project in a tertiary public hospital. Prim Care Diabetes. 2023 Aug;17(4):354-358. doi: 10.1016/j.pcd.2023.05.007. Epub 2023 Jun 14.

  PMID: 37328386 BACKGROUND

• Dos Reis MA, Kunas CA, da Silva Araujo T, Schneiders J, de Azevedo PB, Nakayama LF, Rados DRV, Umpierre RN, Berwanger O, Lavinsky D, Malerbi FK, Navaux POA, Schaan BD. Advancing healthcare with artificial intelligence: diagnostic accuracy of machine learning algorithm in diagnosis of diabetic retinopathy in the Brazilian population. Diabetol Metab Syndr. 2024 Aug 29;16(1):209. doi: 10.1186/s13098-024-01447-0.

  PMID: 39210394 BACKGROUND

MeSH Terms

Conditions

Diabetic Retinopathy

Condition Hierarchy (Ancestors)

Retinal Diseases; Eye Diseases; Diabetic Angiopathies; Vascular Diseases; Cardiovascular Diseases; Diabetes Complications; Diabetes Mellitus; Endocrine System Diseases

Study Officials

• Beatriz D Schaan, MD, PhD

  Hospital de Clínicas de Porto Alegre

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Beatriz D Schaan, MD, PhD

CONTACT

+55 51 3359-8127; bschaan@hcpa.edu.br

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: QUADRUPLE
• Who Masked: PARTICIPANT, CARE PROVIDER, INVESTIGATOR, OUTCOMES ASSESSOR
• Purpose: SCREENING
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Model Details: The AID-DR trial is designed as a randomized, controlled, double-blinded, non-inferiority trial with two parallel groups and a primary endpoint of adequate referrals to specialized care. Randomization will be performed in a 1:1 ratio using variable block sizes.

Study Record Dates

• First Submitted: June 4, 2025
• First Posted: November 19, 2025
• Study Start: August 8, 2024
• Primary Completion (Estimated): August 1, 2026
• Study Completion (Estimated): December 1, 2026
• Last Updated: November 19, 2025

Record last verified: 2025-11

Data Sharing

• IPD Sharing: Will not share

Locations

BR (1)