ACCESS 2: AI for pediatriC diabetiC Eye examS Study 2
For patients and families
In plain language
An automatic summary of structured registry data. It is an orientation aid, not a substitute for the official protocol or a physician assessment.
- What is being studied
- The protocol lists: Point of Care Autonomous AI diabetic retinopathy exam.
- Who it may be relevant to
- Registry conditions: Type 1 Diabetes, Type 2 Diabetes, Cystic Fibrosis-related Diabetes. Basic parameters: 8 years — 21 years · All.
- What needs checking
- Age, condition and sex are only basic indicators. Prior treatment, laboratory values and other mandatory requirements appear in the eligibility criteria below.
- Where it takes place
- United States
- Next step
- Save the trial, show it to the treating physician, and confirm current recruitment with the study center. Costs, documents and travel →
Unsure about the terms? Read our patient guide →
Official title
Implementing Digital Retinal Exams Into Comprehensive Pediatric Diabetes Care
Overview
The purpose of this study is to determine if use of a nonmydriatic fundus camera using autonomous artificial intelligence software at the point of care increases the proportion of underserved youth with diabetes screened for diabetic retinopathy, and to determine the diagnostic accuracy of the autonomous AI system in detecting diabetic retinopathy from retinal images of youth with diabetes.
Detailed description
This study will recruit up to 500 individuals ages 8-21 with type 1 or type 2 diabetes. In this study, participants will undergo a point-of-care diabetic eye exam using autonomous AI software on a non-mydriatic fundus camera. Participants will receive the diabetic eye exam results immediately from the autonomous AI system, and if abnormal will be referred to an eye care provider for a dilated eye exam.
In the AI for ChildrenS Diabetic Eye ExamS Study (ACCESS2), 398 participants will be enrolled to determine if point of care autonomous AI increases the proportion of minority and underserved youth screened for diabetic retinopathy. The autonomous AI interpretation will also be compared to consensus grading of retinal specialists to determine if there is agreement and to determine the diagnostic accuracy of the system in youth.
A cohort of youth with known diabetic retinopathy (true positives) will also be enrolled as an enriched population to determine the diagnostic accuracy of autonomous AI compared to the prognostic standard interpretation of a central reading center.
Interventions
- Diagnostic test Point of Care Autonomous AI diabetic retinopathy exam
Participants will undergo point-of-care diabetic retinopathy screening using autonomous artificial intelligence software to interpret retinal images taken with a non-mydriatic fundus camera and providing an immediate result.
Primary outcome measures
- Proportion screened for diabetic retinopathy [Time frame: Day 1]
Secondary outcome measures (4)
- Percentage of agreement in interpretation of retinal images [Time frame: Day 1]
- Sensitivity of autonomous AI vs. prognostic standard [Time frame: Day 1]
- Specificity of autonomous AI vs. prognostic standard [Time frame: Day 1]
- Proportion with diabetic retinopathy [Time frame: Day 1]
Eligibility criteria
Inclusion criteria
Meets American Diabetes Association (ADA) criteria for diabetic retinopathy screening:
- Diagnosis of Type 1 diabetes for ≥3 years, and age 11 or in puberty
- Diagnosis of Type 2 diabetes
Enriched cohort:
- Patients with Type 1 or Type 2 diabetes,
- 8-21 years of age with known diabetic retinopathy (true positives).
- No time limit on last diabetic eye exam.
Exclusion criteria
- Known diabetic eye exam in the last 12 months
Criteria are shown verbatim from the registry (in English). Final eligibility is always assessed by the study center.
Healthy volunteers: No
Study design
- Allocation
- N/A
- Model
- Single group
- Masking
- Open label
- Primary purpose
- Screening
Study locations
United States · 1 center
- Johns Hopkins Pediatric Diabetes Center — Baltimore
Publications
- Channa R, Wolf R, Abramoff MD. Autonomous Artificial Intelligence in Diabetic Retinopathy: From Algorithm to Clinical Application. J Diabetes Sci Technol. 2021 May;15(3):695-698. doi: 10.1177/1932296820909900. Epub 2020 Mar 4. PMID 32126819
- Thomas CG, Channa R, Prichett L, Liu TYA, Abramoff MD, Wolf RM. Racial/Ethnic Disparities and Barriers to Diabetic Retinopathy Screening in Youths. JAMA Ophthalmol. 2021 Jul 1;139(7):791-795. doi: 10.1001/jamaophthalmol.2021.1551. PMID 34042939
- Wolf RM, Channa R, Abramoff MD, Lehmann HP. Cost-effectiveness of Autonomous Point-of-Care Diabetic Retinopathy Screening for Pediatric Patients With Diabetes. JAMA Ophthalmol. 2020 Oct 1;138(10):1063-1069. doi: 10.1001/jamaophthalmol.2020.3190. PMID 32880616
- Wolf RM, Liu TYA, Thomas C, Prichett L, Zimmer-Galler I, Smith K, Abramoff MD, Channa R. The SEE Study: Safety, Efficacy, and Equity of Implementing Autonomous Artificial Intelligence for Diagnosing Diabetic Retinopathy in Youth. Diabetes Care. 2021 Mar;44(3):781-787. doi: 10.2337/dc20-1671. Epub 2021 Jan 21. PMID 33479160
- Porter M, Channa R, Wagner J, Prichett L, Liu TYA, Wolf RM. Prevalence of diabetic retinopathy in children and adolescents at an urban tertiary eye care center. Pediatr Diabetes. 2020 Aug;21(5):856-862. doi: 10.1111/pedi.13037. Epub 2020 May 31. PMID 32410329
Identifiers
NCT: NCT05463289 · IRB00180692 · 1R01EY033233-01