Diabetes, Vision Disorders
Conditions
Keywords
Artificial Intelligence, AI, diabetic eye disease, pragmatic
Brief summary
This pragmatic clinical trial is being conducted to test the effectiveness of AI in improving screening and follow-up eye care compared to usual-care among patients with diabetes across 4 primary care clinics. This is an autonomous AI-based screening to detect diabetic eye disease at primary care visits.
Detailed description
Four clinics from two health systems will be recruited, with two clinics from each health system and randomly assigned to either usual-care or the AI Intervention with 2 clinics assigned to each arms. Beginning in month 3, a 6-week baseline period will be conducted in all clinics, followed by a 4-month intervention period for the two clinics assigned to AI. Primary Objective: Compare the odds of patients, who get eye screening in the AI and usual-care arms within 5 months of the recommendation Secondary Objective: 1. Compare the odds of patients, who completed follow-up with recommended eye care in the AI and usual-care arms within 5 months of the recommendation 2. Compare the odds of patients in different demographic groups who receive eye screening in the AI and usual-care arms within 5 months of the recommendation
Interventions
OTHERAI
AI-based eye screening program
OTHERUsual Practice
PCP recommends annual vision screening, a separate visit entirely
Sponsors
University of Wisconsin, Madison
Study design
Allocation
RANDOMIZED
Intervention model
PARALLEL
Primary purpose
HEALTH_SERVICES_RESEARCH
Masking
NONE
Intervention model description
Parallel cluster randomized control trial
Eligibility
Sex/Gender
ALL
Age
22 Years to No maximum
Healthy volunteers
Yes
Inclusion criteria
Clinic Inclusion Criteria: * Serve at least 267 patients with diabetes during the study period * No point-of-care screening system in use for diabetic eye disease * Agree to share limited identifiers data as requested Patient Inclusion Criteria: * Age 22 years or older * Diagnosis of type 1 or 2 diabetes * No known diabetic eye disease * No diabetic eye exam in the past 12 months
Exclusion criteria
* Have a documented eye exam 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
Design outcomes
Primary
| Measure | Time frame |
|---|---|
| Proportion of patients who get eye screening in the AI and usual-care arms within 5 months of the recommendation | up to 5 months |
Secondary
| Measure | Time frame |
|---|---|
| Proportion of patients, who completed follow-up with recommended eye care in the AI and usual-care arms within 5 months of the recommendation | up to 5 months |
| Proportion of patients in different demographic groups who receive eye screening in the AI and usual-care arms within 5 months of the recommendation | up to 5 months |
Countries
United States
Contacts
PRINCIPAL_INVESTIGATORRoomsa Channa, MD
University of Wisconsin, Madison
Outcome results
None listed