Diabetic Retinopathy Screening Among Federally Qualified Health Center Patients Using Point-of-Care AI: DRES-POCAI: A...

Area of Science:

• Ophthalmology
• Artificial Intelligence in Healthcare
• Public Health

Background:

• Diabetic retinopathy screening (DRS) rates are historically low in underserved populations due to access barriers.
• Artificial intelligence (AI) offers a potential solution to improve screening accessibility and outcomes.
• Federally Qualified Health Centers (FQHCs) are crucial for delivering care to underserved communities.

Purpose of the Study:

• To increase DRS rates within FQHC primary care workflows.
• To facilitate early detection of diabetic retinopathy (DR) and improve timely specialist follow-up.
• To assess the impact of AI-powered DRS on patient knowledge, attitudes, and satisfaction.

Main Methods:

• A randomized clinical trial involving 848 diabetic patients aged 22+ at two FQHC sites.
• The intervention group received AI-powered DRS integrated with electronic health records (EHRs).
• The control group received standard referral care to eye specialists.

Main Results:

• The primary outcome is DRS completion status.
• Secondary outcomes include DR diagnosis stage, referral completion, and patient-reported outcomes related to AI-powered DRS.
• Study results are pending publication following data collection and analysis.

Conclusions:

• The DRES-POCAI trial will determine the effectiveness of AI-powered DRS in FQHC settings.
• This AI integration aims to enhance screening rates and facilitate early DR diagnosis and treatment.
• Findings are expected to inform the optimal implementation of AI-driven eye care in primary care.