AI Screening Tool Increases Diabetic Eye Exam Referrals for African Americans, Study Finds
核心洞察
A Johns Hopkins study found African American patients were more likely to receive diabetic eye exam referrals when screened by an AI-assisted diagnostic tool (64.9% vs. 44.4%).
Patients evaluated with the AI tool were 15% more likely to be African American among those who attended their follow-up diabetic retinopathy (搜索) evaluation.
The FDA-approved AI tool provides immediate, on-the-spot retinal screening results during primary care visits, potentially addressing known healthcare disparities.
Investigators at the Wilmer Eye Institute, Johns Hopkins Medicine (搜索) have found that African American patients with diabetes were significantly more likely to receive a diabetic eye exam referral when screened by an FDA-approved AI-assisted diagnostic tool, according to findings published April 13 in npj Digital Medicine.
The exploratory, peer-reviewed study examined whether referrals made by an AI-assisted diagnostic screening program increased patient adherence to recommended annual diabetic eye exams, with a focus on two historically disadvantaged patient groups: African American patients and patients covered under Medicaid.
Diabetic retinopathy (搜索)—the most common diabetes-associated eye disease—is the leading cause of blindness globally. Because patients may not experience symptoms early on, annual diabetic eye exams are essential for timely diagnosis and treatment. Yet African Americans and other racial and ethnic minorities, who are disproportionately affected by diabetic retinopathy, are also less likely to receive these annual exams.
How the AI Screening Tool Works
Patients evaluated with the AI tool had retinal images taken using a specialized camera and analyzed in real time during their primary care appointment. If diabetic retinopathy (搜索) was detected, patients were informed and given a referral to the Wilmer Eye Institute or another eye care specialist of their choice that same day.
"A referral [from a primary care provider] doesn't guarantee people will attend a diabetic eye exam, even if it's needed," said T.Y. Alvin Liu, M.D., principal investigator and founding director of the James P. Gills Jr., M.D., & Heather Gills Artificial Intelligence Innovation Center at the Wilmer Eye Institute.
Study Design and Key Findings
In their retrospective analysis, the researchers identified 3,745 adult patients with diabetes who visited the Wilmer Eye Institute for a diabetic retinopathy (搜索) evaluation between August 2020 and September 2022. Of this group, 3,352 patients (mean age 60.6 years) received referrals from their primary care providers, while 393 patients (mean age 61.6 years) received a recommendation from the AI-assisted screening tool.
Comparing the two referral methods, the researchers observed that a higher percentage of African American patients received an eye exam referral when the AI diagnostic tool was used (64.9% vs. 44.4%). The number of referrals for patients insured by Medicaid were comparable (0.8% vs. 0.6%) regardless of referral method.
Additionally, patients with hypertension (搜索) (89.6% vs. 82.6%) and chronic kidney disease (搜索) (26.2% vs. 20.9%) were also more likely to receive an eye exam referral when the AI-assisted tool was used, compared to people without either condition.
Investigating how referral methods translated to changes in patient care, Liu's team found that people who both opted for the AI-assisted tool and attended their diabetic retinopathy (搜索) evaluation were 15% more likely to be African American. Medicaid coverage did not impact patient appointment attendance regardless of referral source.
Addressing Healthcare Disparities
"With the AI tool, the patient is evaluated on the spot and given a test result. They're not being asked to attend an appointment because they may have something wrong," Liu said. "Other obstacles may limit whether patients can attend the screenings. But we were able to see that they are more convinced they need care if they're given immediate results with clear instructions on what to do."
The current study builds on previous work from Liu and his team, which found that, on a population level, the number of eye exam referrals for people with diabetic retinopathy (搜索) increased when the AI tool was used. Focusing on African American and Medicaid patients—two groups at high risk for poor visual health outcomes—allowed the researchers to clearly determine if the AI tool's use translated to positive changes in patient care.
Future Directions
Liu emphasized that while the findings are encouraging, further work is needed to evaluate whether improved test access translates to changes in long-term patient vision health outcomes. "Ultimately, AI tools are not meaningful unless you can demonstrate that their real-world deployment positively impacts patient lives. With future work, we want to examine how patients continue to interact with these AI tools over time and how that translates to specific eye health outcomes."
Support for the study was provided by the Gills Artificial Intelligence Innovation Center at the Wilmer Eye Institute and a Research to Prevent Blindness Career Development Award received by Alvin Liu. Researchers contributing to the study included Michael D. Abramoff, Roomasa Channa, Harold Lehmann, Ariel Leong, Jiangxia Wang, and Risa M. Wolf.