AI screening for diabetic retinopathy accurate, helps remove barriers to care
Click Here to Manage Email Alerts
The use of artificial intelligence in screening for diabetic retinopathy led to accurate referrals in Rwanda with reportedly high patient satisfaction, according to a study published in the British Journal of Ophthalmology.
“This study has the potential to make a big impact for patients with diabetes in Africa,” Wanjiku “Ciku” Mathenge, MBChB, MMed, PhD, medical adviser of global programs for the nonprofit organization Orbis International and the study’s principal investigator, said in a press release from the organization. “In the study, we found that most patients had not had a recent full eye exam despite worrying about their vision and knowing their risks for developing diabetic retinopathy.”
Researchers screened participants for diabetic retinopathy at four diabetes clinics in Rwanda using Orbis’ Cybersight AI tool, which detects optic nerve and macular anomalies. A U.K. National Health System-certified retinal image grader evaluated the images, and those with grades above 2 were considered referrable.
Of 827 participants (59.6% women) screened by AI, 275 were referred for follow-up. According to results, 99.5% of participants were satisfied with the AI screening, with 63.7% reporting they preferred AI over human grading.
Further, researchers reported the sensitivity of AI for referable diabetic retinopathy was 92%, with a specificity of 85%. About one-third of participants were referred by AI for diabetic retinopathy alone, while the remainder were referred for diabetic retinopathy with an anomaly, an anomaly alone or other reasons.
According to the release, participants were satisfied with the AI screening because they received their exam during their diabetes appointment, saving time and cost of travel for a separate appointment. The screening also did not require participants to have their pupils dilated, and results were available immediately after the procedure, giving participants the opportunity to learn about their condition and its associated risks.
“Our research findings show that access to easy-to-use and conveniently located screening technologies allows patients to get the care they need and to prevent vision loss or blindness from diabetic retinopathy,” Mathenge said in the release. “The key now will be to ensure that such technologies become affordable and accessible to all.”
Reference:
- Study shows high patient satisfaction with AI eye screenings. https://www.prnewswire.com/news-releases/study-shows-high-patient-satisfaction-with-ai-eye-screenings-301896490.html. Published Aug. 9, 2023. Accessed Aug. 10, 2023.
Read more about
Click Here to Manage Email Alerts