Remidio Innovative Solutions has announced the publication of a landmark independent evaluation of regulatory-approved artificial intelligence (AI) algorithms for diabetic retinopathy (DR) screening in The Lancet Digital Health. Led by Professor Alicja Rudnicka, Professor Adnan Tufail, and a team from the UK National Health Service (NHS), the study represents the largest real-world assessment of DR AI conducted to date.
The evaluation analysed more than 200,000 real-world screening encounters and approximately 1.2 million retinal images. Among the 32 DR AI algorithms initially assessed, eight met the criteria for inclusion in the final analysis. Remidio’s CE Class IIa–approved DR AI was one of the algorithms evaluated in this large-scale study.
Strong Clinical Performance in Population Screening
As per the press release, the evaluation demonstrated that Remidio’s AI delivers high sensitivity for both referable and sight-threatening diabetic retinopathy, while simultaneously maintaining strong specificity and predictive value—key requirements for large-scale population screening programmes.
For referable DR, which includes moderate non-proliferative DR and more advanced disease, Remidio’s AI achieved an overall sensitivity of 87 percent. Importantly, sensitivity increased to approximately 99 percent for moderate-to-severe non-proliferative DR and around 97 percent for proliferative DR. These results indicate that the system is highly unlikely to miss sight-threatening disease, thereby supporting timely referral and early intervention to prevent avoidable vision loss.
High Specificity Reduces Unnecessary Referrals
In addition to strong sensitivity, the AI demonstrated high specificity and positive predictive value. As a result, the system minimised false positives and reduced unnecessary referrals that can burden eye-care services.
Moreover, with a negative predictive value of approximately 98 percent, the AI provides strong reassurance for negative screening results. This performance supports broader screening coverage and enables the safe extension of screening intervals without increasing pressure on healthcare systems.
Clinical Perspectives on Screening Impact
Dr. R. Kim, Senior Consultant at Aravind Eye Hospital, highlighted the significance of the findings:
“Large-scale diabetic retinopathy screening requires both diagnostic accuracy and operational discipline. This evaluation shows that AI can reliably detect sight-threatening disease while maintaining the specificity needed to avoid overwhelming referral pathways. Such balance is essential for sustainable screening programmes, particularly in high-volume public health settings.”
Real-World Evidence at Scale
Dr. Divya, Chief Medical Officer at Remidio Innovative Solutions, emphasised the importance of real-world validation:
“This study evaluates AI performance at true screening scale rather than under controlled conditions. The results demonstrate that Remidio’s AI can consistently identify sight-threatening disease while avoiding unnecessary referrals, which is critical for safe and efficient public health screening.”
Equity, Scalability, and Health-System Benefits
The study also confirmed that Remidio’s AI performance remained stable across demographic subgroups, including age, sex, and ethnicity. This consistency supports equitable deployment across diverse populations.
At the health-system level, the findings suggest that the AI can reduce dependence on human image grading by up to approximately 80 percent. Consequently, specialist capacity can be redirected toward patients who require active clinical care. By increasing true-positive detection and reducing avoidable referrals, the AI has the potential to significantly enhance the cost-effectiveness of diabetic retinopathy screening pathways.
Built for Real-World Screening Environments
These results reinforce Remidio’s long-standing focus on developing AI solutions tailored for real-world screening, particularly within public health and resource-constrained settings. As the global burden of diabetes and diabetic retinopathy continues to rise, AI systems that combine high diagnostic sensitivity with operational efficiency will be essential for scalable and sustainable eye-care delivery.
Commitment to Better Population Eye Care
Remidio continues to support health systems worldwide by enabling earlier detection, improving clinical outcomes, and enhancing efficiency in eye-care delivery at population scale. The findings published in The Lancet Digital Health further validate the role of AI as a critical tool in addressing the growing challenge of diabetic retinopathy globally.