Eyenuk Successfully Fulfills Contract for Artificial Intelligence Grading of Retinal Images

Source: Eyenuk

Eyenuk announced that it has successfully fulfilled the contract awarded by Public Health England (PHE) to use Eyenuk’s EyeArt AI Eye Screening System to grade 60,000 patient image sets from 6 different National Health Service (NHS) Diabetic Eye Screening Programs in England.

The UK has been leading the world in diabetic retinopathy screening, achieving patient uptake rates of over 80% (screening nearly 2.5 million diabetes patients annually),3 as compared with most parts of the world where typically less than half of diabetes patients receive annual eye screening,4 according to a company news release. As a result, diabetic retinopathy is no longer the leading cause of blindness in the working age group in England.5 However, the growing diabetes population poses significant challenges ahead.

Public Health England (PHE) is an executive agency of the Department of Health and Social Care (DH) that oversees the NHS national health screening programs. An independent Health Technology Assessment from the Moorfields Eye Hospital to determine the screening performance and cost-effectiveness of multiple DR detection AI solutions was conducted and published in 2016.6 Subsequently, PHE initiated a tender process seeking to commission an automated retinal image grading software to grade 60,000 patient image sets from multiple diabetic eye screening programs.

At the end of the competitive tender process, the contract was awarded to Eyenuk.7 The National Diabetic Eye Screening Programme (NDESP) identified 6 local diabetic eye screening (DES) programs to participate in the project with Eyenuk. The project aim was to compare the number of image sets categorized as having no disease, as determined by human graders (manual program grading), with the number as determined by the EyeArt AI eye screening system. Results from this latest real-world analysis, together with results from previous assessments have shown that the EyeArt system has excellent agreement and sensitivity and specificity for detecting diabetic retinopathy.

“Eyenuk was honored to have been awarded the PHE contract for diabetic retinopathy grading, and we are gratified that our EyeArt AI system delivered excellent results when compared with six DES programs in England,” Kaushal Solanki, PhD, founder and CEO of Eyenuk, said in the news release. “We look forward to expanding our work in the U.K. with hope to support all diabetic eye screening programs in the future.”

The independent Health Technology Assessment (HTA) from Moorfields Eye Hospital involving more than 20,000 patients was conducted to determine the screening performance and cost-effectiveness of multiple automated retinal image analysis systems. This study demonstrated that the EyeArt AI System delivered much higher sensitivity (i.e., patient safety) for DR screening than other automated DR screening technologies investigated and that its use is cost-effective alternative to the current, purely manual grading approach. The HTA demonstrated that the EyeArt performance was not affected by ethnicity, gender, or camera type.

1 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4657234/
2 https://www.diabetes.org.uk/about_us/news/diabetes-prevalence-statistics
3 https://www.gov.uk/government/publications/diabetic-eye-screening-2016-to-2017-data
4 K. Fitch, T. Weisman, T. Engel, A. Turpcu, H. Blumen, Y. Rajput, and P. Dave. Longitudinal commercial claims-based cost analysis of diabetic retinopathy screening patterns. Am Health Drug Benefits. 2015;8(6):300–308.
5 G. Liew, M. Michaelides, C. Bunce. A comparison of the causes of blindness certifications in England and Wales in working age adults (16–64 years), 1999–2000 with 2009–2010. BMJ Open Bd. 4 (2014), Nr. 2
6 Adnan Tufail, Venediktos V Kapetanakis, Sebastian Salas-Vega, Catherine Egan, Caroline Rudisill, Christopher G Owen, Aaron Lee, et al. “An Observational Study to Assess If Automated Diabetic Retinopathy Image Assessment Software Can Replace One or More Steps of Manual Imaging Grading and to Determine Their Cost-Effectiveness.” Health Technology Assessment 20, no. 92 (December 2016). https://doi.org/10.3310/hta20920
7 https://www.contractsfinder.service.gov.uk/Notice/13b069bd-97b4-40b6-ac66-337d1526d1e6

Related Content