Business Wire10.02.19
Eyenuk Inc., a global artificial intelligence (AI) medical technology and services company and the leader in real-world applications for AI Eye Screening, announced that a published study1 of more than 100,000 consecutive diabetic patient visits analyzed using the EyeArt AI Eye Screening System. The largest study of AI in health care reported that the EyeArt AI System achieved greater than 91 percent in both sensitivity and specificity for detection of referable diabetic retinopathy (DR). The study found the EyeArt AI System to be a safe and effective, fully automated tool to advance the worldwide need for diabetic retinopathy screening.
“The Value of Automated Diabetic Retinopathy Screening With the EyeArt System: A Study of More Than 100,000 Consecutive Encounters from People with Diabetes” was conducted in collaboration with the Doheny Eye Institute, one of the world’s leading ophthalmology programs affiliated with UCLA, and EyePACS, one of the largest global telemedicine programs for diabetic retinopathy screening.
“Diabetic retinopathy is the most common cause of blindness in working adults, yet this blindness is largely preventable with regular screening,” said Dr. SriniVas Sadda, president and chief scientific officer of the Doheny Eye Institute. “As the number of people with diabetes increases worldwide, manual screening methods simply cannot scale. We’re excited about the EyeArt AI Eye Screening System’s effectiveness in real-world clinical practice and its ability to increase the volume of screenings while improving accuracy and consistency, and reducing costs.”
The EyeArt AI Eye Screening System is the most extensively validated AI technology for autonomous detection of DR to date, tested in real-world settings on more than a half-million patient visits globally with more than 2 million images collected. This retrospective study of over 100,000 patient visits from real-world settings is complemented by another recent announcement of results from a prospective pivotal clinical trial that also demonstrated similar exceptional EyeArt AI System performance.
“While everyone talks about the future promise of AI in health care, this study proves that AI’s ability to transform health care is already here and it is here to stay,” said Kaushal Solanki, Ph.D., founder and CEO of Eyenuk. “By conducting this study on a large cohort of patients from over 400 primary care clinics, it is gratifying to know that the EyeArt AI System consistently provides high diagnostic sensitivity and specificity, in real-world conditions that include variations in patient demographics, dilation status, camera types, image quality, photographer experience, patient workflow and clinic size. By giving clinicians who manage diabetes access to such robust AI eye screening at point-of-care, we can help them identify DR sooner and ensure that patients with vision-threatening disease receive timely treatment.”
The peer-reviewed study assessed the diagnostic efficacy of the EyeArt AI System by analyzing 850,908 fundus images from 107,001 consecutive patient visits collected from 404 primary care clinics. The EyeArt AI System screening achieved 91.3 percent sensitivity and 91.1 percent specificity, showing that the EyeArt AI System performs well regardless of dilation status. Among 101,710 patient cases with the reference standard, only 910 (0.9 percent) were flagged as non-screenable by the EyeArt AI System. The study data represents a diverse range of patient demographics (age, race, ethnicity, sex) and includes images of varying quality captured by different photographers using a wide variety of cameras.
DR is a complication of diabetes caused by damage to the blood vessels of the light-sensitive tissue at the back of the eye (retina). It is a silently progressing disease that at first may cause no symptoms or only mild vision problems. Eventually, it can cause blindness. The condition can develop in anyone who has type 1 or type 2 diabetes.2 It is estimated that one-third of all patients with diabetes will develop DR,3 making it the leading cause of vision loss in working-age adults.4
While DR screening is recommended for all diabetic patients, less than half get screened annually even in the developed world. Since diabetic patients outnumber ophthalmologists by 1,600 to one in the United States,6 there are not enough eye care specialists to meet the DR screening needs of the growing diabetic population. Even for those receiving their annual screening, ophthalmology appointment wait times for DR screening can be weeks or even months.
The EyeArt AI Eye Screening System provides fully automated DR screening in a single office visit, including retinal imaging, DR grading on international standards and reporting. The EyeArt AI System allows diabetes care providers to identify patients with referable DR in clinic, in real time, without needing eye care expertise on-site, so at-risk patients can be immediately referred to an ophthalmologist for further evaluation and treatment. This removes the biggest obstacles to annual DR screening and diagnosis: screening access and patient compliance. Once the patient’s fundus images have been captured and submitted to the EyeArt AI System, the DR screening results are available to view and export to a PDF report in less than 60 seconds.
The EyeArt AI System was developed with funding from the U.S. National Institutes of Health (NIH) and is validated by the U.K. National Health Service (NHS). The EyeArt AI System has CE marking as a class 2a medical device in the European Union and a Health Canada license. In the United States, the EyeArt AI System is limited by federal law to investigational use. It is designed to be General Data Protection Regulation (GDPR) and Health Insurance Portability and Accountability Act of 1996 (HIPAA) compliant.
Learn more about the EyeArt AI Eye Screening System for Diabetic Retinopathy by watching this video.
Eyenuk Inc. is a global artificial intelligence (AI) medical technology and services company and the leader in real-world AI Eye Screening for autonomous disease detection and AI Predictive Biomarkers for risk assessment and disease surveillance. Eyenuk is on a mission to screen every eye in the world to ensure timely diagnosis of life- and vision-threatening diseases, including diabetic retinopathy, glaucoma, age-related macular degeneration, stroke risk, cardiovascular risk and Alzheimer’s disease. EyeArt is a registered trademark of Eyenuk Inc.
References
1 Bhaskaranand, Malavika, Chaithanya Ramachandra, Sandeep Bhat, Jorge Cuadros, Muneeswar Gupta Nittala, Srinivas Sadda, and Kaushal Solanki. “The Value of Automated Diabetic Retinopathy Screening With the EyeArt System: A Study of More Than 100,000 Consecutive Encounters from People with Diabetes.” Diabetes Technology & Therapeutics, July 23, 2019. https://doi.org/10.1089/dia.2019.0164.
2 https://www.mayoclinic.org/diseases-conditions/diabetic-retinopathy/symptoms-causes/syc-20371611
3 Yau JW, Rogers SL, Kawasaki R, et al. Global prevalence and major risk factors of diabetic retinopathy. Diabetes Care. 2012;35:556-64. doi: 10.2337/dc11-1909.
4 Prokofyeva E, Zrenner E. Epidemiology of major eye diseases leading to blindness in Europe: a literature review. Ophthalmic Res. 2012;47:171-188. doi: 10.1159/000329603.
5 Fitch, K et al. Longitudinal commercial claims–based cost analysis of diabetic retinopathy screening patterns. Am Health Drug Benefits. 2015 Sep;8(6):300-8.
6 http://www.icoph.org/ophthalmologists-worldwide.html and https://www.cdc.gov/diabetes/pdfs/data/statistics/national-diabetes-statistics-report.pdf
“The Value of Automated Diabetic Retinopathy Screening With the EyeArt System: A Study of More Than 100,000 Consecutive Encounters from People with Diabetes” was conducted in collaboration with the Doheny Eye Institute, one of the world’s leading ophthalmology programs affiliated with UCLA, and EyePACS, one of the largest global telemedicine programs for diabetic retinopathy screening.
“Diabetic retinopathy is the most common cause of blindness in working adults, yet this blindness is largely preventable with regular screening,” said Dr. SriniVas Sadda, president and chief scientific officer of the Doheny Eye Institute. “As the number of people with diabetes increases worldwide, manual screening methods simply cannot scale. We’re excited about the EyeArt AI Eye Screening System’s effectiveness in real-world clinical practice and its ability to increase the volume of screenings while improving accuracy and consistency, and reducing costs.”
The EyeArt AI Eye Screening System is the most extensively validated AI technology for autonomous detection of DR to date, tested in real-world settings on more than a half-million patient visits globally with more than 2 million images collected. This retrospective study of over 100,000 patient visits from real-world settings is complemented by another recent announcement of results from a prospective pivotal clinical trial that also demonstrated similar exceptional EyeArt AI System performance.
“While everyone talks about the future promise of AI in health care, this study proves that AI’s ability to transform health care is already here and it is here to stay,” said Kaushal Solanki, Ph.D., founder and CEO of Eyenuk. “By conducting this study on a large cohort of patients from over 400 primary care clinics, it is gratifying to know that the EyeArt AI System consistently provides high diagnostic sensitivity and specificity, in real-world conditions that include variations in patient demographics, dilation status, camera types, image quality, photographer experience, patient workflow and clinic size. By giving clinicians who manage diabetes access to such robust AI eye screening at point-of-care, we can help them identify DR sooner and ensure that patients with vision-threatening disease receive timely treatment.”
The peer-reviewed study assessed the diagnostic efficacy of the EyeArt AI System by analyzing 850,908 fundus images from 107,001 consecutive patient visits collected from 404 primary care clinics. The EyeArt AI System screening achieved 91.3 percent sensitivity and 91.1 percent specificity, showing that the EyeArt AI System performs well regardless of dilation status. Among 101,710 patient cases with the reference standard, only 910 (0.9 percent) were flagged as non-screenable by the EyeArt AI System. The study data represents a diverse range of patient demographics (age, race, ethnicity, sex) and includes images of varying quality captured by different photographers using a wide variety of cameras.
DR is a complication of diabetes caused by damage to the blood vessels of the light-sensitive tissue at the back of the eye (retina). It is a silently progressing disease that at first may cause no symptoms or only mild vision problems. Eventually, it can cause blindness. The condition can develop in anyone who has type 1 or type 2 diabetes.2 It is estimated that one-third of all patients with diabetes will develop DR,3 making it the leading cause of vision loss in working-age adults.4
While DR screening is recommended for all diabetic patients, less than half get screened annually even in the developed world. Since diabetic patients outnumber ophthalmologists by 1,600 to one in the United States,6 there are not enough eye care specialists to meet the DR screening needs of the growing diabetic population. Even for those receiving their annual screening, ophthalmology appointment wait times for DR screening can be weeks or even months.
The EyeArt AI Eye Screening System provides fully automated DR screening in a single office visit, including retinal imaging, DR grading on international standards and reporting. The EyeArt AI System allows diabetes care providers to identify patients with referable DR in clinic, in real time, without needing eye care expertise on-site, so at-risk patients can be immediately referred to an ophthalmologist for further evaluation and treatment. This removes the biggest obstacles to annual DR screening and diagnosis: screening access and patient compliance. Once the patient’s fundus images have been captured and submitted to the EyeArt AI System, the DR screening results are available to view and export to a PDF report in less than 60 seconds.
The EyeArt AI System was developed with funding from the U.S. National Institutes of Health (NIH) and is validated by the U.K. National Health Service (NHS). The EyeArt AI System has CE marking as a class 2a medical device in the European Union and a Health Canada license. In the United States, the EyeArt AI System is limited by federal law to investigational use. It is designed to be General Data Protection Regulation (GDPR) and Health Insurance Portability and Accountability Act of 1996 (HIPAA) compliant.
Learn more about the EyeArt AI Eye Screening System for Diabetic Retinopathy by watching this video.
Eyenuk Inc. is a global artificial intelligence (AI) medical technology and services company and the leader in real-world AI Eye Screening for autonomous disease detection and AI Predictive Biomarkers for risk assessment and disease surveillance. Eyenuk is on a mission to screen every eye in the world to ensure timely diagnosis of life- and vision-threatening diseases, including diabetic retinopathy, glaucoma, age-related macular degeneration, stroke risk, cardiovascular risk and Alzheimer’s disease. EyeArt is a registered trademark of Eyenuk Inc.
References
1 Bhaskaranand, Malavika, Chaithanya Ramachandra, Sandeep Bhat, Jorge Cuadros, Muneeswar Gupta Nittala, Srinivas Sadda, and Kaushal Solanki. “The Value of Automated Diabetic Retinopathy Screening With the EyeArt System: A Study of More Than 100,000 Consecutive Encounters from People with Diabetes.” Diabetes Technology & Therapeutics, July 23, 2019. https://doi.org/10.1089/dia.2019.0164.
2 https://www.mayoclinic.org/diseases-conditions/diabetic-retinopathy/symptoms-causes/syc-20371611
3 Yau JW, Rogers SL, Kawasaki R, et al. Global prevalence and major risk factors of diabetic retinopathy. Diabetes Care. 2012;35:556-64. doi: 10.2337/dc11-1909.
4 Prokofyeva E, Zrenner E. Epidemiology of major eye diseases leading to blindness in Europe: a literature review. Ophthalmic Res. 2012;47:171-188. doi: 10.1159/000329603.
5 Fitch, K et al. Longitudinal commercial claims–based cost analysis of diabetic retinopathy screening patterns. Am Health Drug Benefits. 2015 Sep;8(6):300-8.
6 http://www.icoph.org/ophthalmologists-worldwide.html and https://www.cdc.gov/diabetes/pdfs/data/statistics/national-diabetes-statistics-report.pdf
