July 2018
Volume 59, Issue 9
Open Access
ARVO Annual Meeting Abstract  |   July 2018
One Year Results of Clinical Use of an Automatic Diabetic Retinopathy Screening System at Diabetes Care Clinics
Author Affiliations & Notes
  • E Simon Barriga
    VisionQuest Biomedical, Albuquerque, New Mexico, United States
  • Jeremy Benson
    VisionQuest Biomedical, Albuquerque, New Mexico, United States
    Computer Science, The University of New Mexico, Albuquerque, New Mexico, United States
  • Gilberto Zamora
    VisionQuest Biomedical, Albuquerque, New Mexico, United States
  • Javier Lozano
    Clinicas del Azucar, Monterrey, Mexico
  • Sheila C Nemeth
    VisionQuest Biomedical, Albuquerque, New Mexico, United States
  • Peter Soliz
    VisionQuest Biomedical, Albuquerque, New Mexico, United States
  • Footnotes
    Commercial Relationships   E Simon Barriga, VisionQuest Biomedical (E), VisionQuest Biomedical (I); Jeremy Benson, VisionQuest Biomedical (E); Gilberto Zamora, VisionQuest Biomedical (E); Javier Lozano, Clinicas del Azucar (E); Sheila Nemeth, VisionQuest Biomedical (E); Peter Soliz, VisionQuest Biomedical (E), VisionQuest Biomedical (I)
  • Footnotes
    Support  EY018280
Investigative Ophthalmology & Visual Science July 2018, Vol.59, 1887. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      E Simon Barriga, Jeremy Benson, Gilberto Zamora, Javier Lozano, Sheila C Nemeth, Peter Soliz; One Year Results of Clinical Use of an Automatic Diabetic Retinopathy Screening System at Diabetes Care Clinics. Invest. Ophthalmol. Vis. Sci. 2018;59(9):1887.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Purpose : To present clinical performance results of an automatic diabetic retinopathy (DR) tele-screening system operating at a network of comprehensive diabetic care clinics.

Methods : VisionQuest has introduced an Automatic Retinal Imaging Screening System (ARISS) which is being used autonomously at five comprehensive diabetes care clinics that are part of Clinicas del Azucar, in Monterrey, Mexico. Since September 2016, a total of 6,247 patients with diabetes have been screened for the presence of DR using the ARISS system. Retinal images are captured by a nurse or medical technician using Canon CR-2 retinal cameras. Images are uploaded to a central server and are processed and returned by ARISS to the clinics within 20 minutes. The ARISS system returns an output of “refer in 12 months” (no DR or Mild NPDR), “return in 6 months” (Moderate NPDR), or “refer to ophthalmology” (Severe NPDR, proliferative DR, or suspect for clinically significant macular edema).
A QA program samples approximately 25% of the cases which are then over-read by a certified retinal grader. The QA program assesses sensitivity, specificity, predictive values, and workload reduction. These results are reported periodically to the clinics.

Results : Sensitivity of ARISS for referable DR is 98% with a specificity of 77%. To date, only five cases with severe DR were misclassified by ARISS, but all fell into the “return in 6 months” category. No vision loss has been reported in any of those cases. ARISS’ negative predictive value (NPV) is 99.9% and its positive predictive value is 21.2%. Workload reduction, defined as the percent of total cases that did not need referral to an ophthalmologist, was 73%.

Conclusions : The ARISS system demonstrated clinically safe and effective performance for the detection of diabetic retinopathy in a clinical setting. The software screens out 73% of patients who do not need a referral to an ophthalmologist while maintaining high levels of safety. Resource scarcity and limited access to care make automation a viable alternative to screen their diabetic population.

This is an abstract that was submitted for the 2018 ARVO Annual Meeting, held in Honolulu, Hawaii, April 29 - May 3, 2018.

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×