DESCRIPTION
Retinopathy screening and risk assessment with digital imaging systems are proposed as an alternative to conventional dilated fundus examination in diabetic individuals. Digital imaging systems utilize a digital fundus camera to acquire a series of standard field color images and/or monochromatic images of the retina of each eye. The digital images that are captured may then be evaluated on site or transmitted via the Internet to a remote center for interpretation by trained readers, storage, and subsequent comparison. This technology has made possible the linking of diabetic individuals in remote locations (where screening might otherwise not be available) with specialty centers that determine if retinopathy is present and recommend treatment if needed.
The reported purpose of digital retinal imaging with automated image interpretation, in individuals who have diabetes, is to aid in the decision of whether an individual should be referred to an ophthalmologist based on information provided by an automated scoring system. The telemedicine screening programs with manual grading (described above) rely on image interpretation by trained readers. A number of automated scoring systems are being evaluated for diabetic retinopathy screening.
There are currently several digital camera and transmission systems with manual grading available including, but not limited to:
Examples of digital retinal imaging with automated interpretation include:
Diabetic Retinopathy Screening Recommendations of the American Diabetes Association
|
Diabetes Type |
Recommended Time of First Exam |
Follow-up Exam |
|
Adult - Type 1 |
Within 5 years of diagnosis |
Annually* |
|
Adult - Type 2 |
At time of diagnosis |
Annually* |
|
Considering pregnancy (not gestational diabetes) |
Before pregnancy or early in the first trimester of pregnancy |
Every trimester during pregnancy and 1 year postpartum |
*Less frequent exams (every 2 years) may be considered following one or more normal annual eye exams
POLICY
Retinal telescreening with digital imaging and manual grading of images as a screening technique for diabetic retinopathy is considered medically necessary.
Digital retinal imaging with image interpretation by artificial intelligence software that is approved by the U.S. Food and Drug Administration (e.g., IDx-DR, EyeArt) is considered medically necessary for screening for diabetic retinopathy.
Retinal telescreening for all other indications, including, but not limited to, the monitoring and management of disease in individuals diagnosed with diabetic retinopathy is considered investigational.
IMPORTANT REMINDERS
Any specific products referenced in this policy are just examples and are intended for illustrative purposes only. It is not intended to be a recommendation of one product over another, and is not intended to represent a complete listing of all products available. These examples are contained in the parenthetical e.g. statement.
We develop Medical Policies to provide guidance to Members and Providers. This Medical Policy relates only to the services or supplies described in it. The existence of a Medical Policy is not an authorization, certification, explanation of benefits or a contract for the service (or supply) that is referenced in the Medical Policy. For a determination of the benefits that a Member is entitled to receive under his or her health plan, the Member's health plan must be reviewed. If there is a conflict between the Medical Policy and a health plan or government program (e.g., TennCare), the express terms of the health plan or government program will govern.
ADDITIONAL INFORMATION
Telemedicine and telehealth both describe the use of medical information exchanged from one site to another via electronic communications to improve the individual’s health status. Telemedicine is sometimes associated with direct clinical services and telehealth with a broader definition of remote healthcare services. Digital imaging systems may be used in the primary care physicians' office. Services that involve the electronic transmission of digital images across the Tennessee State line must adhere to all applicable Tennessee State requirements for the practice of medicine.
The American College of Radiology and the American Medical Association recommend that physicians using Teleradiology/ tele-imaging should be licensed in both the state where the images were generated and the state where the images are interpreted. Equipment specifications should assure the same image quality and availability if used for the initial diagnostic image interpretation, or for a review. Transmission and storage of images should adhere to appropriate privacy guidelines and restrictions.
SOURCES
Abramoff, M.D., Lavin, P.T., Birch, M., Shah, N., & Folk, J.C. (2018). Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices. NPJ Digital Medicine, doi: 10.1038/s41746-018-0040-6. (Level 3 evidence)
Abramoff, M. D., Whitestone, N., Patnaik, J. L., Rich, E., Ahmed, M., Husain, L., et al. (2023). Autonomous artificial intelligence increases real-world specialist clinic productivity in a cluster-randomized trial. NPJ Digital Medicine, 6 (1), 184. (Level 1 evidence)
American Academy of Ophthalmology. (2019). Diabetic retinopathy preferred practice pattern. Retrieved January 25, 2023 from https://www.aao.org/preferred-practice-pattern/diabetic-retinopathy-ppp.
American Diabetes Association. (2024, January). Standards of care in diabetes-2024. Retrieved October 22, 2024 from http://professional.diabetes.org/standards-of-care.
American Telemedicine Association. (2020, April). Practice guidelines for ocular telehealth - diabetic retinopathy, third edition. Retrieved January 25, 2023 from http://www.americantelemed.org.
BlueCross BlueShield Association. Evidence Positioning System. (4:2024). Retinal telescreening for diabetic retinopathy (9.03.13). Retrieved October 22, 2024 from https://www.bcbsaoca.com/eps/. (19 articles and/or guidelines reviewed)
CMS.gov: Center for Medicare & Medicaid Services. Palmetto, GBA. (2023, May). Ophthalmology: extended ophthalmoscopy and fundus photography (LCD ID L33467). Retrieved September 25, 2023 from https://www.cms.gov.
Heydon, P., Egan, C., Bolter, L., Chambers, R., Anderson, J., Aldington, S., et al. (2021). Prospective evaluation of an artificial intelligence-enabled algorithm for automated diabetic retinopathy screening of 30 000 patients. The British Journal of Ophthalmology, 105 (5), 723-728. (Level 2 evidence)
Ipp, E., Liljenquist, D., Bode, B., Shah, V., Silverstein, S., Regillo, C., et al. (2021). Pivotal evaluation of an artificial intelligence system for autonomous detection of referrable and vision-threatening diabetic retinopathy. JAMA Network Open, 4 (11), e2134254, doi:10.1001/jamanetworkopen.2021.34254 (Level 2 evidence)
Lee, A. Y., Yanagihara, R. T., Lee, C. S., Blazes, M., Jung, H. C., Chee, Y. E., et al. (2021). Multicenter, head-to-head, real-world validation study of seven automated artificial intelligence diabetic retinopathy screening systems. Diabetes Care, 44 (5), 1168-1175. (Level 2 evidence)
Shi, L., Wu, H., Dong, J., Jiang, K., Lu, X., & Shie, J. (2015). Telemedicine for detecting diabetic retinopathy: a systematic review and meta-analysis. British Journal of Ophthalmology, 99, 823-831. (Level 1 evidence)
U.S. Food and Drug Administration. (May, 1999). Center for Devices and Radiological Health. 510(k) Premarket Notification Database. K990205. Retrieved June 5, 2013 from http://www.accessdata.fda.gov.
Villa, R. S., Alvarez, A. C., Del Valle, de D. R., Mendez, S. R., Garcia, C. M., Garcia, R. M., et al. (2016). Five-year experience of teleophthalmology for diabetic retinopathy screening in a rural population. Archivos de la Sociedad Española de Oftalmología, 91 (9), 426-430. Abstract retrieved March 9, 2016 from PubMed database.
ORIGINAL EFFECTIVE DATE: 1/14/2012
MOST RECENT REVIEW DATE: 12/12/2024
ID_BA
Policies included in the Medical Policy Manual are not intended to certify coverage availability. They are medical determinations about a particular technology, service, drug, etc. While a policy or technology may be medically necessary, it could be excluded in a member's benefit plan. Please check with the appropriate claims department to determine if the service in question is a covered service under a particular benefit plan. Use of the Medical Policy Manual is not intended to replace independent medical judgment for treatment of individuals. The content on this Web site is not intended to be a substitute for professional medical advice in any way. Always seek the advice of your physician or other qualified health care provider if you have questions regarding a medical condition or treatment.
This document has been classified as public information.