AI Screening for Diabetic Eye Disease May Save Time and Money

MedicalResearch.com Interview with:

Prof. Yogesan Kanagasingam, PhD Australian of the Year 2015 (WA Finalist) Research Director, Australian e-Health Research Centre Visiting Scholar,  Harvard University Adjunct Professor, School of Medicine University of Notre Dame

Prof. Kanagasingam

Prof. Yogesan Kanagasingam, PhD
Australian of the Year 2015 (WA Finalist)
Research Director, Australian e-Health Research Centre
Visiting Scholar,  Harvard University
Adjunct Professor, School of Medicine
University of Notre Dame

MedicalResearch.com: What is the background for this study? What are the main findings?

Response: We wanted to evaluate how an artificial intelligence (AI)–based grading system for diabetic retinopathy will perform in a real-world clinical setting, at a primary care clinic. 

MedicalResearch.com: What should readers take away from your report?

Response: Sensitivity and specificity of the AI system compared with the gold standard of ophthalmologist evaluation is provided.

The results demonstrate both the potential and the challenges of using AI systems to identify diabetic retinopathy in clinical practice. Key challenges include the low incidence rate of disease and the related high false-positive rate as well as poor image quality.

MedicalResearch.com: What recommendations do you have for future research as a result of this work?

Response: Low incidence rate of disease is an issue. May be a controlled environment, e.g. endocrinology clinic, may overcome this low incidence rate of diseases and high number of patients with diabetes.

Another research direction is how to improve image quality when capturing retinal images from a fundus camera.

How to overcome the issues related to sheen reflection is another research direction.  

MedicalResearch.com: Is there anything else you would like to add?

Response: At present, ophthalmologists or optometrists read all images.

If AI is introduced for image reading then, based the results from this study, ophthalmologists have to check only 8% of the images. This is a huge cost savings to the health system and save lot of time.

The accuracy rate (sensitivity and specificity) from this study is better than human graders.

Citation: 

Kanagasingam Y, Xiao D, Vignarajan J, Preetham A, Tay-Kearney M, Mehrotra A. Evaluation of Artificial Intelligence–Based Grading of Diabetic Retinopathy in Primary Care. JAMA Network Open. 2018;1(5):e182665. doi:10.1001/jamanetworkopen.2018.2665

Oct 6, 2018 @ 12:17 pm

The information on MedicalResearch.com is provided for educational purposes only, and is in no way intended to diagnose, cure, or treat any medical or other condition. Always seek the advice of your physician or other qualified health and ask your doctor any questions you may have regarding a medical condition. In addition to all other limitations and disclaimers in this agreement, service provider and its third party providers disclaim any liability or loss in connection with the content provided on this website.

 

Deep Learning System Can Screen For Diabetic Retinopathy, Glaucoma and Macular Degeneration

MedicalResearch.com Interview with:

Blausen.com staff (2014). "Medical gallery of Blausen Medical 2014". WikiJournal of Medicine 1 (2). DOI:10.15347/wjm/2014.010. ISSN 2002-4436. Illustration depicting diabetic retinopathy

Illustration depicting diabetic retinopathy

Dr. Tien Yin Wong MD PhD
Singapore Eye Research Institute, Singapore National Eye Center,
Duke-NUS Medical School, National University of Singapore
Singapore

MedicalResearch.com: What is the background for this study? What are the main findings?

Response: Currently, annual screening for diabetic retinopathy (DR) is a universally accepted practice and recommended by American Diabetes Association and the International Council of Ophthalmology (ICO) to prevent vision loss. However, implementation of diabetic retinopathy screening programs across the world require human assessors (ophthalmologists, optometrists or professional technicians trained to read retinal photographs). Such screening programs are thus challenged by issues related to a need for significant human resources and long-term financial sustainability.

To address these challenges, we developed an AI-based software using a deep learning, a new machine learning technology. This deep learning system (DLS) utilizes representation-learning methods to process large data and extract meaningful patterns. In our study, we developed and validated this using about 500,000 retinal images in a “real world screening program” and 10 external datasets from global populations. The results suggest excellent accuracy of the deep learning system with sensitivity of 90.5% and specificity of 91.6%, for detecting referable levels of DR and 100% sensitivity and 91.1% specificity for vision-threatening levels of DR (which require urgent referral and should not be missed). In addition, the performance of the deep learning system was also high for detecting referable glaucoma suspects and referable age-related macular degeneration (which also require referral if detected).

The deep learning system was tested in 10 external datasets comprising different ethnic groups: Caucasian whites, African-Americans, Hispanics, Chinese, Indians and Malaysians

Continue reading