Combined automated screening for age-related macular degeneration and diabetic retinopathy in primary care settings

Abstract

Background: Age-related macular degeneration (AMD) and diabetic retinopathy (DR) are among the leading causes of blindness in the United States and other developed countries. Early detection is the key to prevention and effective treatment. We have built an artificial intelligence-based screening system which utilizes a cloud-based platform for combined large scale screening through primary care settings for early diagnosis of these diseases. Methods: iHealthScreen Inc., an independent medical software company, has developed automated AMD and DR screening systems utilizing a telemedicine platform based on deep machine learning techniques. For both diseases, we prospectively imaged both eyes of 340 unselected non-dilated subjects over 50 years of age. For DR specifically, 152 diabetic patients at New York Eye and Ear faculty retina practices, ophthalmic and primary care clinics in New York city with color fundus cameras. Following the initial review of the images, 308 images with other confounding conditions like high myopia and vascular occlusion, and poor quality were excluded, leaving 676 eligible images for AMD and DR evaluation. Three ophthalmologists evaluated each of the images, and after adjudication, the patients were determined referrable or non-referable for AMD DR. Concerning AMD, 172 were labeled referable (intermediate or late), and 504 were non-referable (no or early). Concurrently, regarding DR, 33 were referable (moderate or worse), and 643 were non-referable (none or mild). All images were uploaded to iHealthScreen’s telemedicine platform and analyzed by the automated systems for both diseases. The system performances are tested on per eye basis with sensitivity, specificity, accuracy, and kappa scores with respect to the professional graders. Results: In identifying referable DR, the system achieved a sensitivity of 97.0% and a specificity of 96.3%, and a kappa score of 0.70 on this prospective dataset. For AMD, the sensitivity was 86.6%, the specificity of 92.1%, and a kappa score of 0.76. Conclusions: The AMD and DR screening tools achieved excellent performance operating together to identify two retinal diseases prospectively in mixed datasets, demonstrating the feasibility of such tools in the early diagnosis of eye diseases. These early screening tools will help create an even more comprehensive system capable of being trained on other retinal pathologies, a goal within reach for public health deployment.

Automated artificial intelligence‐based system for clinical follow‐up of patients with age‐related macular degeneration

“…It is well established that deep learning approaches perform well on pattern recognition tasks in imaging data (Ting et al 2019). Numerous approaches have been explored including classification of disease activity in AMD on optical coherence tomography (OCT) scans (Lee, Baughman & Lee 2017, Hwang et al 2019, Motozawa et al 2019, detection of referrable disease on fundus images (Burlina et al 2018, Bhuiyan et al 2021) and quantifying pathological fluid by segmentation of OCT images (De Fauw et al 2018, Schlegl et al 2018, Gao et al 2019.…”

“… 2018 , Bhuiyan et al . 2021 ) and quantifying pathological fluid by segmentation of OCT images (De Fauw et al . 2018 , Schlegl et al .…”

Transparency in Artificial Intelligence Reporting in Ophthalmology-A Scoping Review

“… 40 This study reported 23 of 36 of the transparency parameters we outlined. 40 Two studies used the STARD reporting checklist, and they reported 14 of 36 46 and 19 of 21 56 of the transparency parameters we assessed. These relatively low numbers are in part because many of the factors we reviewed were at the level of model development, not only clinical trialing.…”

Current status and practical considerations of artificial intelligence use in screening and diagnosing retinal diseases: Vision Academy retinal expert consensus

“…The iPredict AI Eye Screening System offers fully automated diagnosis of referable DR (sensitivity of 97.0% and specificity of 96.3%) and AMD (sensitivity of 86.6% and specificity of 92.1%) by analyzing CFPs [89] The Vision Academy recognizes the advantages of AI technology and recommends the use of them to be of additive and synergistic value to current standards of care. In terms of applying such technologies in diagnosing and screening retinal diseases, we summarize the following directions and emphasize several viewpoints important for the future.…”