Telemedical Diabetic Retinopathy Screening in a Primary Care Setting: Quality of Retinal Photographs and Accuracy of Automated Image Analysis. (4th May 2022)

• Record Type: Journal Article
• Authors: Wintergerst, Maximilian W.M.; Bejan, Veronica; Hartmann, Vera; Schnorrenberg, Marina; Bleckwenn, Markus; Weckbecker, Klaus; Finger, Robert P.
• Is Part Of: Ophthalmic epidemiology. Volume 29:Number 3(2022)
• Page Start: 286
• Page End: 295
• Publication Date: 2022-05-04
• Subjects: Diabetic retinopathy screening -- automated image analysis -- deep learning -- image quality grading -- image analysis algorithm -- DR screening -- image quality scale -- diabetic eye disease screening -- diagnostic test accuracy -- primary care -- retinal photography quality -- retinal photographs quality -- EyeArt -- point of care -- general practitioner screening -- disagreement human automatic algorithm; Blindness -- Prevention -- Periodicals; Eye -- Diseases -- Epidemiology -- Periodicals; Ophthalmology -- Periodicals; 614.5997
• DOI: 10.1080/09286586.2021.1939886
• Languages: English
• ISSNs: 0928-6586

Abstract

ABSTRACT: Background: Screening for diabetic eye disease (DED) and general diabetes care is often separate, which leads to delays and low adherence to DED screening recommendations. Thus, we assessed the feasibility, achieved image quality, and possible barriers of telemedical DED screening in a point-of-care general practice setting and the accuracy of an automated algorithm for detection of DED. Methods: Patients with diabetes were recruited at general practices. Retinal images were acquired using a non-mydriatic camera (CenterVue, Italy) by medical assistants. Images were quality assessed and double graded by two graders. All images were also graded automatically using a commercially available artificial intelligence (AI) algorithm (EyeArt version 2.1.0, Eyenuk Inc.). Results: A total of 75 patients (147 eyes; mean age 69 years, 96% type 2 diabetes) were included. Most of the patients (51; 68%) preferred DED screening at the general practice, but only twenty-four (32%) were willing to pay for this service. Images of 63 patients (84%) were determined to be evaluable, and DED was diagnosed in 6 patients (8.0%). The algorithm's positive/negative predictive values (95% confidence interval) were 0.80 (0.28–0.99)/1.00 (0.92–1.00) and 0.75 (0.19–0.99)/0.98 (0.88–1.00) for detection of any DED and referral-warranted DED, respectively. Overall, the number of referrals was 18 (24%) for manual telemedical assessment and 31 (41%) for the artificial intelligence (AI) algorithm, resulting in a relative increase of referrals by 72% when using AI. Conclusions: Our study shows that achieved overall image quality in a telemedical GP-based DED screening was sufficient and that it would be accepted by medical assistants and patients in most cases. However, good image quality and integration into existing workflow remain challenging. Based on these findings, a larger-scale implementation study is warranted.