To Örebro University

Purpose: The multicentre, prospective South Western Eye and Diabetes Deep Learning Algorithm study has developed a new diabetes retinal screening service, incorporating a novel deep learning algorithm, for a low socio-economic, multi-ethnic, outer-metropolitan Sydney region. This preliminary report examines patient satisfaction with retinal imaging and correlation between diabetic retinopathy (DR) and quality of life (QOL).

Methods: Supported by an Ophthalmic Research Institute of Australia grant, South Western Eye and Diabetes Deep Learning Algorithm participants were recruited from diabetes outpatient clinics and underwent two-field, table-top fundus photography and ocular coherence tomography. Questionnaires regarding patient satisfaction with retinal imaging and self-perceived QOL (EQ5D) were completed. Proportion of participants with high satisfaction levels were reported and mean self-perceivedQ OL (EQ-VAS) scores for those with and without DR were compared.

Results: The study is ongoing and preliminary data (n=54) is presented. DR was detected in 50.0% of recruited participants. All participants found it very convenient to undergo photography on the same day as their diabetes appointment and 83.3% would undergo retinal imaging for DR screening again. This was despite 50.0% of participants requiring pharmacological pupil dilation. Preliminary QOL data showed that although DR did not correlate with greater disability, pain or anxiety/depression, average self-perceived health was lower (mean EQ-VAS scores of 68.3% vs 76.3%) in participants with DR than those without DR.

Conclusions: The correlation between DR and lower self-perceived QOL, occurring independently of both visual acuity and knowledge of DR diagnosis, supports the need for efficient screening and early treatment. Retinal imaging was well-tolerated with an overwhelming preference for same-day outpatient DR screening.