JMIR Publications

ABSTRACT

Background:

With the high prevalence of diabetic retinopathy (DR) and its significant visual consequences if untreated, timely identification and management of DR is essential. Teleophthalmology programs have assisted in screening a larger number of individuals at risk for vision loss from DR. Training non-ophthalmological readers to assess remote fundus images for DR may further improve the efficiency of such programs.

Objective:

This study aims to evaluate the performance, safety implications and progress with experience of two ophthalmology nurses trained to read and assess diabetic retinopathy fundus images within a hospital diabetic retinopathy tele-screening program.

Methods:

In this retrospective inter-observer study, two ophthalmology nurses followed a specific training program within a hospital DR tele-screening program and were trained to assess DR images at two levels of intervention: detection of DR (Level 1) and identification of referable disease (Level 2). The reliability of the assessment by Level 1 trained readers in 266 patients and of the identification of patients at risk of vision loss from DR by Level 2 trained readers in 559 more patients was measured. The learning curve, sensitivity and specificity of the readings were evaluated using a group consensus gold standard.

Results:

Almost perfect agreement was measured in identifying the presence of diabetic retinopathy in both Level 1 readers (k = 0.86 and 0.80) and in identifying referable diabetic retinopathy by Level 2 readers (k = 0.80 and 0.83). At least substantial agreement was measured in the Level 2 readers for macular edema (k = 0.79 and 0.88) for all eyes. Good screening threshold sensitivities and specificities were obtained in all Level readers, with sensitivities of 90.6% and 96.9% and specificities of 95.1% and 85.1% for Level 1 readers and with sensitivities of 86.8% and 91.2% and specificities of 91.7% and 97.0% for Level 2 readers. This performance was achieved immediately after training and remained stable throughout the study.

Conclusions:

Notwithstanding the small number of trained readers, this study validates the screening performance of Level 1 and Level 2 diabetic retinopathy readers within this training program emphasizing practical experience and allows the establishment of an ongoing assessment clinic. It highlights the importance of supervised, hands-on experience and may help set parameters to further calibrate the training of DR readers for safe screening programs.