Telemedical diagnosis of retinopathy of prematurity: Accuracy of expert versus non-expert graders

Background/aims: To assess accuracy of telemedical retinopathy of prematurity (ROP) diagnosis by trained non-expert graders compared with expert graders. Methods: Eye examinations (n=248) from 67 consecutive infants were captured using wide-angle retinal photography (RetCam-II, Clarity Medical Systems, Pleasanton, California, USA). Non-expert graders attended two 1-h training sessions on image-based ROP diagnosis. Using a web-based telemedicine system, 14 non-expert and three expert graders provided a diagnosis for each eye: no ROP, mild ROP, type 2 pre-threshold ROP or treatment-requiring ROP. All diagnoses were compared with a reference standard of dilated indirect ophthalmoscopy by an experienced paediatric ophthalmologist. Results: For detection of type 2 or worse ROP, the mean (range) sensitivities and specificities were 0.95 (0.94-0.97) and 0.93 (0.91-0.96) for experts, 0.87 (0.71-0.97) and 0.73 (0.39-0.95) for resident non-experts, and 0.73 (0.41-0.88) and 0.91 (0.84-0.96) for student non-experts, respectively. For detection of treatment-requiring ROP, the mean (range) sensitivities and specificities were 1.00 (1.00-1.00) and 0.93 (0.88-0.96) for experts, 0.88 (0.50-1.00) and 0.84 (0.71-0.98) for resident non-experts, and 0.82 (0.42-1.00) and 0.92 (0.83-0.97) for student non-experts, respectively. Conclusions: Mean sensitivity and specificity of trained non-experts were lower than that of experts, although several non-experts had high accuracy. Development of methods for training non-expert graders may help support telemedical ROP evaluation.