Deep learning versus human graders for classifying diabetic retinopathy severity in a nationwide screening program.

Deep learning algorithms have been used to detect diabetic retinopathy (DR) with specialist-level accuracy. This study aims to validate one such algorithm on a large-scale clinical population, and compare the algorithm performance with that of human graders. A total of 25,326 gradable retinal images of patients with diabetes from the community-based, nationwide screening program of DR in Thailand were analyzed for DR severity and referable diabetic macular edema (DME). Grades adjudicated by a panel of international retinal specialists served as the reference standard. Relative to human graders, for detecting referable DR (moderate NPDR or worse), the deep learning algorithm had significantly higher sensitivity (0.97 vs. 0.74, p < 0.001), and a slightly lower specificity (0.96 vs. 0.98, p < 0.001). Higher sensitivity of the algorithm was also observed for each of the categories of severe or worse NPDR, PDR, and DME (p < 0.001 for all comparisons). The quadratic-weighted kappa for determination of DR severity levels by the algorithm and human graders was 0.85 and 0.78 respectively (p < 0.001 for the difference). Across different severity levels of DR for determining referable disease, deep learning significantly reduced the false negative rate (by 23%) at the cost of slightly higher false positive rates (2%). Deep learning algorithms may serve as a valuable tool for DR screening.

Erratum: Author Correction: Deep learning versus human graders for classifying diabetic retinopathy severity in a nationwide screening program.

[This corrects the article DOI: 10.1038/s41746-019-0099-8.].

Blood culture and conventional media for vitreous culture in infectious endophthalmitis.

OBJECTIVE: To study culture of vitreous fluid specimens in patients with infectious endophthalmitis, using blood culture bottles compared with conventional culture media. MATERIAL AND METHOD: Patients with infectious endophthalmitis, occurred within 6 weeks after ocular trauma or intraocular surgery, were prospectively studied. Vitreous fluid specimens were cultured in both blood culture bottles and conventional culture media. The measured outcome is the yield of positive culture and time to positive culture. RESULTS: The vitreous fluid culture was positive in 14 of 27 eyes (51.85%). Blood culture bottle was positive in 14 of 14 eyes (100%), whereas conventional culture media was positive in 7 of 14 eyes (50%). Most specimens in both techniques showed positive culture within 24 hours. CONCLUSION: Vitreous fluid culture with blood culture bottles is superior to conventional media with statistically significant difference. There was no significant difference in time to positive culture.