Search Results (3)

Purpose: To examine the real-world performance of a support vector machine learning software (RetinaLyze) in order to identify the possible presence of diabetic retinopathy (DR) in patients with diabetes via software implementation in clinical practice. Methods: 1001 eyes from 1001 patients—one eye per patient—participating in the Danish National Screening Programme were included. Three independent ophthalmologists graded all eyes according to the International Clinical Diabetic Retinopathy Disease Severity Scale with the exact level of disease being determined by majority decision. The software detected DR and no DR and was compared to the ophthalmologists’ gradings. Results: At a clinical chosen threshold, the software showed a sensitivity, specificity, positive predictive value and negative predictive value of 84.9% (95% CI: 81.8–87.9), 89.9% (95% CI: 86.8–92.7), 92.1% (95% CI: 89.7–94.4), and 81.0% (95% CI: 77.2–84.7), respectively, when compared to human grading. The results from the routine screening were 87.0% (95% CI: 84.2–89.7), 85.3% (95% CI: 81.8–88.6), 89.2% (95% CI: 86.3–91.7), and 82.5% (95% CI: 78.5–86.0), respectively. AUC was 93.4%. The reference graders Conger’s Exact Kappa was 0.827. Conclusion: The software performed similarly to routine grading with overlapping confidence intervals, indicating comparable performance between the two groups. The intergrader agreement was satisfactory. However, evaluating the updated software alongside updated clinical procedures is crucial. It is therefore recommended that further clinical testing before implementation of the software as a decision support tool is conducted. Full article

Background: Laguna ONhE provides a globin distribution function (GDF), in which a glaucoma discriminator based on deep learning plays an important role, and there is also an optimized globin individual pointer (GIP) for progression analysis. Methods: Signs of optic nerve glaucoma were identified in 1,124,885 fundus images from 203,115 diabetics obtained over 15 years and 117,813 control images. Results: A total of 743,696 images from 313,040 eyes of 173,661 diabetics were analysed. Some exclusions occurred due to excessive illumination, poor quality, or the absence of optic discs. Suspicion of glaucoma was reported in 6.70%, for an intended specificity of 99% (GDF < −15). More signs of glaucoma occur in diabetics as their years of disease increase, and after age 60, compared to controls. The GIP detected progression (p < 0.01) in 2.59% of cases with 4 controls and in 42.6% with 14 controls was higher in cases with lower GDF values. The GDF was corrected for the disc area and proved to be independent of it (r = 0.001925; p = 0.2814). Conclusions: The GDF index suggests a higher and increasing glaucoma probability in diabetics over time. Doubling the number of check-ups from four to eight increases the ability to detect GIP index progression by a factor of 5. Full article

Background: The prevalence of diabetic retinopathy (DR) is expected to increase. This will put an increasing strain on health care resources. Recently, artificial intelligence-based, autonomous DR screening systems have been developed. A direct comparison between different systems is often difficult and only two such comparisons have been published so far. As different screening solutions are now available commercially, with more in the pipeline, choosing a system is not a simple matter. Based on the images gathered in a local DR screening program we performed a retrospective comparison of IDx-DR and Retinalyze. Methods: We chose a non-representative sample of all referable DR positive screening subjects (n = 60) and a random selection of DR negative patient images (n = 110). Only subjects with four good quality, 45-degree field of view images, a macula-centered and disc-centered image from both eyes were chosen for comparison. The images were captured by a Topcon NW-400 fundus camera, without mydriasis. The images were previously graded by a single ophthalmologist. For the purpose of this comparison, we assumed two screening strategies for Retinalyze—where either one or two out of the four images needed to be marked positive by the system for an overall positive result at the patient level. Results: Percentage agreement with a single reader in DR positive and DR negative cases respectively was: 93.3%, 95.5% for IDx-DR; 89.7% and 71.8% for Retinalyze strategy 1; 74.1% and 93.6% for Retinalyze under strategy 2. Conclusions: Both systems were able to analyse the vast majority of images. Both systems were easy to set up and use. There were several limitations to the current pilot study, concerning sample choice and the reference grading that need to be addressed before attempting a more robust future study. Full article