Aim: To evaluate the MONA.health artificial intelligence screening software for detecting referable diabetic retinopathy (DR) and diabetic macular edema (DME), including subgroup analysis. Methods: The algorithm’s threshold value was fixed at the 90% sensitivity operating point on the receiver operating curve to perform the disease classification. Diagnostic performance was appraised on a private test set and publicly available datasets. Stratification analysis was executed on the private test set considering age, ethnicity, sex, insulin dependency, year of examination, camera type, image quality, and dilatation status. Results: The software displayed an area under the curve (AUC) of 97.28% for DR and 98.08% for DME on the private test set. The specificity and sensitivity for combined DR and DME predictions were 94.24 and 90.91%, respectively. The AUC ranged from 96.91 to 97.99% on the publicly available datasets for DR. AUC values were above 95% in all subgroups, with lower predictive values found for individuals above the age of 65 (82.51% sensitivity) and Caucasians (84.03% sensitivity). Conclusion: We report good overall performance of the MONA.health screening software for DR and DME. The software performance remains stable with no significant deterioration of the deep learning models in any studied strata.
Introduction A prospective study was carried out in Belgium to determine the proportion of subjects with a moderate to high risk of developing age-related macular degeneration (AMD), identified using the STARS® (Simplified Théa AMD Risk-Assessment Scale) questionnaire, who were in need of nutritional supplementation, by assessing the vitamin D, zinc oxide and fatty acid profile status. Methods This multicentre cross-sectional pilot study involved 50 Belgian subjects with no or early AMD, aged > 55 years who were at moderate to high risk for AMD. Subjects were assessed using the STARS® questionnaire, visual acuity assessment, an optical coherence tomography scan of the macula and fundus photography. Blood samples were collected, and serum analyses were performed to determine the the omega-6:omega-3 (Ω6:Ω3) ratio and the levels of eicosapentaenoic acid (EPA), docosahexaenoic acid (DHA), zinc and cupric oxides and vitamin D. Results Abnormal serum levels for at least one of the micronutrients was detected in 94% of the subjects. Lower than optimal vitamin D levels were found in 76% of the participants, and 68% of the subjects demonstrated at least one abnormal fatty acid profile. The Ω6:Ω3 ratio was above the reference range for normal values in 54% of the subjects; DHA and EPA levels were below the reference range in 60 and 46% of the subjects, respectively; and zinc oxide concentration was below the reference range in 50% of the subjects. Only 12% of the subjects exhibited cupric oxide deficiency. Conclusion In this study, the STARS® questionnaire was used for early identification of patients at moderate to high risk of AMD in real life. These patients presented a suboptimal nutritional status. Further research is needed to determine if specific diet modification or micronutrient supplement intake delays the onset or slows down the progression of AMD in these subjects. Trial Registration Trial registration: ClinicalTrials.Gov, identifier: NCT04482465.
14 September 2026 in BMC Medical Informatics and Decision Making
Glaucoma is one of the leading causes of irreversible blindness worldwide, affecting more than 76 million people, with prevalence expected to increase subs