Eye and Vision · 10 authors, 2 centres
This summary was generated by AI from a single paper. It has not been reviewed by a clinician and is not clinical advice. Verify against the source before acting on it.
This cross-sectional metabolomics study analyzed aqueous humor from 60 macular edema patients and 20 controls using LC/MS and identified etiology-specific metabolic differences. A machine learning diagnostic model achieved ROC AUCs of 0.79 for AMD-ME, 0.94 for DME, and 0.77 for BRVO-ME in a test cohort.
This cross-sectional metabolomics study collected aqueous humor samples from 60 patients with macular edema of three etiologies and 20 healthy controls, analyzed via LC/MS. Pathway analysis showed differentially expressed metabolites were mainly involved in lipid metabolism and amino acid metabolism. Significant metabolic differences were found among AMD-ME, DME, and BRVO-ME groups, with 93, 19, and 21 DEMs identified in DME, BRVO-ME, and AMD-ME versus controls, respectively. A machine learning diagnostic model achieved ROC AUCs of 0.79 for AMD-ME, 0.94 for DME, and 0.77 for BRVO-ME. Nine novel common DEMs across all three groups were identified.
