Artificial intelligence-based quantification of retinal microvascular biomarkers from fundus photography of chronic kidney disease: a case-control study - Summary - MDSpire
Advertisement
Artificial intelligence-based quantification of retinal microvascular biomarkers from fundus photography of chronic kidney disease: a case-control study
To identify retinal microvascular parameters associated with CKD and evaluate their discriminatory ability using AI-based fundus image analysis.
Key Findings:
Lower arteriovenous ratio (AVR), reduced arterial tortuosity (aTort), and lower arterial vascular density (aVD) associated with CKD.
Higher venous vascular density (vVD) and higher vessel tortuosity within the 3PD region (VT3PD) showed positive associations with CKD.
Final model demonstrated moderate discrimination for CKD (AUC = 0.776).
Exploratory analysis showed limited discrimination between early and advanced CKD (AUC = 0.748).
Interpretation:
Retinal microvascular alterations may serve as non-invasive indicators of early CKD, with several parameters already altered in early stages.
Limitations:
Single-center study may limit generalizability.
Exploratory analysis had limited discrimination between early and advanced CKD.
Conclusion:
AI-derived retinal microvascular parameters are associated with CKD and may facilitate early detection; further validation in larger populations is needed.
