Diabetic nephropathy nomogram construction based on optical coherence tomography angiography variables

Area of Science:

• Ophthalmology
• Nephrology
• Medical Imaging

Background:

• Diabetic nephropathy (DN) is a major complication of type 2 diabetes mellitus (T2DM).
• Early detection and prediction of DN are crucial for effective management.
• Optical coherence tomography angiography (OCTA) offers novel insights into retinal microvasculature.

Purpose of the Study:

• To develop and validate a predictive model and nomogram for diabetic nephropathy (DN).
• To identify key optical coherence tomography angiography (OCTA) variables predictive of DN.
• To assess the clinical utility of the developed nomogram for DN diagnosis.

Main Methods:

• Retrospective enrollment of T2DM patients during diabetic retinopathy screening.
• Development of a prediction model using LASSO selection of OCTA variables.
• Validation of the model using ROC curves, calibration curves, and decision curve analysis.

Main Results:

• The model incorporated deep capillary plexus (DCP) parafoveal density, foveal capillary density (FD-300), age, sex, and axial length.
• The model demonstrated good performance with C-indices of 0.747 (training) and 0.681 (validation).
• Calibration curves showed good agreement, and decision curve analysis supported clinical utility.

Conclusions:

• A prediction model for DN using OCTA-derived variables was successfully developed.
• DCP density and FD-300 are significant predictors of DN.
• The nomogram serves as a potential diagnostic tool, with further external validation needed.