Development and preliminary validation of a predictive model for IgA nephropathy progression

Area of Science:

• Nephrology
• Medical Statistics
• Clinical Prediction Modeling

Background:

• IgA nephropathy (IgAN) is the most common primary glomerular disease globally.
• Predicting IgAN progression at diagnosis is challenging, particularly in primary care settings.
• Accurate prognostic tools are needed for early risk stratification and personalized management.

Purpose of the Study:

• To develop and validate a robust prognostic model for estimating 5-year renal survival in IgAN patients.
• To support early risk stratification and personalized management strategies for IgAN.
• To create a clinically applicable tool for primary care settings.

Main Methods:

• Retrospective enrollment of 1135 IgAN patients from Hangzhou Hospital (training/internal validation).
• External validation using 352 patients from three independent centers.
• LASSO-Cox regression and XGBoost survival models were employed to identify prognostic variables and construct a nomogram.

Main Results:

• The developed nomogram demonstrated high predictive accuracy with AUCs of 0.951 (training), 0.927 (internal validation), and 0.913 (external validation).
• Low Brier scores (0.029 internal, 0.045 external) indicated good calibration.
• Decision curve analysis confirmed the nomogram's favorable clinical utility.

Conclusions:

• A clinically practical prognostic model was developed to estimate 5-year renal survival in IgAN patients.
• The model utilizes routine clinical and pathological features, making it suitable for primary care.
• This tool facilitates early identification of high-risk individuals, enabling personalized long-term management, even in resource-limited settings.