Renal interstitial inflammation predicts IgA nephropathy progression via multiple machine learning models.

Area of Science:

• Nephrology
• Immunology
• Pathology

Background:

• Renal interstitial inflammation (RII) is common in IgA nephropathy (IgAN) but its prognostic significance is unclear.
• This study aimed to clarify the prognostic value of RII in IgAN and develop a predictive model.

Purpose of the Study:

• To investigate the impact of RII on renal outcomes in IgAN patients.
• To develop and validate a machine learning-based model for individualized IgAN prognosis incorporating RII.

Main Methods:

• Retrospective analysis of 540 IgAN patients with renal biopsy data.
• Inclusion of demographics, clinical, laboratory, and histopathological parameters (including RII scores).
• Development and validation of a logistic regression model and nomogram using machine learning techniques.

Main Results:

• RII scores (RIIS1 and RIIS2) were independent predictors of adverse renal outcomes.
• Lower baseline serum albumin, eGFR, and higher SBP and proteinuria were associated with progression.
• The developed nomogram demonstrated high predictive accuracy (C-indices 0.90-0.92) across validation cohorts.

Conclusions:

• Renal interstitial inflammation is a significant independent predictor of renal disease progression in IgAN.
• The developed nomogram provides a valuable tool for individualized risk stratification and prognosis in IgAN patients.