Risk Stratification in Immunoglobulin A Nephropathy Using Network Biomarkers: Development and Validation Study.

Area of Science:

• Nephrology
• Biomarker Discovery
• Network Medicine

Background:

• Traditional risk models for immunoglobulin A nephropathy (IgAN) lack comprehensive assessment and therapeutic guidance.
• Existing models primarily rely on renal indicators, necessitating more refined and integrative approaches.

Purpose of the Study:

• To integrate network biomarkers with unsupervised learning clustering (k-means clustering based on network biomarkers [KMN]) for refined risk stratification in IgAN.
• To explore the clinical value of the KMN approach in IgAN patient management.

Main Methods:

• Analysis of a multicenter prospective cohort of 1460 IgAN patients, with external validation on 200 patients.
• Integration of demographic, renal, and extrarenal indicators, alongside network biomarkers derived from all indicators.
• Application of hierarchical clustering and k-means methods, including ultraperformance liquid chromatography-mass spectrometry and fecal 16S RNA sequencing for metabolic and microbiomic insights.

Main Results:

• The KMN scheme demonstrated superior prognostic accuracy (AUC 0.77) compared to existing tools (AUC 0.72 and 0.69).
• KMN stratification facilitated personalized treatment recommendations, including ACE inhibitors/ARBs for lower-risk and immunosuppressants for higher-risk groups.
• Preliminary findings suggest correlations between IgAN progression, serum metabolites, and gut microbiota.

Conclusions:

• The KMN scheme shows significant potential for clinical application in IgAN management due to its effectiveness and applicability.
• This novel approach offers a more refined risk stratification for personalized therapeutic strategies in IgAN.