JMIR Publications

ABSTRACT

Background:

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

Objective:

This study integrated network biomarkers with unsupervised learning clustering (KMN) to refine risk stratification in IgA nephropathy (IgAN) and explore its clinical value.

Methods:

Involving a multicenter prospective cohort, we analyzed 1,460 patients and validated the approach externally with 200 additional patients. Deeper metabolic and microbiomic insights were gained from two distinct cohorts: 63 patients underwent ultra-performance liquid chromatography-mass spectrometry (UPLC-MS), while another 45 underwent fecal 16s RNA sequencing. Our approach utilized hierarchical clustering and k-means methods, employing three sets of indicators: demographic and renal; renal and extra-renal; and network biomarkers derived from all indicators.

Results:

Among six clustering methods tested, the KMN scheme was the most effective, accurately reflecting patient severity and prognosis with a prognostic accuracy AUC of 0.77, achieved solely through cluster grouping without additional indicators. The KMN stratification significantly outperformed the existing IIgAN-PT (AUC of 0.72) and RF-RG schemes (AUC of 0.69). Clinically, this stratification facilitated personalized treatment, recommending ACEI/ARBs for lower-risk and considering immunosuppressive therapy for higher-risk groups. Preliminary findings also indicated a correlation between IgAN progression and alterations in serum metabolites and gut microbiota, although further research is needed to establish causality.

Conclusions:

The effectiveness and applicability of the KMN scheme indicate its substantial potential for clinical application in IgAN management.