Unsupervised Clustering Identifies High-Risk Phenotypic Subgroup in Patients with Crescentic Glomerulonephritis

Background: The current classification of crescentic glomerulonephritis (cGN) primarily focuses on renal outcomes, its ability to predict overall patient survival remains controversial. This study aims to develop a risk stratification system for overall survival and validate a renal risk score for predicting end-stage renal disease (ESRD) in cGN. Methods: A retrospective analysis was conducted on 224 cGN patients from the First Affiliated Hospital of Sun-Yat Sen University. The primary outcome was all-cause mortality and the secondary outcome was ESRD. Unsupervised clustering analysis, Principal component analysis were used to identify distinct patient groups. Results: The new K-means clustering revealed high-risk (n=142) and low-risk groups (n=82), with significant differences in patient survival outcomes (63.1% vs. 89.6%, P=0.004). Moreover, multivariate Cox regression indicated that the high-risk group independently predicted all-cause mortality (HR=3.28, P=0.002). We found that the crescentic glomerulonephritis kidney risk score (cGN-KS) consisting of serum creatinine levels, the percentage of normal glomeruli, and tubular atrophy/interstitial fibrosis independently predicted ESRD (HR=1.10, P<0.001) in cGN. Conclusion: Our study identifies two survival risk groups and develops a renal risk score in cGN patients, providing a comprehensive risk stratification to facilitate the management of cGN. Funding: Government Support – Non-U.S.