［］Objective: To investigate the ability of the histological level of the key protein cytoskeleton-associated protein 4 (CKAP4) in urine extracellular vesicles as a biomarker for the progression of diabetic kidney disease (DKD). Methods: A total of 143 type 2 diabetic patients with biopsy-proven DKD and 10 patients with renal malignant tumors were enrolled. Renal endpoints were defined as the doubling of serum creatinine level or progression to end-stage kidney disease (ESKD). The expression of CKAP4 in renal tissue was detected by immunohistochemistry. Spearman correlation analysis was used to analyze the correlation between CKAP4 expression level and clinical indicators. The area under the receiver operating characteristic (ROC) curve (AUC) was calculated to assess whether CKAP4 expression could effectively distinguish patients with poor renal prognosis. Receiver operating characteristic (ROC) curve analysis was used to determine the best cut-off value of CKAP4 score for renal events (highest Youden index). Time-dependent AUC analyses were also performed to characterize the predictive accuracy of CKAP4 beyond 6 months after renal biopsy. In addition, hazard ratios between CKAP4 and DN progression were followed up by Cox proportional hazards models. The clinicopathological factors with statistical significance (p<0.05) in univariate analysis were included as covariates in multivariate Cox proportional hazards model analysis. Kaplan-Meier analysis was used to evaluate the difference in renal survival over 6 months after renal biopsy between CKAP4 high and CKAP4 low groups. Results: Compared with the adjacent normal kidney tissues of tumor patients, the expression of CKAP4 in the kidney of DKD patients was significantly increased (P<0.05). The expression of CKAP4 in renal tissues of DKD patients was different in different stages, and the differences between stage Ⅱ and stage Ⅲ, stage Ⅱ and stage Ⅳ, and stage Ⅲ and stage Ⅳ were statistically significant (P<0.05). The expression of CKAP4 in DKD patients was positively correlated with serum creatinine, urea nitrogen and 24h urine protein, and negatively correlated with eGFR and hemoglobin. During a median follow-up period of 2.22 years, 63 patients (44.06%) had DKD progression. Pearson correlation analysis showed that histological CKAP4 increased with the increase of pathological grade of DKD (r=0.808,p<0.001). Of note, multivariate Cox regression analysis showed that elevated CKAP4 was associated with an increased risk of DKD progression (HR: 4.120,95%CI: 1.730-9.811,p=0.001). In addition, in Kaplan-Meier survival analysis, patients with high CKAP4 expression had a significantly higher incidence of renal endpoint events than those with low CKAP4 expression (P<0.0001). At the same time, we developed a good nomogram including CKAP4 classification to predict the risk of DKD progression (C-index 0.689). Conclusions: Our findings suggest that histological expression of CKAP4, derived from urine extracellular vesicles, is an independent risk factor for renal progression over 6 months after renal biopsy in DKD patients.