Renal ischemia-reperfusion (I/R) injury is a leading cause of acute kidney injury (AKI), with high mortality. Recent studies have reported that human umbilical cord mesenchymal stem cells (HucMSCs) play an important role in repairing organ and tissue injuries because of their unique characteristics. However, the potential of HucMSC extracellular vesicles (HucMSC-EVs) to promote the repair of renal tubular cells remains to be explored. This study found that HucMSC-EVs derived from HucMSCs played a protective role and were associated with kidney I/R injury. We found that miR-148b-3p in HucMSC-EVs had a protective effect against kidney I/R injury. HK-2 cells overexpressing miR-148b-3p were protected against I/R injury by inhibiting apoptosis. Next, the target mRNA of miR-148b-3p was predicted online, and the target mRNA, pyruvate dehydrogenase kinase 4 (PDK4), was identified and verified using dual luciferase. We discovered that I/R injury significantly increased endoplasmic reticulum (ER) stress, whereas siR-PDK4 inhibited these effects and protected against I/R injury. Interestingly, after administrating HucMSC-EVs to HK-2 cells, PDK4 expression and ER stress induced by I/R injury were significantly inhibited. HK-2 ingested miR-148b-3p from HucMSC-EVs, and its ER induced by I/R injury was significantly deregulated. This study suggests that HucMSC-EVs protect kidneys from I/R injury during the early I/R stage. These results suggest a new mechanism for HucMSC-EVs in treating AKI and provide a new treatment strategy for I/R injury.

Background: Current staging for Upper Tract Urothelial Carcinoma (UTUC) fails to capture host biological heterogeneity. We aimed to develop and validate a machine - learning based prognostic signature integrating systemic immune - inflammatory and nutritional markers to enhance UTUC risk stratification. Methods: A total of 606 UTUC patients from four centers were divided into a training set (n = 263), an internal validation set (n = 114), and two external validation sets (n = 113, n = 116). Thirteen preoperative hematological markers were screened using LASSO - Cox regression. A Random Survival Forest (RSF) algorithm was utilized to construct a prognostic “ML Score”, and SHAP analysis visualized the nonlinear relationships. A composite nomogram integrating the ML Score with clinical factors (age, grade, pT stage) was developed and comprehensively evaluated. Results: Seven principal predictors were identified: RDW, PLT, NEUT, NLR, SIRI, SII, and AISI. SHAP analysis revealed distinct nonlinear threshold effects of RDW and PLT on mortality risk. The ML Score served as an independent prognostic indicator, successfully identifying patients with significantly poorer disease - free survival (DFS) across all four cohorts (P < 0.01). The integrated nomogram demonstrated outstanding predictive accuracy, with a C - index of 0.762 in the training set and maintaining robust performance in all validation cohorts. Decision curve analysis confirmed its superior clinical net benefit. Conclusion: We developed and validated a robust ML Score that reflects the host’s systemic immune - inflammatory and nutritional status. It offers substantial incremental prognostic value and serves as an accurate, non - invasive tool for personalized risk assessment in UTUC.