Renal Failure最新文献

{"title":"Suppression of nF-κB by ro 106-9920 alleviates ischemia/reperfusion-induced renal dysfunction and inflammation via modulation of neutrophil extracellular trap formation in acute kidney injury mice.","authors":"Ming Wang, Feng Gao","doi":"10.1080/0886022X.2025.2545983","DOIUrl":"10.1080/0886022X.2025.2545983","url":null,"abstract":"<p><p>Neutrophil extracellular trap (NET) formation has been proven to take part in the exacerbation of acute kidney injury (AKI). Ro 106-9920, an effective inhibitor of nuclear factor kappa B (NF-κB) signal, could abrogate the formation of NETs. Herein, we explored whether Ro 106-9920 (Ro) exerts a protective role in AKI by repressing NET formation. The AKI model was induced with 30 min-bilateral renal ischemia followed by reperfusion. After finishing the 7-day treatment of Ro or vehicle, blood and the kidney were collected from each mouse for further analysis. Enzyme-linked immunosorbent assay, H&E, and TUNEL staining, immunohistochemistry, as well as Western blot were carried out to observe the kidney function, renal damage, apoptosis, and inflammation, and to preliminarily uncover the underlying mechanism. Administration with Ro effectively protected against AKI in a dose-dependent manner, as proven by the reduction of serum creatinine, serum neutrophil gelatinase-associated lipocalin, blood urea nitrogen, and serum inflammatory cytokine in AKI models after its administration. Moreover, Ro significantly alleviated morphological damage, kidney cells apoptosis, as well as inflammatory cytokine secretion in renal tissues. Mechanically, phosphorylation of NF-κB and myeloperoxidase activity were observed in renal tissues of AKI models, which suggested NF-κB activation and NETosis occurred in AKI. Notably, Ro treatment could significantly repress the nuclear translocation of NF-κB and the increased myeloperoxidase activity. Ro has a protective potential on ischemia/reperfusion-induced AKI by attenuating apoptosis and inflammation, perhaps by suppressing NF-κB activation and is associated with reduced NETosis.</p>","PeriodicalId":20839,"journal":{"name":"Renal Failure","volume":"47 1","pages":"2545983"},"PeriodicalIF":3.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12344707/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144837426","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development and validation of the predictive scoring system for 90-day mortality in critical ill patients with exertional heatstroke.","authors":"Jiali Cun, Li Zhong, Jingjing Ji, Yan Liu, Zhifeng Liu, Ming Wu","doi":"10.1080/0886022X.2025.2525462","DOIUrl":"10.1080/0886022X.2025.2525462","url":null,"abstract":"<p><strong>Purpose: </strong>Despite rising incidence, exertional heatstroke (EHS) lacks validated prognostic scoring tools. This study aimed to developed and validated a 90-day prognostic model for EHS patients.</p><p><strong>Methods: </strong>We conducted a retrospective cohort study of patients with EHS. Logistic regression analysis was utilized to identify the risk predictors associated with 90-day mortality. Using the mathematical transformation principle, the regression coefficients of each risk predictor were reassigned to develop a practical predictive scoring system. In this study, the predictive capability of the scoring model was validated <i>via</i> ROC curve analysis (AUC-based risk stratification), with model calibration further confirmed by the Hosmer-Lemeshow test.</p><p><strong>Results: </strong>Among 273 EHS patients in this cohort, 24 (8.8%) experienced 90-day mortality. Logistic regression analysis revealed acute kidney injury (AKI), prolonged activated partial thromboplastin time (APTT), and low fibrinogen as independent risk predictors. A scoring system (0-5 points) was developed by reassigning each predictor according to the logistic regression coefficient: AKI 3 points, prolonged APTT (≥47 s) 1 point, and fibrinogen (<2 g/L) 1 point. Internal validation using 1000 bootstrapping samples demonstrated that the scoring system had a relatively high discriminative ability, with a C-index of 0.90 (95% CI: 0.90-0.93). Using receiver operating characteristic curve analysis, the composite index incorporating these three risk predictors demonstrated a sensitivity of 78.3% and specificity of 89.9% in predicting 90-day mortality (area under the curve: 0.90; 95% confidence interval (CI): 0.81-0.98; <i>p</i> < 0.001).</p><p><strong>Conclusions: </strong>A predictive scoring system based on AKI, APTT, and fibrinogen can help predict the risk of 90-day mortality in patients with EHS.</p>","PeriodicalId":20839,"journal":{"name":"Renal Failure","volume":"47 1","pages":"2525462"},"PeriodicalIF":3.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12239103/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144576148","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analysis of red blood cell lifespan and associated influencing factors in anemic dialysis patients.","authors":"Jiaqing Wu, Bei Wu, Weili Gao, Yan Wang, Li Zhu, Li Bai, Lixia Lu, Ji Feng, Yanyan Shao, Liangying Gan, Huiping Zhao, Chunfang Wang, Xinju Zhao, Li Zuo","doi":"10.1080/0886022X.2025.2529439","DOIUrl":"10.1080/0886022X.2025.2529439","url":null,"abstract":"<p><strong>Introduction: </strong>Renal anemia is one of the most common complications in dialysis patients. The shortened red blood cell (RBC) lifespan is an important mechanism of renal anemia. This study aims to investigate the RBC lifespan and its influencing factors in anemic dialysis patients.</p><p><strong>Method: </strong>Prevalent patients on maintenance hemodialysis or peritoneal dialysis, treated with anti-anemia therapy including recombinant human erythropoietin (rHuEPO) or roxadustat for more than 4 months were enrolled. RBC lifespan was measured by the RBC lifespan analyzer RBCS-01A depended on Levitt's carbon monoxide (CO) breath test. Participants were primarily divided into low and high RBC lifespan groups by the average value.</p><p><strong>Result: </strong>A total of 187 patients were included in this study. The average RBC lifespan was 65.2 ± 28.55 days. The logistic regression analysis indicated treating with roxadustat rather than rHuEPO [OR 2.94, 95% CI (1.46, 5.95), <i>p</i> < 0.01], male [OR 2.15, 95% CI (1.08, 4.29), <i>p</i> = 0.03], higher body mass index (BMI) [OR 1.17, 95% CI (1.07, 1.27), <i>p</i> < 0.01], and higher total iron-binding capacity (TIBC) [OR 1.04, 95% CI (1.01, 1.06), <i>p</i> = 0.01] were independent risk factors for the shorten of RBC lifespan. While higher adjusted calcium [OR 0.14, 95% CI (0.03, 0.70), <i>p</i> = 0.02] and older age [OR 0.96, 95% CI (0.94, 0.99), <i>p</i> = 0.01] were independent protective factors.</p><p><strong>Conclusion: </strong>This study demonstrated that independent risk factors contributing to this reduction in RBC lifespan include male, elevated BMI, increased TIBC, and decreased adjusted calcium levels. Additionally, the type of anti-anemia therapy administered appears to have an impact on RBC lifespan.</p>","PeriodicalId":20839,"journal":{"name":"Renal Failure","volume":"47 1","pages":"2529439"},"PeriodicalIF":3.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12278460/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144675532","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Natural language processing for kidney ultrasound analysis: correlating imaging reports with chronic kidney disease diagnosis.","authors":"Chenlu Wang, Ritwik Banerjee, Harry Kuperstein, Hamza Malick, Ruqiyya Bano, Robin L Cunningham, Hira Tahir, Priyal Sakhuja, Janos Hajagos, Farrukh M Koraishy","doi":"10.1080/0886022X.2025.2539938","DOIUrl":"10.1080/0886022X.2025.2539938","url":null,"abstract":"<p><strong>Introduction: </strong>Natural language processing (NLP) has been used to analyze unstructured imaging report data, yet its application in identifying chronic kidney disease (CKD) features from kidney ultrasound reports remains unexplored.</p><p><strong>Methods: </strong>In a single-center pilot study, we analyzed 1,068 kidney ultrasound reports using NLP techniques. To identify kidney echogenicity as either \"normal\" or \"increased,\" we used two methods: one that looks at individual words and another that analyzes full sentences. Kidney length was identified as \"small\" if its length was below the 10th percentile. Nephrologists reviewed 100 randomly selected reports to create the reference standard (ground truth) for initial model training followed by model validation on an independent set of 100 reports.</p><p><strong>Results: </strong>The word-level NLP model outperformed the sentence-level approach in classifying increased echogenicity (accuracy: 0.96 vs. 0.89 for the left kidney; 0.97 vs. 0.92 for the right kidney). This model was then applied to the full dataset to assess associations with CKD. Multivariable logistic regression identified bilaterally increased echogenicity as the strongest predictor of CKD (odds ratio [OR] = 7.642, 95% confidence interval [CI]: 4.887-11.949; <i>p</i> < 0.0001), followed by bilaterally small kidneys (OR = 4.981 [1.522, 16.300]; <i>p</i> = 0.008). Among individuals without CKD, those with bilaterally increased echogenicity had significantly lower kidney function than those with normal echogenicity.</p><p><strong>Conclusions: </strong>State-of-the-art NLP models can accurately extract CKD-related features from ultrasound reports, with the potential of providing a scalable tool for early detection and risk stratification. Future research should focus on validating these models across different healthcare systems.</p>","PeriodicalId":20839,"journal":{"name":"Renal Failure","volume":"47 1","pages":"2539938"},"PeriodicalIF":3.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12322987/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144785145","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Acute kidney injury among patients aged over 80 years after percutaneous coronary intervention: a multicenter, retrospective cohort study.","authors":"Xin Liu, Dingyi Wang, Yalin Cheng, Huimin Li, Yuzhu Lu, Haiyang Gao, Jing Ma, Chaozeng Si, Tingyu Yin, Guohui Fan, Wenduo Zhang","doi":"10.1080/0886022X.2025.2560606","DOIUrl":"10.1080/0886022X.2025.2560606","url":null,"abstract":"<p><strong>Background: </strong>We aimed to investigate the incidence and risk factors of acute kidney injury (AKI) after percutaneous coronary intervention (PCI) in the oldest-old patients (≥80 years), particularly among those with baseline renal insufficiency and peri-operative hydration.</p><p><strong>Methods: </strong>This retrospective cohort study included patients ≥80 years undergoing PCI at two tertiary hospitals in China (hospitalized between January 2020 and December 2024). Baseline renal dysfunction was defined as eGFR < 60 mL/min/1.73 m² on admission. The primary endpoint was AKI event after PCI according to KDIGO criteria. Secondary endpoints included in-hospital mortality, renal replacement therapy, and length of hospital stay. Logistic regression was applied to identify AKI risk factors. Restricted cubic splines (RCS, 4 knots) were used to explore the dynamic risk magnitude for AKI as baseline eGFR changes, adjusting for multivariable.</p><p><strong>Results: </strong>Among the 995 patients included in the final analysis, the incidence of baseline renal insufficiency was 35.9% and that of AKI was 13.8%. Logistic regression showed that STEMI, NSTEMI, acute heart failure, baseline renal insufficiency, a higher neutrophil-to-lymphocyte ratio (NLR), and anemia were independent risk factors for AKI. Among those with baseline renal insufficiency, AKI incidence was 29.7%, and lower baseline eGFR, elevated NLR, and preoperative diuretic use were independent risk factors for AKI. RCS analysis revealed that the AKI risk was significantly increased when eGFR < 67.4 mL/min/1.73 m², regardless of hydration therapy.</p><p><strong>Conclusion: </strong>Patients ≥ 80 years old with baseline renal failure confronted higher AKI risk after PCI procedure. Comprehensive strategies beyond hydration may be needed for AKI prevention in this fragile population.</p>","PeriodicalId":20839,"journal":{"name":"Renal Failure","volume":"47 1","pages":"2560606"},"PeriodicalIF":3.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12466182/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145150700","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The relationship among inflammatory biomarkers, hyperuricemia and chronic kidney disease: analysis of the NHANES 2015-2020.","authors":"Huimin Li, Jingda Huang, Mindan Sun","doi":"10.1080/0886022X.2025.2553808","DOIUrl":"10.1080/0886022X.2025.2553808","url":null,"abstract":"<p><strong>Background: </strong>Inflammation and hyperuricemia are closely associated with chronic kidney disease (CKD). The systemic inflammation response index (SIRI), systemic immune-inflammation index (SII), monocyte-to-lymphocyte ratio (MLR), neutrophil-to-lymphocyte ratio (NLR), and platelet-to-lymphocyte ratio (PLR) are emerging as novel biomarkers. While, the synergistic effects of these biomarkers with hyperuricemia on CKD remain unclear.</p><p><strong>Method: </strong>We analyzed 10,226 participants from 2015-2020 National Health and Nutrition Examination Survey (NHANES). The relationships among inflammatory biomarkers (SIRI, SII, MLR, NLR, and PLR), hyperuricemia and CKD were assessed by multivariate logistic regression models. Restricted cubic splines (RCS) and segmented regression models were used to evaluate the nonlinear relationships. The diagnostic performance was evaluated using receiver operating characteristic (ROC) curve, and incremental predictive value was further calculated by Net Reclassification Improvement (NRI) and Integrated Discrimination Improvement (IDI). The interaction analysis was performed to explore the combined effects.</p><p><strong>Results: </strong>SIRI, SII, MLR, and NLR were significantly linked with CKD. MLR exhibited a threshold effect at 0.22 (<i>p</i>-non-linear < 0.05), with significantly stronger association with CKD above this cutoff. SIRI demonstrated the best diagnostic accuracy among these biomarkers. Significant interactions were observed between hyperuricemia and inflammatory biomarkers (SIRI, SII, MLR, NLR), indicating that the association between inflammatory biomarkers and CKD is more pronounced in the presence of hyperuricemia.</p><p><strong>Conclusion: </strong>There were significant associations between inflammatory biomarkers (SII, SIRI, NLR, MLR) and CKD, with particularly stronger correlations observed in patients with hyperuricemia.</p>","PeriodicalId":20839,"journal":{"name":"Renal Failure","volume":"47 1","pages":"2553808"},"PeriodicalIF":3.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12416012/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145016202","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Outcomes of single kidney transplantation from small pediatric donors aged <5 years: comparative analysis between pediatric and adult recipients.","authors":"Runtao Feng, Bingzhou Zhong, Haoxin Liang, Jianan Chen, Jianmin Hu, Song Zhou, Guorong Liao, Jun Liao, Weiwei Jiang, Siqiang Yang, Yongguang Liu","doi":"10.1080/0886022X.2025.2562446","DOIUrl":"10.1080/0886022X.2025.2562446","url":null,"abstract":"<p><p>The use of kidneys from small pediatric donors (< 5 years) for single kidney transplantation (SKT) may expand the donor pool. In recent years, many national allocation policies have given priority to pediatric recipients. However, comparative studies involving pediatric and adult recipients of single kidney transplants from small pediatric donors are limited. All patients who underwent SKT from small pediatric donors aged < 5 years at our center between January 1, 2015 and June 30, 2024 were included in this study. The outcomes included graft survival, patient survival, and post-transplant complications, which were compared between pediatric and adult recipients. The patient cohort included 83 adult recipients and 55 pediatric recipients from 48 and 40 small pediatric donors (aged < 5 years), respectively. Three-year death-censored graft survival and patient survival in pediatric recipients were 81.7% and 100%, respectively, which were not significantly different from those in adult recipients (89.0% and 95.8%). The leading cause of graft loss was vascular thrombosis (6 cases), followed by rejection (5 cases). No significant differences were observed between pediatric and adult recipients regarding primary nonfunction, the incidence of proteinuria, vascular and urinary complications, or the cumulative incidence of acute rejection. However, adult recipients experienced a significantly higher incidence of delayed graft function than pediatric recipients. SKT from small pediatric donors achieved comparable outcomes in adult and pediatric recipients, validating that current policies prioritizing pediatric recipients are clinically appropriate. Addressing risks of vascular thrombosis and rejection may further improve outcomes.</p>","PeriodicalId":20839,"journal":{"name":"Renal Failure","volume":"47 1","pages":"2562446"},"PeriodicalIF":3.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12451948/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145086931","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Large language models in nephrology: applications and challenges in chronic kidney disease management.","authors":"Yongzheng Hu, Jianping Liu, Wei Jiang","doi":"10.1080/0886022X.2025.2555686","DOIUrl":"10.1080/0886022X.2025.2555686","url":null,"abstract":"<p><p>Large language models (LLMs) represent a transformative advance in artificial intelligence, with growing potential to impact chronic kidney disease (CKD) management. CKD is a complex, highly prevalent condition requiring multifaceted care and substantial patient engagement. Recent developments in LLMs-including conversational AI, multimodal integration, and autonomous agents-offer novel opportunities to enhance patient education, streamline clinical documentation, and support decision-making across nephrology practice. Early reports suggest that LLMs can improve health literacy, facilitate adherence to complex treatment regimens, and reduce administrative burdens for clinicians. However, the rapid deployment of these technologies raises important challenges, including patient privacy, data security, model accuracy, algorithmic bias, and ethical accountability. Moreover, real-world evidence supporting the safety and effectiveness of LLMs in nephrology remains limited. Addressing these challenges will require rigorous validation, robust regulatory frameworks, and ongoing collaboration between clinicians, AI developers, and patients. As LLMs continue to evolve, future efforts should focus on the development of nephrology-specific models, prospective clinical trials, and strategies to ensure equitable and transparent implementation. If appropriately integrated, LLMs have the potential to reshape the landscape of CKD care and education, improving outcomes for patients and supporting the nephrology workforce in an era of increasing complexity.</p>","PeriodicalId":20839,"journal":{"name":"Renal Failure","volume":"47 1","pages":"2555686"},"PeriodicalIF":3.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12418797/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145016147","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrated lipidomics and proteomics analysis in the cardiac surgery-associated acute kidney injury.","authors":"Fangfang Zhou, Youjun Xu, Shuzhen Zhang, Lailiang Wang, Xingyue Zheng, Wenqing Ding, Hongchuang Ma, Qun Luo","doi":"10.1080/0886022X.2025.2561797","DOIUrl":"10.1080/0886022X.2025.2561797","url":null,"abstract":"<p><p>This study aimed to identify potential serum biomarkers and explore associated signaling pathways involved in cardiac surgery-associated acute kidney injury (CSA-AKI) by integrating proteomic and lipidomic analyses. A total of 34 patients were enrolled, including 17 CSA-AKI patients and 17 controls. Untargeted lipidomic analysis was performed using liquid chromatography-mass spectrometry (LC-MS) approach. Proteomics analysis was conducted using data-independent acquisition-based LC-MS/MS detection. The integration of proteomics and lipidomics was evaluated using statistical and bioinformatics methods. The two groups had different serum protein and lipid profiles, which included 185 differentially expressed proteins and 65 differentially expressed lipids. The protein and lipid molecules were enriched in biologic pathway implicated in biosynthesis of arachidonic acid metabolism, gonadotropin-releasing hormone signaling pathway, leukocyte trans endothelial migration, and glycerophospholipid metabolism. Correlation analysis revealed that 4 proteins were positively correlated with 21 lipids, whereas 7 proteins were negatively correlated with the 21 lipids. These results suggested that significantly altered proteins and lipids may be involved in the early stage of CSA-AKI and could serve as potentially promising markers. The association between proteins and lipid molecules and the underlying signaling pathways may elucidate the pathogenesis of CSA-AKI.</p>","PeriodicalId":20839,"journal":{"name":"Renal Failure","volume":"47 1","pages":"2561797"},"PeriodicalIF":3.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12498359/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145213405","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine learning model predicts clotting risk during CRRT in ESKD patients: a SHAP-interpretable approach.","authors":"Shuang Qiu, Shibo Mu, Yongyuan Tao, Ning Zhang, Jiuxu Bai, Ning Cao","doi":"10.1080/0886022X.2025.2562448","DOIUrl":"10.1080/0886022X.2025.2562448","url":null,"abstract":"<p><p>Ensuring fluent extracorporeal circulation and preventing circuit clotting are important for end-stage kidney disease (ESKD) patients undergoing continuous renal replacement therapy (CRRT). This study aimed to develop a predictive model using machine learning (ML) algorithms to evaluate clotting risk after initiating CRRT, enhancing treatment safety and effectiveness. This study involved 636 ESKD patients who underwent CRRT. Feature selection was conducted <i>via</i> the least absolute shrinkage and selection operator (LASSO) algorithm. ML algorithms, including support vector machine (SVM), extreme gradient boosting (XGBoost), random forest (RF), gradient boosting machine (GBM), decision tree, and logistic regression (LR), were applied to construct models through tenfold cross-validation. Model performance was assessed <i>via</i> the area under the receiver operating characteristic curve (AUC) and additional metrics. The Shapley additive explanation (SHAP) values quantify each feature's contribution. This study included 199 patients with blood clots during extracorporeal circulation, corresponding to an incidence rate of 31.3%. The AUC values were 0.864 (SVM), 0.815 (XGBoost), 0.806 (GBM), 0.778 (RF), 0.732 (Decision Tree), and 0.717 (LR). The SVM exhibited the best performance. The initial dose of low-molecular-weight heparin (LMWH) was identified as the most significant factor influencing coagulation. ML serves as a reliable tool for predicting the risk of extracorporeal circuit clotting in ESKD patients undergoing CRRT. The SHAP method elucidates key risk factors, providing a basis for early clinical intervention.</p>","PeriodicalId":20839,"journal":{"name":"Renal Failure","volume":"47 1","pages":"2562448"},"PeriodicalIF":3.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12517423/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145259139","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}