Renal Failure最新文献

{"title":"A practical guide for nephrologist peer reviewers: evaluating artificial intelligence and machine learning research in nephrology.","authors":"Yanni Wang, Wisit Cheungpasitporn, Hatem Ali, Jianbo Qing, Charat Thongprayoon, Wisit Kaewput, Karim M Soliman, Zhengxing Huang, Min Yang, Zhongheng Zhang","doi":"10.1080/0886022X.2025.2513002","DOIUrl":"10.1080/0886022X.2025.2513002","url":null,"abstract":"<p><p>Artificial intelligence (AI) and machine learning (ML) are transforming nephrology by enhancing diagnosis, risk prediction, and treatment optimization for conditions such as acute kidney injury (AKI) and chronic kidney disease (CKD). AI-driven models utilize diverse datasets-including electronic health records, imaging, and biomarkers-to improve clinical decision-making. Applications such as convolutional neural networks for kidney biopsy interpretation, and predictive modeling for renal replacement therapies underscore AI's potential. Nonetheless, challenges including data quality, limited external validation, algorithmic bias, and poor interpretability constrain the clinical reliability of AI/ML models. To address these issues, this article offers a structured framework for nephrologist peer reviewers, integrating the TRIPOD-AI (Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis-AI Extension) checklist. Key evaluation criteria include dataset integrity, feature selection, model validation, reporting transparency, ethics, and real-world applicability. This framework promotes rigorous peer review and enhances the reproducibility, clinical relevance, and fairness of AI research in nephrology. Moreover, AI/ML studies must confront biases-data, selection, and algorithmic-that adversely affect model performance. Mitigation strategies such as data diversification, multi-center validation, and fairness-aware algorithms are essential. Overfitting in AI is driven by small patient cohorts faced with thousands of candidate features; our framework spotlights this imbalance and offers concrete remedies. Future directions in AI-driven nephrology include multimodal data fusion for improved predictive modeling, deep learning for automated imaging analysis, wearable-based monitoring, and clinical decision support systems (CDSS) that integrate comprehensive patient data. A visual summary of key manuscript sections is included.</p>","PeriodicalId":20839,"journal":{"name":"Renal Failure","volume":"47 1","pages":"2513002"},"PeriodicalIF":3.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12239107/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144576146","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":"Bioinformatics reveals TNFAIP6 as a candidate gene and suggests its potential crosstalk in the treatment of hemodialysis in chronic kidney disease.","authors":"Guoxin Zhang, Jieqiong Fu, Wenming Niu","doi":"10.1080/0886022X.2025.2528757","DOIUrl":"10.1080/0886022X.2025.2528757","url":null,"abstract":"<p><p>Hemodialysis (HD) is a life-sustaining treatment for chronic kidney disease (CKD) patients. This study aimed to identify candidate diagnostic biomarkers associated with HD-treated CKD. The public dataset was acquired from the Gene Expression Omnibus database. The differentially expressed genes (DEGs) showing opposite trends across the three groups were obtained as crosstalk genes, and their potential pathways were explored through KEGG and GSEA analyses. Next, hub genes were identified using LASSO regression, and their diagnostic potential was assessed <i>via</i> ROC analysis. Key immune cell populations were identified using ssGSEA. Blood samples from healthy controls (<i>n</i> = 10), CKD patients (<i>n</i> = 9), and HD-treated CKD patients (<i>n</i> = 7) were collected to validate hub gene expression. A total of 132 crosstalk genes were identified, with the TGF-β and KRAS signaling pathways potentially activated in the HD group. Two hub genes, SIK1 and TNFAIP6, exhibited AUC values exceeding 0.8 for diagnosing CKD and HD-treated CKD groups. Compared to the other groups, neutrophil abundance was significantly higher in CKD group and showed a strong correlation with the hub genes. External datasets and RT-qPCR validated a consistent expression trend of TNFAIP6. Therefore, TNFAIP6 may represent a potential candidate gene with biomarker relevance in CKD and HD-treated CKD. TNFAIP6 has been previously associated with the TGF-β pathway and neutrophil regulation, and its crosstalk mechanism in HD-treated CKD warrants further exploration.</p>","PeriodicalId":20839,"journal":{"name":"Renal Failure","volume":"47 1","pages":"2528757"},"PeriodicalIF":3.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12261513/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144626995","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":"METTL3 alleviates renal tubular mitochondrial dysfunction by regulating the TUG1/PGC-1a axis in an IGF2BP2-dependent manner in diabetic nephropathy.","authors":"Tong Chen, Juan Wang, Yanyan Xu, Yonghong Zhu, Ying Jin, Qiuling Fan","doi":"10.1080/0886022X.2025.2521455","DOIUrl":"10.1080/0886022X.2025.2521455","url":null,"abstract":"<p><strong>Purpose: </strong>To explore the N6-methyladenosine (m⁶A) modification mechanism of taurine upregulated gene 1 (TUG1) and whether methyltransferase 3 (METTL3) can promote peroxisome proliferators-activated receptor γ coactivator 1 alpha (PGC-1α) transcription and alleviate mitochondrial dysfunction.</p><p><strong>Methods: </strong><i>In vitro</i> high glucose (HG)-treated HK-2 cell models and <i>in vivo</i> db/db mice models injected with rAAV-METTL3 <i>via</i> the tail vein were established. The expression levels were determined by RT-qPCR, western blot, and immunohistochemical staining. RNA m⁶A modification was analyzed by the RNase Mazf. The biochemical indicators of mice were detected by enzyme-linked immunosorbent assay. Cell apoptosis was detected by flow cytometry. Histopathological staining was performed to evaluate kidney injury. mtDNA content, mitochondrial complex activity, and ATP were detected by RT-qPCR and detection kits, respectively, per the manufacturer's instructions. Mitochondrial reactive oxygen species production in HK-2 cells incubated with MitoSOX Red and mitochondrial morphology were observed under a fluorescence microscope and transmission electron microscope, respectively. Molecular interactions were verified through RNA immunoprecipitation, RNA pull-down, and dual-luciferase reporter gene assay.</p><p><strong>Results: </strong>METTL3 and TUG1 expression levels decreased in the kidneys of diabetic mice and HG-treated HK-2 cells. Mechanistically, METTL3-mediated m⁶A modification increased the stability of TUG1 in an insulin-like growth factor 2 mRNA binding protein 2 (IGF2BP2)-dependent manner. METTL3-mediated m⁶A modification of TUG1 promotes PGC-1α activation, thereby alleviating mitochondrial dysfunction in HG-treated HK-2 cells and db/db mice. Moreover, METTL3 overexpression alleviated kidney injury in db/db mice.</p><p><strong>Conclusion: </strong>METTL3 targets TUG1/PGC-1α and ameliorates mitochondrial dysfunction in diabetic nephropathy in an IGF2BP2-dependent manner.</p>","PeriodicalId":20839,"journal":{"name":"Renal Failure","volume":"47 1","pages":"2521455"},"PeriodicalIF":3.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12281650/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144675534","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":"Impact of rapamycin on delayed graft function in kidney transplant recipients: a meta-analysis.","authors":"Yan Tang, Jiefu Zhu, Xiaolan Mao, Zhitao Cai","doi":"10.1080/0886022X.2025.2515530","DOIUrl":"10.1080/0886022X.2025.2515530","url":null,"abstract":"<p><strong>Objective: </strong>To evaluate the effect of rapamycin on DFG (delayed graft function in kidney transplant) recipients through a systematic review and meta-analysis.</p><p><strong>Methods: </strong>We searched PubMed, Embase, Cochrane Library, and other databases for studies assessing rapamycin use in kidney transplantation with a focus on DGF. The search was conducted from the time of database construction to December 2024. Literature search and quality evaluation were conducted by two researchers. Data were analyzed using RevMan 5.3, with odds ratio (OR) for dichotomous outcomes and mean differences (MD) for continuous outcomes. The meta-analysis was performed with Q-<i>I</i>²; fixed model for <i>I</i>² < 50%; sensitivity analysis for <i>I</i>² ≥ 50%. <i>p</i> Values < 0.05 were considered statistically significant.</p><p><strong>Results: </strong>Nine studies (<i>n</i> = 9,219) were included. Rapamycin was associated with an increased risk of DGF (OR = 1.29, 95% CI: 1.04-1.58), with a prolonged DGF duration (MD = 8.86, 95% CI: 3.84-13.89). No significant differences were found in graft survival (OR = 1.40, 95% CI: 0.72-2.73); patient survival (OR = 1.89, 95% CI: 0.84-4.26), or rejection incidence (OR = 1.22, 95% CI: 0.78-1.90).</p><p><strong>Conclusions: </strong>Rapamycin significantly increases the risk and duration of DGF after kidney transplantation. However, it does not appear to affect long-term outcomes such as graft survival or rejection rates. These findings suggest that rapamycin should be used cautiously in transplant recipients at risk for DGF, and further studies are needed to optimize immunosuppressive strategies for this population.</p>","PeriodicalId":20839,"journal":{"name":"Renal Failure","volume":"47 1","pages":"2515530"},"PeriodicalIF":3.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12217102/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144529422","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":"Prevalence of acute kidney injury in Mexico; a systematic review and meta-analysis of pre-pandemic reports.","authors":"Jose J Zaragoza, Jonathan S Chavez-Iñiguez, Armando Vazquez-Rangel","doi":"10.1080/0886022X.2024.2449573","DOIUrl":"10.1080/0886022X.2024.2449573","url":null,"abstract":"<p><strong>Background: </strong>Acute Kidney Injury (AKI) is a health problem worldwide, accounting for high hospital morbidity and mortality. There is little available information regarding the characteristics and incidence of AKI in Latin America (LA), especially in Mexico.</p><p><strong>Objectives: </strong>Systematically search the literature and perform a meta-analysis of the epidemiology of AKI in Mexico, to provide data on AKI and kidney replacement therapy (KRT) that would contribute to general knowledge in this matter.</p><p><strong>Methods: </strong>We performed a systematic search for articles in pediatric and adult patients admitted to the general ward, Emergency Room or Intensive Care Unit published between January 1, 2000, and September 30, 2024. MEDLINE LILIACS, EMBASE and SciELO were searched, as additional reports from supplements, abstracts, and conference sessions. We performed a random-effects meta-analysis for clinically and methodologically comparable studies to estimate the frequency of AKI and KRT. We calculated pooled estimates stratified by age group, year of publication, and setting.</p><p><strong>Results: </strong>83 full-text articles were included. The percentage of AKI was calculated at 35% (95% CI, 28-42). Mortality for AKI adult patients was 36% (95% CI, 28-45). An overall KRT rate was 7% (95% CI, 6-9), all-cause mortality for AKI requiring KRT was 49% (95% CI, 42-56), with a global Ι2 estimated in 99.87% (<i>p</i> < 0.01).</p><p><strong>Conclusion: </strong>AKI is common in Mexico and remains a main public health problem that needs to be addressed at every level of care. Efforts should be made to reinitiate AKI research and control in Mexico and LA.</p>","PeriodicalId":20839,"journal":{"name":"Renal Failure","volume":"47 1","pages":"2449573"},"PeriodicalIF":3.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11784032/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143067596","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":"Causal insights into major risk factors for diabetic kidney disease: a comprehensive meta-analysis and Mendelian randomization study.","authors":"Yucong Zhou, Yahong Liu, Liang Wu, Yucai Zhang, Huixin Wen, Jiangwei Hu, Zhenxia Huo, Shuyuan Ju, Ruizheng Sheng","doi":"10.1080/0886022X.2025.2468741","DOIUrl":"10.1080/0886022X.2025.2468741","url":null,"abstract":"<p><strong>Background: </strong>This study aims to identify major risk factors for diabetic kidney disease (DKD) and examine their causal relationships using meta-analysis and Mendelian randomization.</p><p><strong>Materials and methods: </strong>This study reviewed diabetic nephropathy literature up to September 2024, evaluating quality with NOS, AMSTAR 2, and JBI. It analyzed heterogeneity using the Baujat plot and leave-one-out method, and conducted meta-analysis with fixed- or random-effects models based on I². Publication bias was assessed with a funnel plot and Egger's test. Mendelian randomization using GWAS SNPs explored causal links through IVW, MR-Egger, weighted median, and weighted mode, while pleiotropy and heterogeneity were checked with the MR-Egger intercept and Cochran's Q.</p><p><strong>Results: </strong>Meta-analysis identified several significant risk factors for DKD, including hypertension (relative risk [RR] = 6.33), comorbidities (RR = 4.96), poor glycemic control (RR = 3.27), non-adherence to treatment (RR = 3.30), an unhealthy diet (RR = 5.96), physical inactivity (RR = 5.60), and hyperuricemia (RR = 5.24). MR analysis further confirmed a causal relationship between high carbohydrate intake (odds ratio [OR] = 1.393, <i>p</i> = 0.043) and increased DKD risk, while vegetable consumption (OR = 0.816, <i>p</i> = 0.011) was identified as a protective factor. These findings reinforce the critical role of dietary and lifestyle interventions in DKD prevention.</p><p><strong>Conclusions: </strong>By integrating meta-analysis with Mendelian randomization, this study provides robust evidence linking modifiable risk factors, particularly dietary habits and lifestyle behaviors, to DKD development. The findings highlight the need for early preventive strategies targeting glycemic control, hypertension, and dietary modifications to mitigate DKD progression.</p>","PeriodicalId":20839,"journal":{"name":"Renal Failure","volume":"47 1","pages":"2468741"},"PeriodicalIF":3.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11984328/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143516523","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":"Chronic kidney disease management in patients with a failing graft: a comparative study with incident non-transplant hemodialysis patients.","authors":"Ana Rita Silva, Maria Guedes Marques, Luís Rodrigues, Lídia Santos, Catarina Romãozinho, Francisco Caramelo, Helena Sá, Arnaldo Figueiredo, Rui Alves, Rita Leal","doi":"10.1080/0886022X.2024.2447791","DOIUrl":"10.1080/0886022X.2024.2447791","url":null,"abstract":"","PeriodicalId":20839,"journal":{"name":"Renal Failure","volume":"47 1","pages":"2447791"},"PeriodicalIF":3.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11731143/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142972057","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":"Construction of a C-reactive protein-albumin-lymphocyte index-based prediction model for all-cause mortality in patients on maintenance hemodialysis.","authors":"Junmin Huang, Junfeng Hao, Huasheng Luo, Lu Chen, Hongying Luo, Huafeng Liu, Yongzhi Xu, Peng Wang","doi":"10.1080/0886022X.2024.2444396","DOIUrl":"10.1080/0886022X.2024.2444396","url":null,"abstract":"<p><strong>Objective: </strong>The mortality rate of patients undergoing maintenance hemodialysis (MHD) remains high. The C-reactive protein-albumin-lymphocyte (CALLY) index is a novel biomarker that reflects inflammation, nutritional and immune status, all merged into one single derived parameter. No study has yet linked the CALLY index to survival in hemodialysis. This study aims to explore the correlation between the CALLY index and mortality in MHD patients, and develop and validate a nomogram to estimate the likelihood of death in this population.</p><p><strong>Methods: </strong>This retrospective cohort study collected data from 436 patients and they were divided into survival group (<i>n</i> = 335) and non-survival group (<i>n</i> = 101). Multivariate logistic regression analysis was used to screen factors associated with death, and nomograms were developed to estimate the risk of death in MHD patients. The discrimination and calibration of nomograms were validated using the area under the receiver operating characteristic (ROC) curve (AUC) and calibration curve. In the study, stratification analysis and covariate adjustment were conducted to explore the correlation between the CALLY index and the mortality of MHD patients.</p><p><strong>Results: </strong>In the final model, logistic regression showed that the CALLY index, creatinine, triglycerides, dialysis duration, absolute neutrophil count, blood urea nitrogen, sodium and ferritin were variables associated with mortality in MHD patients. A nomogram was developed to assess the risk of death in MHD patients. The AUC of the model was 0.821 (95% CI: 0.778-0.861). The results of stratified analysis and calibration model showed that the CALLY index was a protective factor for maintaining the mortality of MHD patients.</p><p><strong>Conclusions: </strong>The CALLY index is closely related to the mortality of MHD patients. A nomogram constructed based on CALLY index can effectively evaluate the mortality risk of MHD patients.</p>","PeriodicalId":20839,"journal":{"name":"Renal Failure","volume":"47 1","pages":"2444396"},"PeriodicalIF":3.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11734386/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142984616","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":"Public interest in chronic kidney disease and dialysis: a 20-year data analysis.","authors":"Jose Arriola-Montenegro, Wisit Cheungpasitporn, Charat Thongprayoon, Iasmina M Craici, Jing Miao","doi":"10.1080/0886022X.2025.2462253","DOIUrl":"10.1080/0886022X.2025.2462253","url":null,"abstract":"<p><p>Chronic kidney disease (CKD) is a growing global health challenge. As the disease progresses, it can lead to end-stage renal disease, necessitating dialysis or kidney transplantation. However, access to these life-saving treatments is often limited by geographic, financial, and resource constraints, underscoring the importance of public awareness and interest. This study examined global and U.S. search trends related to CKD and dialysis using Google Trends™ data from 2004 to 2024. Public search activity was measured using the Relative Search Interest (RSI) index, which ranges from 0 to 100. Both CKD and dialysis exhibited an upward trend in search activity worldwide and in the U.S., as indicated by a positive slope in linear regression analysis (all <i>p</i> < .0001), though some fluctuations and regional differences were observed. Pearson's correlation analysis demonstrated a strong relationship between the U.S. dialysis RSI scores from Google Trends and real-world dialysis incidence rates from the United States Renal Data System (USRDS) (<i>r</i> = 0.961, <i>p</i> < .0001). Notably, in 2020, search activity for both CKD and dialysis declined, likely due to disruptions caused by the COVID-19 pandemic. The study highlights the potential of Google Trends as a valuable tool for assessing public interest and awareness of kidney health, providing insights that can inform public health strategies and educational initiatives. However, relying solely on Google Trends data to assess public interest is insufficient, due to inherent limitations and biases. Findings derived from search trends should be interpreted with caution and ideally supplemented with additional research methodologies.</p>","PeriodicalId":20839,"journal":{"name":"Renal Failure","volume":"47 1","pages":"2462253"},"PeriodicalIF":3.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11834807/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143433566","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":"Risk prediction for acute kidney disease and adverse outcomes in patients with chronic obstructive pulmonary disease: an interpretable machine learning approach.","authors":"Siqi Jiang, Lingyu Xu, Xinyuan Wang, Chenyu Li, Chen Guan, Lin Che, Yanfei Wang, Xuefei Shen, Yan Xu","doi":"10.1080/0886022X.2025.2485475","DOIUrl":"10.1080/0886022X.2025.2485475","url":null,"abstract":"<p><strong>Background: </strong>Little is known about acute kidney injury (AKI) and acute kidney disease (AKD) in patients with chronic obstructive pulmonary disease (COPD) and COPD mortality based on the acute/subacute renal injury. This study develops machine learning models to predict AKI, AKD, and mortality in COPD patients, utilizing web applications for clinical decisions.</p><p><strong>Methods: </strong>We included 2,829 inpatients from January 2016 to December 2018. Data were split into 80% for training and 20% for testing. Eight machine learning algorithms were used, and model performance was evaluated using various metrics. SHAP was used to visualize the decision process. The best models, assessed using AUROC were used to develop web applications for identifying high-risk patients.</p><p><strong>Results: </strong>The incidence rates were 13.71% for AKI and 15.11% for AKD. The overall mortality rate was 4.84%. LightGBM performed best with AUROC of 0.815, 0.827, and 0.934 in AKI, AKD, and mortality, respectively. Key predictors for AKI were Scr, neutrophil percentage, cystatin c, BUN, and LDH. For AKD, the key predictors were age, AKI grade, HDL-C, Scr, and BUN. The key predictors for mortality included the use of dopamine and epinephrine drugs, cystatin c, renal function trajectory, albumin, and neutrophil percentage. Force plots visualized the prediction process for individual patients.</p><p><strong>Conclusions: </strong>The incidence of AKI and AKD is significant in patients with COPD. Renal function trajectory is crucial for predicting mortality in these patients. Web applications were developed to predict AKI, AKD, and mortality, improving prognosis by identifying high-risk patients and reducing adverse events and disease progression.</p>","PeriodicalId":20839,"journal":{"name":"Renal Failure","volume":"47 1","pages":"2485475"},"PeriodicalIF":3.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11983531/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143804166","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}