{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T05:24:42Z","timestamp":1786944282970,"version":"build-2736575974"},"reference-count":32,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T00:00:00Z","timestamp":1786924800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Surg."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Arteriovenous fistula (AVF) dysfunction remains a major challenge in patients with end-stage renal disease (ESRD) undergoing hemodialysis. This study aimed to develop and evaluate an interpretable machine learning model based on clinical variables and preoperative laboratory parameters to predict AVF dysfunction.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective study included patients with ESRD who underwent creation of a new autogenous AVF between January 2021 and December 2023. AVF dysfunction was defined as clinically relevant inadequate access function caused by AVF stenosis, occlusion, or thrombosis within 1 year after AVF creation. Candidate predictors included preoperative clinical variables, routine laboratory parameters, and derived composite indices. The overall cohort was randomly divided into train and test cohorts. Five machine learning models, including XGBoost, random forest, Naive Bayes, support vector machine, and logistic regression, were developed and compared.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Among the 696 patients, 130 (18.7%) developed AVF dysfunction within 1 year. Through recursive feature elimination-based feature selection, six predictors were selected for the final model, including hemoglobin (HB), aggregate index of systemic inflammation (AISI), dialysis vintage, calcium\u2013phosphorus product, triglycerides, and C-reactive protein-to-albumin ratio. The XGBoost model showed favorable discrimination, with AUCs of 0.915 in the train cohort and 0.912 in the test cohort, as well as favorable overall performance in terms of area under the precision\u2013recall curve, sensitivity, specificity, positive and negative predictive values, accuracy, and\n                      <jats:italic>F<\/jats:italic>\n                      1-score. The calibration plot, Brier scores, calibration intercepts, and calibration slopes of XGBoost were also acceptable. Decision curve analysis indicated positive net benefit across a range of threshold probabilities. SHAP analysis identified HB, AISI, and dialysis vintage as the leading contributors to model predictions.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>An interpretable XGBoost model based on six preoperative variables was developed to predict AVF dysfunction within 1 year after AVF creation in patients with ESRD.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fsurg.2026.1860573","type":"journal-article","created":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T04:36:44Z","timestamp":1786941404000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["An interpretable XGBoost model for predicting arteriovenous fistula dysfunction in end stage renal disease"],"prefix":"10.3389","volume":"13","author":[{"given":"Run","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Nephrology, The First Hospital Affiliated to Army Medical University","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiongfang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Nephrology, The First Hospital Affiliated to Army Medical University","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaolan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Nephrology, The First Hospital Affiliated to Army Medical University","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Nephrology, The First Hospital Affiliated to Army Medical University","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengjie","family":"Cai","sequence":"additional","affiliation":[{"name":"Department of Nephrology, The First Hospital Affiliated to Army Medical University","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Na","family":"Yin","sequence":"additional","affiliation":[{"name":"Department of Nephrology, The First Hospital Affiliated to Army Medical University","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pan","family":"Xie","sequence":"additional","affiliation":[{"name":"Department of Nephrology, The First Hospital Affiliated to Army Medical University","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Nephrology, The First Hospital Affiliated to Army Medical University","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lihua","family":"Fu","sequence":"additional","affiliation":[{"name":"Department of Nephrology, The First Hospital Affiliated to Army Medical University","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,17]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"S1","DOI":"10.1053\/j.ajkd.2019.12.001","article-title":"KDOQI clinical practice guideline for vascular access: 2019 update","volume":"75","author":"Lok","year":"2020","journal-title":"Am J Kidney Dis"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1111","DOI":"10.1001\/jamasurg.2021.4527","article-title":"Arteriovenous fistula maturation, functional patency, and intervention rates","volume":"156","author":"Huber","year":"2021","journal-title":"JAMA Surg"},{"key":"B3","doi-asserted-by":"publisher","first-page":"608","DOI":"10.1177\/1129729819826037","article-title":"Role of neutrophil-to-lymphocyte ratio as a prognostic indicator for hemodialysis arteriovenous fistula failure","volume":"20","author":"Wongmahisorn","year":"2019","journal-title":"J Vasc Access"},{"key":"B4","doi-asserted-by":"publisher","first-page":"735","DOI":"10.1177\/11297298241237830","article-title":"A systematic review of prediction models on arteriovenous fistula: risk scores and machine learning approaches","volume":"26","author":"Meng","year":"2025","journal-title":"J Vasc Access"},{"key":"B5","doi-asserted-by":"publisher","first-page":"e110937","DOI":"10.7759\/cureus.110937","article-title":"Machine learning and artificial intelligence approaches for predicting arteriovenous fistula dysfunction in hemodialysis: a systematic review","volume":"18","author":"Ahmed Mohammed","year":"2026","journal-title":"Cureus"},{"key":"B6","doi-asserted-by":"publisher","first-page":"12355","DOI":"10.3390\/ijerph182312355","article-title":"Development and validation of a machine learning model predicting arteriovenous fistula failure in a large network of dialysis clinics","volume":"18","author":"Peralta","year":"2021","journal-title":"Int J Environ Res Public Health"},{"key":"B7","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1038\/s41746-022-00710-w","article-title":"Predicting radiocephalic arteriovenous fistula success with machine learning","volume":"5","author":"Heindel","year":"2022","journal-title":"NPJ Digit Med"},{"key":"B8","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1038\/s41746-025-02187-9","article-title":"Predicting 1-year successful clinical use of an arteriovenous access for hemodialysis using machine learning","volume":"9","author":"Li","year":"2025","journal-title":"NPJ Digit Med"},{"key":"B9","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1186\/s40001-025-02490-x","article-title":"Machine learning-based risk prediction model for arteriovenous fistula stenosis","volume":"30","author":"Shu","year":"2025","journal-title":"Eur J Med Res"},{"key":"B10","doi-asserted-by":"publisher","first-page":"19203","DOI":"10.1038\/s41598-025-04310-y","article-title":"Predicting long-term patency of radiocephalic arteriovenous fistulas with machine learning and the PREDICT-AVF web app","volume":"15","author":"Fitzgibbon","year":"2025","journal-title":"Sci Rep"},{"key":"B11","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1186\/s12882-025-04201-4","article-title":"Machine learning-based prediction model for arteriovenous fistula thrombosis risk: a retrospective cohort study from 2017 to 2024","volume":"26","author":"Shu","year":"2025","journal-title":"BMC Nephrol"},{"key":"B12","doi-asserted-by":"publisher","first-page":"2150","DOI":"10.3390\/medicina61122150","article-title":"Development of a machine learning-based predictive model for arteriovenous fistula occlusion after surgery: a retrospective cohort study from 2015 to 2025","volume":"61","author":"Lee","year":"2025","journal-title":"Medicina"},{"key":"B13","doi-asserted-by":"publisher","first-page":"e37737","DOI":"10.1097\/MD.0000000000037737","article-title":"Retrospective analysis of predictive factors for AVF dysfunction in patients undergoing MHD","volume":"103","author":"Wang","year":"2024","journal-title":"Medicine"},{"key":"B14","doi-asserted-by":"publisher","first-page":"17659","DOI":"10.1038\/s41598-023-35444-6","article-title":"An effective AI model for automatically detecting arteriovenous fistula stenosis","volume":"13","author":"Song","year":"2023","journal-title":"Sci Rep"},{"key":"B15","doi-asserted-by":"publisher","first-page":"793","DOI":"10.1053\/j.ajkd.2017.11.020","article-title":"Arteriovenous fistula maturation in prevalent hemodialysis patients in the United States: a national study","volume":"71","author":"Woodside","year":"2018","journal-title":"Am J Kidney Dis"},{"key":"B16","doi-asserted-by":"publisher","first-page":"2464","DOI":"10.3390\/biomedicines12112464","article-title":"Arterio-venous fistula calcifications-risk factors and clinical relevance","volume":"12","author":"Grosu","year":"2024","journal-title":"Biomedicines"},{"key":"B17","doi-asserted-by":"publisher","first-page":"241","DOI":"10.24920\/004411","article-title":"Predictive value of systemic immune inflammation index, aggregate index of systemic inflammation, and systemic inflammation response index in lower extremity deep venous thrombosis following severe trauma","volume":"39","author":"Li","year":"2024","journal-title":"Chin Med Sci J"},{"key":"B18","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.atherosclerosis.2020.04.018","article-title":"Platelet-leukocyte interplay during vascular disease","volume":"307","author":"Schrottmaier","year":"2020","journal-title":"Atherosclerosis"},{"key":"B19","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1111\/sdi.12365","article-title":"Pre-existing arterial micro-calcification predicts primary unassisted arteriovenous fistula failure in incident hemodialysis patients","volume":"28","author":"Choi","year":"2015","journal-title":"Semin Dial"},{"key":"B20","doi-asserted-by":"publisher","first-page":"e0120266","DOI":"10.1371\/journal.pone.0120266","article-title":"Precedent fluctuation of serum hs-CRP to albumin ratios and mortality risk of clinically stable hemodialysis patients","volume":"10","author":"Hwang","year":"2015","journal-title":"PLoS One"},{"key":"B21","doi-asserted-by":"publisher","first-page":"326","DOI":"10.1186\/s12872-024-03995-9","article-title":"The predictive value of cardiovascular outcomes and mortality assessed by the c-reactive protein to albumin ratio in the UK biobank","volume":"24","author":"W\u00e4ndell","year":"2024","journal-title":"BMC Cardiovasc Disord"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1416","DOI":"10.1177\/11297298221115557","article-title":"Novel insights into modifiable risk factors for arteriovenous fistula failure and the importance of CKD lipid profile: a meta-analysis","volume":"25","author":"Wei","year":"2024","journal-title":"J Vasc Access"},{"key":"B23","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1177\/03913988241269534","article-title":"Evaluation of the relationship between proximal upper-extremity arteriovenous fistula patency and atherogenic index of plasma","volume":"47","author":"Pala","year":"2024","journal-title":"Int J Artif Organs"},{"key":"B24","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1177\/11297298211011864","article-title":"Effects of plasma atherogenic index and plasma osmolality on arteriovenous fistula patency in hemodialysis patients","volume":"24","author":"G\u00fcven","year":"2023","journal-title":"J Vasc Access"},{"key":"B25","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.krcp.2015.02.001","article-title":"Hyperphosphatemia is associated with patency loss of arteriovenous fistula after 1 year of hemodialysis","volume":"34","author":"Moon","year":"2015","journal-title":"Kidney Res Clin Pract"},{"key":"B26","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1053\/ajkd.1998.v31.pm9531176","article-title":"Association of serum phosphorus and calcium x phosphate product with mortality risk in chronic hemodialysis patients: a national study","volume":"31","author":"Block","year":"1998","journal-title":"Am J Kidney Dis"},{"key":"B27","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1177\/1708538118814611","article-title":"Calcium phosphate product level as a predictor for arteriovenous fistula re-operations in patients with chronic renal failure","volume":"27","author":"T\u00fcys\u00fcz","year":"2019","journal-title":"Vascular"},{"key":"B28","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1186\/s13037-025-00449-9","article-title":"Predictors of early arteriovenous fistula failure in patients with end stage renal disease on hemodialysis: a systematic review and meta-analysis","volume":"19","author":"Salih","year":"2025","journal-title":"Patient Saf Surg"},{"key":"B29","doi-asserted-by":"publisher","first-page":"255","DOI":"10.4174\/astr.2024.106.5.255","article-title":"Predicting factors for early failure of vascular access in hemodialysis patients","volume":"106","author":"Kim","year":"2024","journal-title":"Ann Surg Treat Res"},{"key":"B30","doi-asserted-by":"publisher","first-page":"1432437","DOI":"10.3389\/fmed.2024.1432437","article-title":"Nomogram-based prediction of the risk of AVF maturation: a retrospective study","volume":"11","author":"Zhao","year":"2024","journal-title":"Front Med"},{"key":"B31","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1186\/s12882-025-04182-4","article-title":"Prevailing insights into anastomotic angles of surgically created arteriovenous fistulas: a literature review","volume":"26","author":"Li","year":"2025","journal-title":"BMC Nephrol"},{"key":"B32","doi-asserted-by":"publisher","first-page":"5946","DOI":"10.3390\/jcm12185946","article-title":"Cannulation technique of vascular access in hemodialysis and the impact on the arteriovenous fistula survival: systematic review and meta-analysis","volume":"12","author":"Peralta","year":"2023","journal-title":"J Clin Med"}],"container-title":["Frontiers in Surgery"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fsurg.2026.1860573\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T04:36:48Z","timestamp":1786941408000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fsurg.2026.1860573\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,17]]},"references-count":32,"alternative-id":["10.3389\/fsurg.2026.1860573"],"URL":"https:\/\/doi.org\/10.3389\/fsurg.2026.1860573","relation":{},"ISSN":["2296-875X"],"issn-type":[{"value":"2296-875X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,17]]},"article-number":"1860573"}}