Objective  To investigate the influencing factors of arteriovenous fistula (AVF) maturation failure in hemodialysis patients, and to construct a risk prediction model for AVF maturation failure based on machine learning algorithms.

Methods  Patients who underwent initial AVF formation at Kaifeng People's Hospital from January 2021 to January 2025 were selected as the study subjects. Relevant medical records were collected, and patients were divided into a normal group and a maturation failure group based on whether maturation failure occurred within 12 weeks after AVF formation. The patients were then split into training and validation sets in a 7 : 3 ratio. Logistic regression, extreme gradient boosting (XGBoost), random forest (RF), and gradient boosting machine (GBM) algorithms were used to identify factors influencing AVF maturation failure. A predictive nomogram, calibration curve, and receiver operating characteristic curve were plotted.

Results  A total of 260 patients undergoing initial AVF formation were included, with 143 in the normal group and 117 in the maturation failure group, 182 in the training set and 78 in the validation set. Multivariate Logistic regression results indicated that age and ALB were independent influencing factors. The XGBoost, RF, and GBM algorithms identified 20, 21, and 19 risk factors for AVF maturation failure, respectively. Age, ALB, GLU, and Hb were common variables across all models. The nomogram model constructed based on these variables demonstrated high predictive accuracy the AUCs of the training set and validation set were 0.881[95%CI (0.829, 0.933)] and 0.912 [95%CI (0.838, 0.986)], respectively.

Conclusion  Age, ALB, Hb, and GLU are the key factors affecting AVF maturation failure in hemodialysis patients. The risk prediction model developed using these indicators exhibits excellent predictive performance and may assist clinicians in selecting vascular access strategies and preventing  complications.

1.Zhang Y, Kong X, Liang L, et al. Regulation of vascular remodeling by immune microenvironment after the establishment of autologous arteriovenous fistula in ESRD patients[J]. Front Immunol, 2024, 15: 1365422. DOI: 10.3389/fimmu.2024.1365422.

2.Konner K, Nonnast-Daniel B, Ritz E. The arteriovenous fistula[J]. J Am Soc Nephrol, 2003, 14(6): 1669-1680. DOI: 10.1097/01.asn.0000069219.88168.39.

3.中华医学会肾脏病学分会专家组. 透析通路中国指南（2024年版）[J]. 中华肾脏病杂志, 2024, 40(12): 990-1070. [Chinese Society of Nephrology. Guidelines for dialysis access in China (2024)[J]. Chinese Journal of Nephrology, 2024, 40(12): 990-1070.] DOI: 10.3760/cma.j.cn441217-20230926-00935.

4.赵彬, 王慧, 王玉柱, 等. 自体动静脉内瘘成熟的预测因素及辅助成熟干预时机的初步探讨[J]. 中华肾脏病杂志, 2023, 39(4): 263-271. [Zhao B, Wang H, Wang YZ, et al. Predictive factors of autogenous arteriovenous fistula maturation and preliminary study on assisted maturation intervention timing[J]. Chinese Journal of Nephrology, 2023, 39(4): 263-271.] DOI: 10.3760/cma.j.cn441217-20220920-00933.

5.Bi WL, Hosny A, Schabath MB, et al. Artificial intelligence in cancer imaging: clinical challenges and applications[J]. CA Cancer J Clin, 2019, 69(2): 127-157. DOI: 10.3322/caac.21552.

6.Tran KA, Kondrashova O, Bradley A, et al. Deep learning in cancer diagnosis, prognosis and treatment selection[J]. Genome Med, 2021, 13(1): 152. DOI: 10.1186/s13073-021-00968-x.

7.张雷, 胡鑫涛, 陈巍, 等. 基于机器学习算法构建多病共存老年人轻度认知功能障碍预测模型[J]. 医学新知, 2025, 35(4): 409-418. [Zhang L, Hu XT, Chen W, et al. Constructing a predictive model for mild cognitive impairment in elderly individuals with coexisting multiple diseases based on machine learning algorithms[J]. Yixue Xinzhi Zazhi , 2025, 35(4): 409-418.] DOI: 10.12173/j.issn.1004-5511.202312108.

8.Feng C, Liu F. Artificial intelligence in renal pathology: current status and future[J]. Biomol Biomed, 2023, 23(2): 225-234. DOI: 10.17305/bjbms.2022.8318.

9.Sassanarakkit S, Hadpech S, Thongboonkerd V. Theranostic roles of machine learning in clinical management of kidney stone disease[J]. Comput Struct Biotechnol J, 2022, 21: 260-266. DOI: 10.1016/j.csbj.2022.12.004.

10.Aslan MF, Sabanci K. A novel proposal for deep learning-based diabetes prediction: converting clinical data to image data[J]. Diagnostics (Basel), 2023, 13(4): 796. DOI: 10.3390/diagnostics13040796.

11.Matsushita FY, Krebs VLJ, de Carvalho WB. Complete blood count and C-reactive protein to predict positive blood culture among neonates using machine learning algorithms[J]. Clinics (Sao Paulo), 2022, 78: 100148. DOI: 10.1016/j.clinsp.2022.100148.

12.Hu Y, Irinyi L, Hoang MTV, et al. Inferring species compositions of complex fungal communities from long- and short-read sequence data[J]. mBio, 2022, 13(2): e0244421. DOI: 10.1128/mbio.02444-21.

13.武煜, 陈炳华, 张林, 等. 老年维持性血液透析患者血管通路超声影像及血栓形成的风险预测[J]. 中国老年学杂志, 2025, 45(10): 2374-2379. [Wu Y, Chen BH, Zhang L, et al. Ultrasonographic imaging of vascular access and risk prediction of thrombosis in elderly maintenance hemodialysis patients[J]. Chinese Journal of Gerontology, 2025, 45(10): 2374-2379.] DOI: 10.3969/j.issn.1005-9202.

14.李鸿博. 维持性血液透析患者自体动静脉内瘘并发症的危险因素分析及风险预测模型的构建[J]. 中国血液净化, 2023, 22(11): 861-865. [Li HB. Analysis of risk factors and construction of a risk prediction model for the complications of autologous arteriovenous fistula in maintenance hemodialysis patients[J]. Chinese Journal of Blood Purification, 2023, 22(11): 861-865.] DOI: 10.3969/j.issn.1671-4091.2023.11.014.

15.何静, 梅吉本, 胡艳, 等. 维持性血液透析患者自体动静脉内瘘功能不良及PTA术后狭窄的影响因素分析[J]. 中南医学科学杂志, 2025, 53(4): 720-723, 727. [He J, Mei JB, Hu Y, et al. Analysis of influencing factors of autogenous arteriovenous fistula dysfunction and post-PTA stenosis in maintenance hemodialysis patients[J]. Medical Science Journal of Central South China, 2025, 53(4): 720-723, 727.] DOI: 10.15972/j.cnki.43-1509/r.2025.04.039.

16.Wong E, Ballew SH, Daya N, et al. Hospitalization risk among older adults with chronic kidney disease[J]. Am J Nephrol, 2019, 50(3): 212-220. DOI: 10.1159/000501539.

17.Liu XY, Li ZW, Zhang B, et al. Effects of preoperative bicarbonate and lactate levels on short-term outcomes and prognosis in elderly patients with colorectal cancer[J]. BMC Surg, 2023, 23(1): 127. DOI: 10.1186/s12893-023-02039-x.

18.Iizaka S, Sanada H, Matsui Y, et al. Serum albumin level is a limited nutritional marker for predicting wound healing in patients with pressure ulcer: two multicenter prospective cohort studies[J]. Clin Nutr, 2011, 30(6): 738-745. DOI: 10.1016/j.clnu.2011.07.003.

19.Chen J, Shao J, Zhang X, et al. Monitoring early dynamic changes of plasma cell-free DNA and pretreatment pre-albumin to predict chemotherapy effectiveness and survival outcomes in advanced non-small cell lung cancer[J]. Ann Transl Med, 2022, 10(5): 253. DOI: 10.21037/atm-22-12.

20.Shi CH, Wang C, Bai R, et al. Associations among glycemic excursions, glycated hemoglobin and high-sensitivity C-reactive protein in patients with poorly controlled type 2 diabetes mellitus[J]. Exp Ther Med, 2015, 10(5): 1937-1942. DOI: 10.3892/etm.2015.2730.

21.Pothen L, Verdoy R, De Mulder D, et al. Sustained downregulation of vascular smooth muscle acta2 after transient angiotensin II infusion: a new model of "vascular memory"[J]. Front Cardiovasc Med, 2022, 9: 854361. DOI: 10.3389/fcvm.2022.854361.

22.Yang L, Chen W, Li B, et al. Circular RNA circ_0026218 suppressed atherosclerosis progression via miR-338-3p/SIRT6 Axis[J]. Biomed Res Int, 2023, 2023: 5647758. DOI: 10.1155/2023/5647758.

23.Wu F, Wang JY, Dorman B, et al. c-Jun-mediated miR-19b expression induces endothelial barrier dysfunction in an in vitro model of hemorrhagic shock[J]. Mol Med, 2022, 28(1): 123. DOI: 10.1186/s10020-022-00550-0.