维持性血液透析患儿代谢性酸中毒风险预测的决策树模型构建及预测效能分析

doi:10.3761/j.issn.2096-7446.2026.05.004

摘要/Abstract

摘要：

目的对维持性血液透析患儿发生代谢性酸中毒的危险因素进行分析，并构建决策树模型。方法回顾性收集2022年11月—2024年11月南京市某三级甲等医院收治的205例维持性血液透析患儿的临床资料，根据是否发生代谢性酸中毒将其分为代谢性酸中毒组和非代谢性酸中毒组，采用单因素及多因素Logistic回归分析影响维持性血液透析患儿并发代谢性酸中毒的危险因素，采用决策树算法与Logistic回归分析构建风险预测模型，并比较两种模型对维持性血液透析患儿并发代谢性酸中毒的预测价值。结果 205例维持性血液透析患儿中有101例发生代谢性酸中毒，其发生率为49.27%。多因素Logistic回归分析结果显示，糖尿病、营养不良、血尿素氮、血清不饱和铁结合力及血钾等为维持性血液透析患儿并发代谢性酸中毒的危险因素（P<0.05）。根据危险因素构建决策树模型，模型选择血钾、血尿素氮、糖尿病、血清不饱和铁结合力、营养不良等5个解释变量，合计5层，共22个节点，其中血钾为维持性血液透析患儿并发代谢性酸中毒最为重要的影响因素。维持性血液透析患儿并发代谢性酸中毒的决策树模型受试者操作特征曲线下面积为0.928（95%CI：0.883~0.959），Logistic回归模型受试者操作特征曲线下面积为0.901（95%CI：0.852~0.938），两种模型的Delong检验结果为Z=2.453，P<0.001。结论糖尿病、营养不良、血尿素氮、血清不饱和铁结合力及血钾为维持性血液透析患儿并发代谢性酸中毒的危险因素，根据危险因素构建的决策树风险预测模型具有较高的预测效能，可为临床医务人员更准确地预测和实施针对性的预防措施提供理论依据。

关键词: 维持性血液透析, 儿童, 代谢性酸中毒, 决策树算法, 风险预测模型

Abstract:

Objective To analyze the risk factors of metabolic acidosis in children undergoing maintenance hemodialysis and construct a decision tree model. Methods The clinical data of 205 children undergoing maintenance hemodialysis admitted to a tertiary general hospital from November 2022 to November 2024 were retrospectively selected. They were divided into metabolic acidosis group and non-metabolic acidosis group according to the occurrence of metabolic acidosis. Univariate and multivariate logistic regression analyses were used to analyze the risk factors affecting metabolic acidosis in children undergoing maintenance hemodialysis. Decision tree algorithm and logistic regression algorithm were used to construct risk prediction models，and the predictive values of the two models for metabolic acidosis in children undergoing maintenance hemodialysis were compared. Results Among the 205 children undergoing maintenance hemodialysis，101 cases developed metabolic acidosis，with an incidence rate of 49.27%. Multivariate logistic regression analysis showed that diabetes mellitus，malnutrition，blood urea nitrogen，serum unsaturated iron binding capacity and blood potassium were risk factors for metabolic acidosis in children undergoing maintenance hemodialysis（P<0.05）. A decision tree model was constructed based on the risk factors，which selected 5 explanatory variables including blood potassium，blood urea nitrogen，diabetes mellitus，serum unsaturated iron binding capacity and malnutrition，with a total of 5 layers and 22 nodes. Among them，blood potassium was the most important influencing factor for metabolic acidosis in children undergoing maintenance hemodialysis. The AUC value of the decision tree model for metabolic acidosis in children undergoing maintenance hemodialysis was 0.928（95%CI：0.883~0.959），and the AUC value of the logistic regression model was 0.901（95%CI：0.852~0.938）. The Delong test results of the two models showed Z=2.453，P<0.001. Conclusion Diabetes mellitus，malnutrition，blood urea nitrogen，serum unsaturated iron binding capacity and blood potassium are risk factors for metabolic acidosis in children undergoing maintenance hemodialysis. The decision tree risk prediction model constructed based on these risk factors has high predictive efficiency，providing a scientific and effective theoretical basis for clinical medical staff to provide more accurate prediction and implement targeted preventive measures.

Key words: Maintenance Hemodialysis, Children, Metabolic Acidosis, Decision Tree Algorithm, Risk Prediction

夏镭, 赵蕾, 陈丹. 维持性血液透析患儿代谢性酸中毒风险预测的决策树模型构建及预测效能分析[J]. 中华急危重症护理杂志, 2026, 7(5): 540-545.

XIA Lei, ZHAO Lei, CHEN Dan. Construction of a decision tree model for risk prediction of metabolic acidosis in maintenance hemodialysis children and analysis of its predictive performance[J]. Chinese Journal of Emergency and Critical Care Nursing, 2026, 7(5): 540-545.

图/表 5

参考文献 18

[1]	Iguidbashian J, Imran R, Yi JA. Maintenance and salvage of he-modialysis access[J]. 2023, 103(4):685-701.
[2]	沈茜, 方晓燕, 孙玉, 等. 维持性腹膜透析和血液透析治疗儿童终末期肾病的临床分析和疗效比较[J]. 中国血液净化, 2019, 18(6):402-405.
	Shen Q, Fang XY, Sun Y, et al. A comparative study of peritoneal dialysis and hemodialysis for end-stage renal disease children[J]. Chin J Blood Purif, 2019, 18(6):402-405.
[3]	陈进忠, 张炜, 潘健怡, 等. 珠三角地区血液透析患者代谢性酸中毒与心脏瓣膜钙化的相关关系:多中心横断面研究[J]. 中华肾脏病杂志, 2021(2):113-120. doi: 10.3760/cma.j.cn441217-20200428-00019
	Chen JZ, Zhang W, Pan JY, et al. Correlation analysis between metabolic acidosis and cardiac valve calcification in hemodialysis patients in the Pearl River Delta Region:a multicenter cross-sectional study[J]. Chin J Nephrol, 2021(2):113-120.
[4]	于小勇, 徐新丽. AKI对身体主要器官的影响[J]. 中国中西医结合肾病杂志, 2024, 25(2):101.
	Yu XY, Xu XL. The impact of AKI on the main organs of the body[J]. Chin J Integr Tradit West Nephrol, 2024, 25(2):101.
[5]	冉海鸿. 西宁维持性血液透析间期患者代谢性酸中毒的相关危险因素分析[D]. 西宁: 青海大学, 2022.
	Ran HH. Analysis of related risk factors of metabolicacidosis in patients with maintenance hemodialysisin Xining[D]. Xining: Qinghai University, 2022.
[6]	Costa A, Pais M, Loureiro J, et al. Decision tree-based classification as a support to diagnosis in the Alzheimer’s disease continuum using cerebrospinal fluid biomarkers:insights from automated analysis[J]. Braz J Psychiatry, 2022, 44(4):370-377.
[7]	Toyoda H, Terai H, Yamada K, et al. A decision tree analysis to predict clinical outcome of minimally invasive lumbar decompression surgery for lumbar spinal stenosis with and without coexisting spondylolisthesis and scoliosis[J]. 2023, 23(7):973-981.
[8]	Kidney Disease:Improving Global Outcomes(KDIGO) CKD Work Group. KDIGO 2024 clinical practice guideline for the evaluation and management of chronic kidney disease[J]. Kidney Int, 2024, 105(4S):S117-S314. doi: 10.1016/j.kint.2023.10.018 pmid: 38490803
[9]	陈功勋, 朱登纳, 王玉梅, 等. 主观全面营养评估工具(SGNA)在住院神经损伤患儿中的应用[J]. 临床儿科杂志, 2024, 42(11):962-967.
	Chen GX, Zhu DN, Wang YM, et al. Application of subjective global nutritional assessment tool(SGNA) in the nutritional assessment of hospitalized children with neurologically impairment[J]. J Clin Pediatr, 2024, 42(11):962-967.
[10]	郑春雄, 胡良勇, 吴杰, 等. 血液透析装置应用于儿童血液透析治疗时的量值溯源和质量控制问题探讨[J]. 中国计量, 2022,(9):59-60.
	Zheng CX, Hu LY, Wu J, et al. Discussion on the traceability of measurement values and quality control issues when hemodialysis devices are applied in children’s hemodialysis treatment[J]. China Metrol, 2022,(9):59-60.
[11]	刘文彦, 李宇红, 徐海霞, 等. 20例儿童原发性远端肾小管酸中毒的临床表型与基因分析[J]. 实用临床医药杂志, 2023, 27(6):123-127.
	Liu WY, Li YH, Xu HX, et al. Clinical phenotype of 20 children with primary distal renal tubular acidosis and their gene analysis[J]. J Clin Med Pract, 2023, 27(6):123-127.
[12]	万静芳, 陈客宏. 维持性血液透析患者最佳透析液碳酸氢盐浓度的研究进展[J]. 实用医学杂志, 2024, 40(18):2520-2524.
	Wan JF, Chen KH. Advances in research on optimal dialysate bicarbonate concentration for maintenance hemodialysis patients[J]. J Pract Med, 2024, 40(18):2520-2524.
[13]	李拱榆, 曲廖准, 唐小玲. 不同透析方式及透析龄终末期肾病患者代谢性酸中毒的相关因素分析[J]. 中国中西医结合肾病杂志, 2024, 25(3):255-257.
	Li GY, Qu LZ, Tang XL. Analysis of related factors of metabolic acidosis in patients with end-stage renal disease under Different dialysis methods and dialysis ages[J]. Chin J Integr Tradit West Nephrol, 2024, 25(3):255-257.
[14]	师伟严. 肌酸和碳酸氢钠的补充对男子大学生足球运动员体成分、速度和下肢力量的影响研究[D]. 兰州: 西北民族大学, 2023.
	Shi WY. Effects of creatine and sodium bicarbonate supplementation on body composition,speed,and lower limb strength of male college football players[D]. Lanzhou: Northwest Minzu University, 2023.
[15]	胡婷, 肖琼, 郭月菲, 等. 连续肾脏替代疗法中应用枸橼酸钠抗凝后发生代谢性酸中毒的危险因素分析[J]. 现代消化及介入诊疗, 2022, 24(1):90-91.
	Hu T, Xiao Q, Guo YF, et al. Risk factor analysis of metabolic acidosis after citrate sodium anticoagulation in continuous renal replacement therapy[J]. Mod Interv Diagn Treat, 2022, 24(1):90-91.
[16]	冉海鸿, 李伟. 高海拔地区维持性血液透析间期患者代谢性酸中毒的发生及不良结局[J]. 临床医学进展, 2022, 12(1):343-351.
	Ran HH, Li W. Incidence and adverse outcome of metabolic acidosis in maintenance hemodialysis patients at high altitude[J]. Adv Clin Med, 2022, 12(1):343-351. doi: 10.12677/ACM.2022.121052
[17]	Tanaka S, Jung H, Yamashina S, et al. Clinical prediction rule for locomotive syndrome in older adults:a decision tree model[J]. J Orthop Sci, 2023, 28(4):886-894. doi: 10.1016/j.jos.2022.04.008
[18]	Kim K, Woo S, Kim SH, et al. The prediction model of non-suicidal self-injury in psychiatric patients using decision tree analysis[J]. Yonsei Med J, 2024, 65(3):137-147. doi: 10.3349/ymj.2023.0129 pmid: 38373833