Construction of Risk-Prediction Models for Autogenous Arteriovenous Fistula Thrombosis in Patients on Maintenance Hemodialysis.

IF 2.2 3区医学 Q3 HEMATOLOGY

Blood Purification Pub Date : 2024-01-01 Epub Date: 2024-08-01 DOI:10.1159/000540543

Xiaoyu Jin, Yuying Fan, Jingshu Li, Xiaona Qi, Xue Li, Hongyi Li

{"title":"Construction of Risk-Prediction Models for Autogenous Arteriovenous Fistula Thrombosis in Patients on Maintenance Hemodialysis.","authors":"Xiaoyu Jin, Yuying Fan, Jingshu Li, Xiaona Qi, Xue Li, Hongyi Li","doi":"10.1159/000540543","DOIUrl":null,"url":null,"abstract":"Introduction: Autogenous arteriovenous fistula (AVF) is the preferred vascular access in patients undergoing maintenance hemodialysis (MHD). However, complications such as thrombosis may occur. This study aimed to construct and validate a machine learning-based risk-prediction model for AVF thrombosis, hypothesizing that such a model can effectively predict occurrences, providing a foundation for early clinical intervention.Methods: The retrospective longitudinal study included a total of 270 patients who underwent MHD at the Hemodialysis Center of the Second Affiliated Hospital of Harbin Medical University between March 2021 and December 2022. During this study, baseline data and scale information of patients between March 2020 and December 2021 were collected. We recorded outcome indicators between March 2021 and December 2022 for subsequent analyses. Five machine learning models were developed (artificial neural network, logistic regression, ridge classification, random forest, and adaptive boosting). The sensitivity (recall), specificity, accuracy, and precision of each model were evaluated. The effect size of each variable was analyzed and ranked. Models were assessed using the area under the receiver-operating characteristic (AUROC) curve.Results: Among the 270 included patients, 105 had AVF thrombosis (55 male and 50 female patients; age range, 29-79 years; mean age, 56.72 years; standard deviation [SDs], ±13.10 years). Conversely, 165 patients did not have AVF thrombosis (99 male and 66 female patients; age range, 23-79 years; mean age, 53.58 years; SD, ± 13.33 years). During the observation period, approximately 52.6% of patients with AVF experienced long-term complications. The most common complications associated with AVF were thrombosis (105; 38.9%), aneurysm formation (27; 10%), and excessively high output flow (10; 3.7%). Fifty-four (20%) patients with AVF required intervention because of complications associated with vascular access. The AUROC curve of the testing set was between 0.858 and 0.903.Conclusion: In this study, we developed five machine learning models to predict the risk of AVF thrombosis, providing a reference for early clinical intervention.","PeriodicalId":8953,"journal":{"name":"Blood Purification","volume":null,"pages":null},"PeriodicalIF":2.2000,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Blood Purification","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1159/000540543","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/8/1 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"HEMATOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Introduction: Autogenous arteriovenous fistula (AVF) is the preferred vascular access in patients undergoing maintenance hemodialysis (MHD). However, complications such as thrombosis may occur. This study aimed to construct and validate a machine learning-based risk-prediction model for AVF thrombosis, hypothesizing that such a model can effectively predict occurrences, providing a foundation for early clinical intervention.

Methods: The retrospective longitudinal study included a total of 270 patients who underwent MHD at the Hemodialysis Center of the Second Affiliated Hospital of Harbin Medical University between March 2021 and December 2022. During this study, baseline data and scale information of patients between March 2020 and December 2021 were collected. We recorded outcome indicators between March 2021 and December 2022 for subsequent analyses. Five machine learning models were developed (artificial neural network, logistic regression, ridge classification, random forest, and adaptive boosting). The sensitivity (recall), specificity, accuracy, and precision of each model were evaluated. The effect size of each variable was analyzed and ranked. Models were assessed using the area under the receiver-operating characteristic (AUROC) curve.

Results: Among the 270 included patients, 105 had AVF thrombosis (55 male and 50 female patients; age range, 29-79 years; mean age, 56.72 years; standard deviation [SDs], ±13.10 years). Conversely, 165 patients did not have AVF thrombosis (99 male and 66 female patients; age range, 23-79 years; mean age, 53.58 years; SD, ± 13.33 years). During the observation period, approximately 52.6% of patients with AVF experienced long-term complications. The most common complications associated with AVF were thrombosis (105; 38.9%), aneurysm formation (27; 10%), and excessively high output flow (10; 3.7%). Fifty-four (20%) patients with AVF required intervention because of complications associated with vascular access. The AUROC curve of the testing set was between 0.858 and 0.903.

Conclusion: In this study, we developed five machine learning models to predict the risk of AVF thrombosis, providing a reference for early clinical intervention.

查看原文本刊更多论文

构建维持性血液透析患者自体动静脉瘘血栓形成的风险预测模型。

简介：自体动静脉瘘（AVF）是维持性血液透析患者首选的血管通路。然而，可能会出现血栓等并发症。本研究旨在构建并验证基于机器学习的动静脉内瘘血栓形成风险预测模型，假设该模型能有效预测血栓形成的发生，为早期临床干预奠定基础：该回顾性纵向研究纳入了2021年3月至2022年12月期间在哈尔滨医科大学附属第二医院血液透析中心接受维持性血液透析（MHD）的270例患者。本研究收集了 2020 年 3 月至 2021 年 12 月期间患者的基线数据和量表信息。我们记录了 2021 年 3 月至 2022 年 12 月期间的结果指标，用于后续分析。我们开发了五种机器学习模型（人工神经网络、逻辑回归、脊分类、随机森林和自适应提升）。对每个模型的灵敏度（召回率）、特异性、准确度和精确度进行了评估。对每个变量的效应大小进行了分析和排序。使用接受者操作特征曲线下面积（AUROC）对模型进行评估：在纳入的 270 例患者中，有 105 例患有动静脉瘘血栓（男性 55 例，女性 50 例；年龄范围 29-79 岁；平均年龄 56.72 岁；标准差 [SD]，±13.10 岁）。相反，165 名患者没有出现动静脉瘘血栓（男性 99 人，女性 66 人；年龄范围为 23-79 岁；平均年龄为 53.58 岁；标准差 [SD] 为 ±13.33 岁）。在观察期间，约 52.6% 的动静脉瘘患者出现了长期并发症。动静脉瘘最常见的并发症是血栓形成（105 例；38.9%）、动脉瘤形成（27 例；10%）和输出流量过高（10 例；3.7%）。54名（20%）动静脉瘘患者因血管通路相关并发症而需要介入治疗。测试集的 AUROC 曲线介于 0.858 和 0.903 之间：在这项研究中，我们建立了五个机器学习模型来预测动静脉瘘血栓形成的风险，为早期临床干预提供了参考。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Blood Purification 医学-泌尿学与肾脏学

CiteScore

5.80

自引率

3.30%

发文量

审稿时长

6-12 weeks

期刊介绍： Practical information on hemodialysis, hemofiltration, peritoneal dialysis and apheresis is featured in this journal. Recognizing the critical importance of equipment and procedures, particular emphasis has been placed on reports, drawn from a wide range of fields, describing technical advances and improvements in methodology. Papers reflect the search for cost-effective solutions which increase not only patient survival but also patient comfort and disease improvement through prevention or correction of undesirable effects. Advances in vascular access and blood anticoagulation, problems associated with exposure of blood to foreign surfaces and acute-care nephrology, including continuous therapies, also receive attention. Nephrologists, internists, intensivists and hospital staff involved in dialysis, apheresis and immunoadsorption for acute and chronic solid organ failure will find this journal useful and informative. ''Blood Purification'' also serves as a platform for multidisciplinary experiences involving nephrologists, cardiologists and critical care physicians in order to expand the level of interaction between different disciplines and specialities.