Prediction of intradialytic hypotension by machine learning: A systematic review.

IF 2.7 4区 医学 Q2 UROLOGY & NEPHROLOGY
Jacob Ninan, Nasrin Nikravangolsefid, Hong Hieu Truong, Mariam Charkviani, Larry J Prokop, Raghavan Murugan, Gilles Clermont, Kianoush B Kashani, Juan Pablo Domecq Garces
{"title":"Prediction of intradialytic hypotension by machine learning: A systematic review.","authors":"Jacob Ninan, Nasrin Nikravangolsefid, Hong Hieu Truong, Mariam Charkviani, Larry J Prokop, Raghavan Murugan, Gilles Clermont, Kianoush B Kashani, Juan Pablo Domecq Garces","doi":"10.1007/s40620-025-02288-4","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Intradialytic hypotension is associated with increased morbidity, and mortality. Several machine learning (ML) algorithms have been recently developed to predict intradialytic hypotension. We systematically reviewed ML models employed to predict intradialytic hypotension, their performance, methodological integrity, and clinical applicability.</p><p><strong>Methods: </strong>We conducted this systematic review with a pre-established protocol registered at the International Prospective Register of Systematic Reviews (PROSPERO ID: CRD42022362194). Six databases, from their inception to July 20, 2023, were comprehensively searched. Two independent investigators reviewed the articles, extracted data, and evaluated the risk of bias using the Prediction model Risk of Bias Assessment Tool (PROBAST).</p><p><strong>Results: </strong>Out of 84 screened articles, 16 studies with 14,500 adult patients on hemodialysis were included in the review. Fourteen studies (87.5%) were found to have a high risk of bias. The intradialytic hypotension prevalence in the population investigated was between 1.2 and 51%. A diverse range of predictive ML tools were used to predict intradialytic hypotension, with various neural networking models being the most frequent, appearing in 13 studies (AUROC ranges: 0.684-0.978). One study performed both internal and external validation.</p><p><strong>Conclusions: </strong>Researchers have made a concerted effort to develop ML tools to predict intradialytic hypotension. Despite their significant efforts, the lack of thorough external and clinical validation, and heterogeneity among the models and settings have resulted in a substantial challenge to offering ML tools as a global intradialytic hypotension prevention and management solution. Future studies should focus on external and clinical validation of these models to enhance the chances of clinically relevant changes in clinical practices.</p>","PeriodicalId":16542,"journal":{"name":"Journal of Nephrology","volume":" ","pages":""},"PeriodicalIF":2.7000,"publicationDate":"2025-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Nephrology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s40620-025-02288-4","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"UROLOGY & NEPHROLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Background: Intradialytic hypotension is associated with increased morbidity, and mortality. Several machine learning (ML) algorithms have been recently developed to predict intradialytic hypotension. We systematically reviewed ML models employed to predict intradialytic hypotension, their performance, methodological integrity, and clinical applicability.

Methods: We conducted this systematic review with a pre-established protocol registered at the International Prospective Register of Systematic Reviews (PROSPERO ID: CRD42022362194). Six databases, from their inception to July 20, 2023, were comprehensively searched. Two independent investigators reviewed the articles, extracted data, and evaluated the risk of bias using the Prediction model Risk of Bias Assessment Tool (PROBAST).

Results: Out of 84 screened articles, 16 studies with 14,500 adult patients on hemodialysis were included in the review. Fourteen studies (87.5%) were found to have a high risk of bias. The intradialytic hypotension prevalence in the population investigated was between 1.2 and 51%. A diverse range of predictive ML tools were used to predict intradialytic hypotension, with various neural networking models being the most frequent, appearing in 13 studies (AUROC ranges: 0.684-0.978). One study performed both internal and external validation.

Conclusions: Researchers have made a concerted effort to develop ML tools to predict intradialytic hypotension. Despite their significant efforts, the lack of thorough external and clinical validation, and heterogeneity among the models and settings have resulted in a substantial challenge to offering ML tools as a global intradialytic hypotension prevention and management solution. Future studies should focus on external and clinical validation of these models to enhance the chances of clinically relevant changes in clinical practices.

机器学习预测分析性低血压:一项系统综述。
背景:分析性低血压与发病率和死亡率增加有关。最近开发了几种机器学习(ML)算法来预测分析性低血压。我们系统地回顾了用于预测分析性低血压的ML模型、它们的性能、方法的完整性和临床适用性。方法:我们使用在国际前瞻性系统评价注册(PROSPERO ID: CRD42022362194)注册的预先建立的方案进行了该系统评价。6个数据库,从建立到2023年7月20日,被全面检索。两名独立研究人员审查了文章,提取了数据,并使用预测模型偏倚风险评估工具(PROBAST)评估了偏倚风险。结果:在84篇筛选的文章中,16项研究纳入了14,500名血液透析成人患者。发现14项研究(87.5%)存在高偏倚风险。在调查人群中,溶栓性低血压的患病率在1.2 - 51%之间。各种预测ML工具被用于预测分析性低血压,其中各种神经网络模型最为常见,出现在13项研究中(AUROC范围:0.684-0.978)。一项研究进行了内部和外部验证。结论:研究人员已经共同努力开发ML工具来预测分析性低血压。尽管他们做出了巨大的努力,但缺乏彻底的外部和临床验证,以及模型和设置之间的异质性,导致将ML工具作为一种全球的分析性低血压预防和管理解决方案面临重大挑战。未来的研究应侧重于这些模型的外部和临床验证,以增加临床实践中临床相关变化的机会。
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
Journal of Nephrology
Journal of Nephrology 医学-泌尿学与肾脏学
CiteScore
5.60
自引率
5.90%
发文量
289
审稿时长
3-8 weeks
期刊介绍: Journal of Nephrology is a bimonthly journal that considers publication of peer reviewed original manuscripts dealing with both clinical and laboratory investigations of relevance to the broad fields of Nephrology, Dialysis and Transplantation. It is the Official Journal of the Italian Society of Nephrology (SIN).
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信