Risk prediction for acute kidney disease and adverse outcomes in patients with chronic obstructive pulmonary disease: an interpretable machine learning approach.

IF 3 3区 医学 Q1 UROLOGY & NEPHROLOGY
Renal Failure Pub Date : 2025-12-01 Epub Date: 2025-04-07 DOI:10.1080/0886022X.2025.2485475
Siqi Jiang, Lingyu Xu, Xinyuan Wang, Chenyu Li, Chen Guan, Lin Che, Yanfei Wang, Xuefei Shen, Yan Xu
{"title":"Risk prediction for acute kidney disease and adverse outcomes in patients with chronic obstructive pulmonary disease: an interpretable machine learning approach.","authors":"Siqi Jiang, Lingyu Xu, Xinyuan Wang, Chenyu Li, Chen Guan, Lin Che, Yanfei Wang, Xuefei Shen, Yan Xu","doi":"10.1080/0886022X.2025.2485475","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Little is known about acute kidney injury (AKI) and acute kidney disease (AKD) in patients with chronic obstructive pulmonary disease (COPD) and COPD mortality based on the acute/subacute renal injury. This study develops machine learning models to predict AKI, AKD, and mortality in COPD patients, utilizing web applications for clinical decisions.</p><p><strong>Methods: </strong>We included 2,829 inpatients from January 2016 to December 2018. Data were split into 80% for training and 20% for testing. Eight machine learning algorithms were used, and model performance was evaluated using various metrics. SHAP was used to visualize the decision process. The best models, assessed using AUROC were used to develop web applications for identifying high-risk patients.</p><p><strong>Results: </strong>The incidence rates were 13.71% for AKI and 15.11% for AKD. The overall mortality rate was 4.84%. LightGBM performed best with AUROC of 0.815, 0.827, and 0.934 in AKI, AKD, and mortality, respectively. Key predictors for AKI were Scr, neutrophil percentage, cystatin c, BUN, and LDH. For AKD, the key predictors were age, AKI grade, HDL-C, Scr, and BUN. The key predictors for mortality included the use of dopamine and epinephrine drugs, cystatin c, renal function trajectory, albumin, and neutrophil percentage. Force plots visualized the prediction process for individual patients.</p><p><strong>Conclusions: </strong>The incidence of AKI and AKD is significant in patients with COPD. Renal function trajectory is crucial for predicting mortality in these patients. Web applications were developed to predict AKI, AKD, and mortality, improving prognosis by identifying high-risk patients and reducing adverse events and disease progression.</p>","PeriodicalId":20839,"journal":{"name":"Renal Failure","volume":"47 1","pages":"2485475"},"PeriodicalIF":3.0000,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Renal Failure","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1080/0886022X.2025.2485475","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/4/7 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"UROLOGY & NEPHROLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Background: Little is known about acute kidney injury (AKI) and acute kidney disease (AKD) in patients with chronic obstructive pulmonary disease (COPD) and COPD mortality based on the acute/subacute renal injury. This study develops machine learning models to predict AKI, AKD, and mortality in COPD patients, utilizing web applications for clinical decisions.

Methods: We included 2,829 inpatients from January 2016 to December 2018. Data were split into 80% for training and 20% for testing. Eight machine learning algorithms were used, and model performance was evaluated using various metrics. SHAP was used to visualize the decision process. The best models, assessed using AUROC were used to develop web applications for identifying high-risk patients.

Results: The incidence rates were 13.71% for AKI and 15.11% for AKD. The overall mortality rate was 4.84%. LightGBM performed best with AUROC of 0.815, 0.827, and 0.934 in AKI, AKD, and mortality, respectively. Key predictors for AKI were Scr, neutrophil percentage, cystatin c, BUN, and LDH. For AKD, the key predictors were age, AKI grade, HDL-C, Scr, and BUN. The key predictors for mortality included the use of dopamine and epinephrine drugs, cystatin c, renal function trajectory, albumin, and neutrophil percentage. Force plots visualized the prediction process for individual patients.

Conclusions: The incidence of AKI and AKD is significant in patients with COPD. Renal function trajectory is crucial for predicting mortality in these patients. Web applications were developed to predict AKI, AKD, and mortality, improving prognosis by identifying high-risk patients and reducing adverse events and disease progression.

慢性阻塞性肺疾病患者急性肾脏疾病和不良结局的风险预测:可解释的机器学习方法
背景:关于慢性阻塞性肺疾病(COPD)患者的急性肾损伤(AKI)和急性肾脏疾病(AKD)以及基于急性/亚急性肾损伤的COPD死亡率,我们知之甚少。本研究开发了机器学习模型来预测慢性阻塞性肺病患者的AKI、AKD和死亡率,利用web应用程序进行临床决策。方法:纳入2016年1月至2018年12月住院患者2829例。数据分成80%用于训练,20%用于测试。使用了八种机器学习算法,并使用各种指标评估模型性能。SHAP用于可视化决策过程。使用AUROC评估的最佳模型被用于开发识别高危患者的web应用程序。结果:AKI和AKD的发生率分别为13.71%和15.11%。总死亡率为4.84%。LightGBM在AKI、AKD和死亡率方面的AUROC分别为0.815、0.827和0.934,效果最好。AKI的主要预测因子是Scr、中性粒细胞百分比、胱抑素c、BUN和LDH。对于AKD,关键预测因素是年龄、AKI分级、HDL-C、Scr和BUN。死亡率的主要预测因子包括多巴胺和肾上腺素药物的使用、胱抑素c、肾功能轨迹、白蛋白和中性粒细胞百分比。力图将个体患者的预测过程可视化。结论:慢性阻塞性肺病患者AKI和AKD发生率显著。肾功能轨迹对于预测这些患者的死亡率至关重要。开发了Web应用程序来预测AKI、AKD和死亡率,通过识别高危患者、减少不良事件和疾病进展来改善预后。
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
Renal Failure
Renal Failure 医学-泌尿学与肾脏学
CiteScore
3.90
自引率
13.30%
发文量
374
审稿时长
1 months
期刊介绍: Renal Failure primarily concentrates on acute renal injury and its consequence, but also addresses advances in the fields of chronic renal failure, hypertension, and renal transplantation. Bringing together both clinical and experimental aspects of renal failure, this publication presents timely, practical information on pathology and pathophysiology of acute renal failure; nephrotoxicity of drugs and other substances; prevention, treatment, and therapy of renal failure; renal failure in association with transplantation, hypertension, and diabetes mellitus.
×
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