Lian Feng, Min Li, Zhen Jiang, Jiao Chen, Zhen-Jiang Bai, Xiao-Zhong Li, Guo-Ping Lu, Yan-Hong Li
{"title":"[Clinical sub-phenotypes of acute kidney injury in children and their association with prognosis].","authors":"Lian Feng, Min Li, Zhen Jiang, Jiao Chen, Zhen-Jiang Bai, Xiao-Zhong Li, Guo-Ping Lu, Yan-Hong Li","doi":"10.7499/j.issn.1008-8830.2408060","DOIUrl":null,"url":null,"abstract":"<p><strong>Objectives: </strong>To investigate the clinical sub-phenotype (SP) of pediatric acute kidney injury (AKI) and their association with clinical outcomes.</p><p><strong>Methods: </strong>General status and initial values of laboratory markers within 24 hours after admission to the pediatric intensive care unit (PICU) were recorded for children with AKI in the derivation cohort (<i>n</i>=650) and the validation cohort (<i>n</i>=177). In the derivation cohort, a least absolute shrinkage and selection operator (LASSO) regression analysis was used to identify death-related indicators, and a two-step cluster analysis was employed to obtain the clinical SP of AKI. A logistic regression analysis was used to develop a parsimonious classifier model with simplified metrics, and the area under the curve (AUC) was used to assess the value of this model. This model was then applied to the validation cohort and the combined derivation and validation cohort. The association between SPs and clinical outcomes was analyzed with all children with AKI as subjects.</p><p><strong>Results: </strong>In the derivation cohort, two clinical SPs of AKI (SP1 and SP2) were identified by the two-step cluster analysis using the 20 variables screened by LASSO regression, namely SP<sub>d</sub>1 group (<i>n</i>=536) and SP<sub>d</sub>2 group (<i>n</i>=114). The simplified classifier model containing eight variables (<i>P</i><0.05) had an AUC of 0.965 in identifying the two clinical SPs of AKI (<i>P</i><0.001). The validation cohort was clustered into SP<sub>v</sub>1 group (<i>n</i>=156) and SP<sub>v</sub>2 group (<i>n</i>=21), and the combined derivation and validation cohort was clustered into SP1 group (<i>n</i>=694) and SP2 group (<i>n</i>=133). After adjustment for confounding factors, compared with the SP1 group, the SP2 group had significantly higher incidence rates of multiple organ dysfunction syndrome and death during the PICU stay (<i>P</i><0.001), and SP2 was significantly associated with the risk of death within 28 days after admission to the PICU (<i>P</i><0.001).</p><p><strong>Conclusions: </strong>This study establishes a parsimonious classifier model and identifies two clinical SPs of AKI with different clinical features and outcomes.The SP2 group has more severe disease and worse clinical prognosis.</p>","PeriodicalId":39792,"journal":{"name":"中国当代儿科杂志","volume":"27 1","pages":"47-54"},"PeriodicalIF":0.0000,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11750252/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"中国当代儿科杂志","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.7499/j.issn.1008-8830.2408060","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Medicine","Score":null,"Total":0}
引用次数: 0
Abstract
Objectives: To investigate the clinical sub-phenotype (SP) of pediatric acute kidney injury (AKI) and their association with clinical outcomes.
Methods: General status and initial values of laboratory markers within 24 hours after admission to the pediatric intensive care unit (PICU) were recorded for children with AKI in the derivation cohort (n=650) and the validation cohort (n=177). In the derivation cohort, a least absolute shrinkage and selection operator (LASSO) regression analysis was used to identify death-related indicators, and a two-step cluster analysis was employed to obtain the clinical SP of AKI. A logistic regression analysis was used to develop a parsimonious classifier model with simplified metrics, and the area under the curve (AUC) was used to assess the value of this model. This model was then applied to the validation cohort and the combined derivation and validation cohort. The association between SPs and clinical outcomes was analyzed with all children with AKI as subjects.
Results: In the derivation cohort, two clinical SPs of AKI (SP1 and SP2) were identified by the two-step cluster analysis using the 20 variables screened by LASSO regression, namely SPd1 group (n=536) and SPd2 group (n=114). The simplified classifier model containing eight variables (P<0.05) had an AUC of 0.965 in identifying the two clinical SPs of AKI (P<0.001). The validation cohort was clustered into SPv1 group (n=156) and SPv2 group (n=21), and the combined derivation and validation cohort was clustered into SP1 group (n=694) and SP2 group (n=133). After adjustment for confounding factors, compared with the SP1 group, the SP2 group had significantly higher incidence rates of multiple organ dysfunction syndrome and death during the PICU stay (P<0.001), and SP2 was significantly associated with the risk of death within 28 days after admission to the PICU (P<0.001).
Conclusions: This study establishes a parsimonious classifier model and identifies two clinical SPs of AKI with different clinical features and outcomes.The SP2 group has more severe disease and worse clinical prognosis.
目的:探讨小儿急性肾损伤(AKI)的临床亚表型(SP)及其与临床转归的关系。方法:记录衍生组(n=650)和验证组(n=177) AKI患儿入院后24小时内的一般状态和实验室标志物的初始值。衍生队列采用最小绝对收缩和选择算子(LASSO)回归分析确定死亡相关指标,采用两步聚类分析获得AKI的临床SP。采用logistic回归分析方法建立了简化指标的简约分类器模型,并用曲线下面积(area under the curve, AUC)评价模型的价值。然后将该模型应用于验证队列和推导与验证联合队列。以所有AKI患儿为研究对象,分析了SPs与临床结果之间的关系。结果:衍生队列中,采用LASSO回归筛选的20个变量进行两步聚类分析,确定了AKI的2个临床sp (SP1和SP2),即SPd1组(n=536)和SPd2组(n=114)。简化的分类器模型包含8个变量(PPv1组(n=156)和SPv2组(n=21)),合并推导和验证队列分为SP1组(n=694)和SP2组(n=133)。调整混杂因素后,SP2组在PICU停留期间多脏器功能障碍综合征和死亡发生率明显高于SP1组(ppp)。结论:本研究建立了简约分类模型,鉴别出两种临床特征和结局不同的AKI临床SPs。SP2组病情加重,临床预后较差。
中国当代儿科杂志Medicine-Pediatrics, Perinatology and Child Health
CiteScore
1.50
自引率
0.00%
发文量
5006
期刊介绍:
The Chinese Journal of Contemporary Pediatrics (CJCP) is a peer-reviewed open access periodical in the field of pediatrics that is sponsored by the Central South University/Xiangya Hospital of Central South University and under the auspices of the Ministry of Education of China. It is cited as a source in the scientific and technological papers of Chinese journals, the Chinese Science Citation Database (CSCD), and is one of the core Chinese periodicals in the Peking University Library. CJCP has been indexed by MEDLINE/PubMed/PMC of the American National Library, American Chemical Abstracts (CA), Holland Medical Abstracts (EM), Western Pacific Region Index Medicus (WPRIM), Scopus and EBSCO. It is a monthly periodical published on the 15th of every month, and is distributed both at home and overseas. The Chinese series publication number is CN 43-1301/R;ISSN 1008-8830. The tenet of CJCP is to “reflect the latest advances and be open to the world”. The periodical reports the most recent advances in the contemporary pediatric field. The majority of the readership is pediatric doctors and researchers.