Unsupervised clustering identifies sub-phenotypes and reveals novel outcome predictors in patients with dialysis-requiring sepsis-associated acute kidney injury

Heterogeneity exists in sepsis-associated acute kidney injury (SA-AKI). This study aimed to perform unsupervised consensus clustering in critically ill patients with dialysis-requiring SA-AKI. This prospective observational cohort study included all septic patients, defined by the Sepsis-3 criteria,...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Annals of medicine (Helsinki) 2023-12, Vol.55 (1), p.2197290-2197290
Hauptverfasser: Lai, Chun-Fu, Liu, Jung-Hua, Tseng, Li-Jung, Tsao, Chun-Hao, Chou, Nai-Kuan, Lin, Shuei-Liong, Chen, Yung-Ming, Wu, Vin-Cent
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 2197290
container_issue 1
container_start_page 2197290
container_title Annals of medicine (Helsinki)
container_volume 55
creator Lai, Chun-Fu
Liu, Jung-Hua
Tseng, Li-Jung
Tsao, Chun-Hao
Chou, Nai-Kuan
Lin, Shuei-Liong
Chen, Yung-Ming
Wu, Vin-Cent
description Heterogeneity exists in sepsis-associated acute kidney injury (SA-AKI). This study aimed to perform unsupervised consensus clustering in critically ill patients with dialysis-requiring SA-AKI. This prospective observational cohort study included all septic patients, defined by the Sepsis-3 criteria, with dialysis-requiring SA-AKI in surgical intensive care units in Taiwan between 2009 and 2018. We employed unsupervised consensus clustering based on 23 clinical variables upon initializing renal replacement therapy. Multivariate-adjusted Cox regression models and Fine-Gray sub-distribution hazard models were built to test associations between cluster memberships with mortality and being free of dialysis at 90 days after hospital discharge, respectively. Consensus clustering among 999 enrolled patients identified three sub-phenotypes characterized with distinct clinical manifestations upon renal replacement therapy initiation (n = 352, 396 and 251 in cluster 1, 2 and 3, respectively). They were followed for a median of 48 (interquartile range 9.5-128.5) days. Phenotypic cluster 1, featured by younger age, lower Charlson Comorbidity Index, higher baseline estimated glomerular filtration rate but with higher severity of acute illness was associated with an increased risk of death (adjusted hazard ratio of 3.05 [95% CI, 2.35-3.97]) and less probability to become free of dialysis (adjusted sub-distribution hazard ratio of 0.55 [95% CI, 0.38-0.8]) than cluster 3. By examining distinct features of the sub-phenotypes, we discovered that pre-dialysis hyperlactatemia ≥3.3 mmol/L was an independent outcome predictor. A clinical model developed to determine high-risk sub-phenotype 1 in this cohort (C-static 0.99) can identify a sub-phenotype with high in-hospital mortality risk (adjusted hazard ratio of 1.48 [95% CI, 1.25-1.74]) in another independent multi-centre SA-AKI cohort. Our data-driven approach suggests sub-phenotypes with clinical relevance in dialysis-requiring SA-AKI and serves an outcome predictor. This strategy represents further development toward precision medicine in the definition of high-risk sub-phenotype in patients with SA-AKI. Key messages Unsupervised consensus clustering can identify sub-phenotypes of patients with SA-AKI and provide a risk prediction. Examining the features of patient heterogeneity contributes to the discovery of serum lactate levels ≥ 3.3 mmol/L upon initializing RRT as an independent outcome predictor. This data-driven approa
doi_str_mv 10.1080/07853890.2023.2197290
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2800148453</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><doaj_id>oai_doaj_org_article_084a7f1cf1ed4d55a8badf895bb7111c</doaj_id><sourcerecordid>2800148453</sourcerecordid><originalsourceid>FETCH-LOGICAL-c535t-8b7a534fa43decf87066bd698db459b31fb2760a53dd22ca82d58bf6a013deb13</originalsourceid><addsrcrecordid>eNp9ks1u3CAUha2qVZOmfYRWLLvxlB9j41VbRf2JFKmbZo0wXGaYesABPNG8TR61ODOJmk3FAnE55zsInap6T_CKYIE_4U5wJnq8opiyFSV9R3v8ojonrOU1xS1-WZ0vmnoRnVVvUtpijGlH8OvqjHW4YZTS8-r-xqd5grh3CQzS45wyROfXyBnw2VkHCaV5qKcN-JAPUzkqb1CEPagxIR_2MKIwZx12gKYIxukcYkLOo0llVxgJ3bm8Qcap8ZBcqiPczu4hIsG0DFRKQTuVS77Scwb0xxkPh4LYzvHwtnplSxK8O-0X1c33b78vf9bXv35cXX69rjVnPNdi6BRnjVUNM6Ct6HDbDqbthRka3g-M2IF2LS4aYyjVSlDDxWBbhUkxDIRdVFdHrglqK6fodioeZFBOPgxCXEsVs9MjSCwa1VmiLQHTGM6VGJSxoufD0BFCdGF9PrKmediB0eUXohqfQZ_feLeR67CXBJfVdqwQPp4IMdzOkLLcuaRhHJWHMCdJBcakEQ1fpPwo1TGkFME-5RAsl6rIx6rIpSryVJXi-_DvI59cj90ogi9HgfM2xJ26C3E0MqvDGKKNymuXJPt_xl_3RNUb</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2800148453</pqid></control><display><type>article</type><title>Unsupervised clustering identifies sub-phenotypes and reveals novel outcome predictors in patients with dialysis-requiring sepsis-associated acute kidney injury</title><source>Taylor &amp; Francis Open Access</source><source>MEDLINE</source><source>DOAJ Directory of Open Access Journals</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><source>PubMed Central</source><creator>Lai, Chun-Fu ; Liu, Jung-Hua ; Tseng, Li-Jung ; Tsao, Chun-Hao ; Chou, Nai-Kuan ; Lin, Shuei-Liong ; Chen, Yung-Ming ; Wu, Vin-Cent</creator><creatorcontrib>Lai, Chun-Fu ; Liu, Jung-Hua ; Tseng, Li-Jung ; Tsao, Chun-Hao ; Chou, Nai-Kuan ; Lin, Shuei-Liong ; Chen, Yung-Ming ; Wu, Vin-Cent</creatorcontrib><description>Heterogeneity exists in sepsis-associated acute kidney injury (SA-AKI). This study aimed to perform unsupervised consensus clustering in critically ill patients with dialysis-requiring SA-AKI. This prospective observational cohort study included all septic patients, defined by the Sepsis-3 criteria, with dialysis-requiring SA-AKI in surgical intensive care units in Taiwan between 2009 and 2018. We employed unsupervised consensus clustering based on 23 clinical variables upon initializing renal replacement therapy. Multivariate-adjusted Cox regression models and Fine-Gray sub-distribution hazard models were built to test associations between cluster memberships with mortality and being free of dialysis at 90 days after hospital discharge, respectively. Consensus clustering among 999 enrolled patients identified three sub-phenotypes characterized with distinct clinical manifestations upon renal replacement therapy initiation (n = 352, 396 and 251 in cluster 1, 2 and 3, respectively). They were followed for a median of 48 (interquartile range 9.5-128.5) days. Phenotypic cluster 1, featured by younger age, lower Charlson Comorbidity Index, higher baseline estimated glomerular filtration rate but with higher severity of acute illness was associated with an increased risk of death (adjusted hazard ratio of 3.05 [95% CI, 2.35-3.97]) and less probability to become free of dialysis (adjusted sub-distribution hazard ratio of 0.55 [95% CI, 0.38-0.8]) than cluster 3. By examining distinct features of the sub-phenotypes, we discovered that pre-dialysis hyperlactatemia ≥3.3 mmol/L was an independent outcome predictor. A clinical model developed to determine high-risk sub-phenotype 1 in this cohort (C-static 0.99) can identify a sub-phenotype with high in-hospital mortality risk (adjusted hazard ratio of 1.48 [95% CI, 1.25-1.74]) in another independent multi-centre SA-AKI cohort. Our data-driven approach suggests sub-phenotypes with clinical relevance in dialysis-requiring SA-AKI and serves an outcome predictor. This strategy represents further development toward precision medicine in the definition of high-risk sub-phenotype in patients with SA-AKI. Key messages Unsupervised consensus clustering can identify sub-phenotypes of patients with SA-AKI and provide a risk prediction. Examining the features of patient heterogeneity contributes to the discovery of serum lactate levels ≥ 3.3 mmol/L upon initializing RRT as an independent outcome predictor. This data-driven approach can be useful for prognostication and lead to a better understanding of therapeutic strategies in heterogeneous clinical syndromes.</description><identifier>ISSN: 0785-3890</identifier><identifier>EISSN: 1365-2060</identifier><identifier>DOI: 10.1080/07853890.2023.2197290</identifier><identifier>PMID: 37043222</identifier><language>eng</language><publisher>England: Taylor &amp; Francis</publisher><subject>Acute kidney injury ; Acute Kidney Injury - etiology ; Acute Kidney Injury - therapy ; cluster analysis ; competing risk ; Dialysis - adverse effects ; Humans ; Nephrology &amp; Urology ; Phenotype ; Prospective Studies ; recovery of function ; renal replacement therapy ; Retrospective Studies ; Sepsis - complications ; Sepsis - therapy ; Sepsis-3 ; sequential organ failure assessment</subject><ispartof>Annals of medicine (Helsinki), 2023-12, Vol.55 (1), p.2197290-2197290</ispartof><rights>2023 The Author(s). Published by Informa UK Limited, trading as Taylor &amp; Francis Group 2023</rights><rights>2023 The Author(s). Published by Informa UK Limited, trading as Taylor &amp; Francis Group 2023 The Author(s)</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c535t-8b7a534fa43decf87066bd698db459b31fb2760a53dd22ca82d58bf6a013deb13</citedby><cites>FETCH-LOGICAL-c535t-8b7a534fa43decf87066bd698db459b31fb2760a53dd22ca82d58bf6a013deb13</cites><orcidid>0000-0003-2109-1522 ; 0000-0002-1041-5571 ; 0000-0001-5494-7708 ; 0000-0002-9241-1258 ; 0000-0001-7935-0991</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC10101673/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC10101673/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,314,723,776,780,860,881,2096,27479,27901,27902,53766,53768,59116,59117</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/37043222$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Lai, Chun-Fu</creatorcontrib><creatorcontrib>Liu, Jung-Hua</creatorcontrib><creatorcontrib>Tseng, Li-Jung</creatorcontrib><creatorcontrib>Tsao, Chun-Hao</creatorcontrib><creatorcontrib>Chou, Nai-Kuan</creatorcontrib><creatorcontrib>Lin, Shuei-Liong</creatorcontrib><creatorcontrib>Chen, Yung-Ming</creatorcontrib><creatorcontrib>Wu, Vin-Cent</creatorcontrib><title>Unsupervised clustering identifies sub-phenotypes and reveals novel outcome predictors in patients with dialysis-requiring sepsis-associated acute kidney injury</title><title>Annals of medicine (Helsinki)</title><addtitle>Ann Med</addtitle><description>Heterogeneity exists in sepsis-associated acute kidney injury (SA-AKI). This study aimed to perform unsupervised consensus clustering in critically ill patients with dialysis-requiring SA-AKI. This prospective observational cohort study included all septic patients, defined by the Sepsis-3 criteria, with dialysis-requiring SA-AKI in surgical intensive care units in Taiwan between 2009 and 2018. We employed unsupervised consensus clustering based on 23 clinical variables upon initializing renal replacement therapy. Multivariate-adjusted Cox regression models and Fine-Gray sub-distribution hazard models were built to test associations between cluster memberships with mortality and being free of dialysis at 90 days after hospital discharge, respectively. Consensus clustering among 999 enrolled patients identified three sub-phenotypes characterized with distinct clinical manifestations upon renal replacement therapy initiation (n = 352, 396 and 251 in cluster 1, 2 and 3, respectively). They were followed for a median of 48 (interquartile range 9.5-128.5) days. Phenotypic cluster 1, featured by younger age, lower Charlson Comorbidity Index, higher baseline estimated glomerular filtration rate but with higher severity of acute illness was associated with an increased risk of death (adjusted hazard ratio of 3.05 [95% CI, 2.35-3.97]) and less probability to become free of dialysis (adjusted sub-distribution hazard ratio of 0.55 [95% CI, 0.38-0.8]) than cluster 3. By examining distinct features of the sub-phenotypes, we discovered that pre-dialysis hyperlactatemia ≥3.3 mmol/L was an independent outcome predictor. A clinical model developed to determine high-risk sub-phenotype 1 in this cohort (C-static 0.99) can identify a sub-phenotype with high in-hospital mortality risk (adjusted hazard ratio of 1.48 [95% CI, 1.25-1.74]) in another independent multi-centre SA-AKI cohort. Our data-driven approach suggests sub-phenotypes with clinical relevance in dialysis-requiring SA-AKI and serves an outcome predictor. This strategy represents further development toward precision medicine in the definition of high-risk sub-phenotype in patients with SA-AKI. Key messages Unsupervised consensus clustering can identify sub-phenotypes of patients with SA-AKI and provide a risk prediction. Examining the features of patient heterogeneity contributes to the discovery of serum lactate levels ≥ 3.3 mmol/L upon initializing RRT as an independent outcome predictor. This data-driven approach can be useful for prognostication and lead to a better understanding of therapeutic strategies in heterogeneous clinical syndromes.</description><subject>Acute kidney injury</subject><subject>Acute Kidney Injury - etiology</subject><subject>Acute Kidney Injury - therapy</subject><subject>cluster analysis</subject><subject>competing risk</subject><subject>Dialysis - adverse effects</subject><subject>Humans</subject><subject>Nephrology &amp; Urology</subject><subject>Phenotype</subject><subject>Prospective Studies</subject><subject>recovery of function</subject><subject>renal replacement therapy</subject><subject>Retrospective Studies</subject><subject>Sepsis - complications</subject><subject>Sepsis - therapy</subject><subject>Sepsis-3</subject><subject>sequential organ failure assessment</subject><issn>0785-3890</issn><issn>1365-2060</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>0YH</sourceid><sourceid>EIF</sourceid><sourceid>DOA</sourceid><recordid>eNp9ks1u3CAUha2qVZOmfYRWLLvxlB9j41VbRf2JFKmbZo0wXGaYesABPNG8TR61ODOJmk3FAnE55zsInap6T_CKYIE_4U5wJnq8opiyFSV9R3v8ojonrOU1xS1-WZ0vmnoRnVVvUtpijGlH8OvqjHW4YZTS8-r-xqd5grh3CQzS45wyROfXyBnw2VkHCaV5qKcN-JAPUzkqb1CEPagxIR_2MKIwZx12gKYIxukcYkLOo0llVxgJ3bm8Qcap8ZBcqiPczu4hIsG0DFRKQTuVS77Scwb0xxkPh4LYzvHwtnplSxK8O-0X1c33b78vf9bXv35cXX69rjVnPNdi6BRnjVUNM6Ct6HDbDqbthRka3g-M2IF2LS4aYyjVSlDDxWBbhUkxDIRdVFdHrglqK6fodioeZFBOPgxCXEsVs9MjSCwa1VmiLQHTGM6VGJSxoufD0BFCdGF9PrKmediB0eUXohqfQZ_feLeR67CXBJfVdqwQPp4IMdzOkLLcuaRhHJWHMCdJBcakEQ1fpPwo1TGkFME-5RAsl6rIx6rIpSryVJXi-_DvI59cj90ogi9HgfM2xJ26C3E0MqvDGKKNymuXJPt_xl_3RNUb</recordid><startdate>20231212</startdate><enddate>20231212</enddate><creator>Lai, Chun-Fu</creator><creator>Liu, Jung-Hua</creator><creator>Tseng, Li-Jung</creator><creator>Tsao, Chun-Hao</creator><creator>Chou, Nai-Kuan</creator><creator>Lin, Shuei-Liong</creator><creator>Chen, Yung-Ming</creator><creator>Wu, Vin-Cent</creator><general>Taylor &amp; Francis</general><general>Taylor &amp; Francis Group</general><scope>0YH</scope><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><scope>5PM</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0003-2109-1522</orcidid><orcidid>https://orcid.org/0000-0002-1041-5571</orcidid><orcidid>https://orcid.org/0000-0001-5494-7708</orcidid><orcidid>https://orcid.org/0000-0002-9241-1258</orcidid><orcidid>https://orcid.org/0000-0001-7935-0991</orcidid></search><sort><creationdate>20231212</creationdate><title>Unsupervised clustering identifies sub-phenotypes and reveals novel outcome predictors in patients with dialysis-requiring sepsis-associated acute kidney injury</title><author>Lai, Chun-Fu ; Liu, Jung-Hua ; Tseng, Li-Jung ; Tsao, Chun-Hao ; Chou, Nai-Kuan ; Lin, Shuei-Liong ; Chen, Yung-Ming ; Wu, Vin-Cent</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c535t-8b7a534fa43decf87066bd698db459b31fb2760a53dd22ca82d58bf6a013deb13</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Acute kidney injury</topic><topic>Acute Kidney Injury - etiology</topic><topic>Acute Kidney Injury - therapy</topic><topic>cluster analysis</topic><topic>competing risk</topic><topic>Dialysis - adverse effects</topic><topic>Humans</topic><topic>Nephrology &amp; Urology</topic><topic>Phenotype</topic><topic>Prospective Studies</topic><topic>recovery of function</topic><topic>renal replacement therapy</topic><topic>Retrospective Studies</topic><topic>Sepsis - complications</topic><topic>Sepsis - therapy</topic><topic>Sepsis-3</topic><topic>sequential organ failure assessment</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Lai, Chun-Fu</creatorcontrib><creatorcontrib>Liu, Jung-Hua</creatorcontrib><creatorcontrib>Tseng, Li-Jung</creatorcontrib><creatorcontrib>Tsao, Chun-Hao</creatorcontrib><creatorcontrib>Chou, Nai-Kuan</creatorcontrib><creatorcontrib>Lin, Shuei-Liong</creatorcontrib><creatorcontrib>Chen, Yung-Ming</creatorcontrib><creatorcontrib>Wu, Vin-Cent</creatorcontrib><collection>Taylor &amp; Francis Open Access</collection><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>Annals of medicine (Helsinki)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Lai, Chun-Fu</au><au>Liu, Jung-Hua</au><au>Tseng, Li-Jung</au><au>Tsao, Chun-Hao</au><au>Chou, Nai-Kuan</au><au>Lin, Shuei-Liong</au><au>Chen, Yung-Ming</au><au>Wu, Vin-Cent</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Unsupervised clustering identifies sub-phenotypes and reveals novel outcome predictors in patients with dialysis-requiring sepsis-associated acute kidney injury</atitle><jtitle>Annals of medicine (Helsinki)</jtitle><addtitle>Ann Med</addtitle><date>2023-12-12</date><risdate>2023</risdate><volume>55</volume><issue>1</issue><spage>2197290</spage><epage>2197290</epage><pages>2197290-2197290</pages><issn>0785-3890</issn><eissn>1365-2060</eissn><abstract>Heterogeneity exists in sepsis-associated acute kidney injury (SA-AKI). This study aimed to perform unsupervised consensus clustering in critically ill patients with dialysis-requiring SA-AKI. This prospective observational cohort study included all septic patients, defined by the Sepsis-3 criteria, with dialysis-requiring SA-AKI in surgical intensive care units in Taiwan between 2009 and 2018. We employed unsupervised consensus clustering based on 23 clinical variables upon initializing renal replacement therapy. Multivariate-adjusted Cox regression models and Fine-Gray sub-distribution hazard models were built to test associations between cluster memberships with mortality and being free of dialysis at 90 days after hospital discharge, respectively. Consensus clustering among 999 enrolled patients identified three sub-phenotypes characterized with distinct clinical manifestations upon renal replacement therapy initiation (n = 352, 396 and 251 in cluster 1, 2 and 3, respectively). They were followed for a median of 48 (interquartile range 9.5-128.5) days. Phenotypic cluster 1, featured by younger age, lower Charlson Comorbidity Index, higher baseline estimated glomerular filtration rate but with higher severity of acute illness was associated with an increased risk of death (adjusted hazard ratio of 3.05 [95% CI, 2.35-3.97]) and less probability to become free of dialysis (adjusted sub-distribution hazard ratio of 0.55 [95% CI, 0.38-0.8]) than cluster 3. By examining distinct features of the sub-phenotypes, we discovered that pre-dialysis hyperlactatemia ≥3.3 mmol/L was an independent outcome predictor. A clinical model developed to determine high-risk sub-phenotype 1 in this cohort (C-static 0.99) can identify a sub-phenotype with high in-hospital mortality risk (adjusted hazard ratio of 1.48 [95% CI, 1.25-1.74]) in another independent multi-centre SA-AKI cohort. Our data-driven approach suggests sub-phenotypes with clinical relevance in dialysis-requiring SA-AKI and serves an outcome predictor. This strategy represents further development toward precision medicine in the definition of high-risk sub-phenotype in patients with SA-AKI. Key messages Unsupervised consensus clustering can identify sub-phenotypes of patients with SA-AKI and provide a risk prediction. Examining the features of patient heterogeneity contributes to the discovery of serum lactate levels ≥ 3.3 mmol/L upon initializing RRT as an independent outcome predictor. This data-driven approach can be useful for prognostication and lead to a better understanding of therapeutic strategies in heterogeneous clinical syndromes.</abstract><cop>England</cop><pub>Taylor &amp; Francis</pub><pmid>37043222</pmid><doi>10.1080/07853890.2023.2197290</doi><tpages>1</tpages><orcidid>https://orcid.org/0000-0003-2109-1522</orcidid><orcidid>https://orcid.org/0000-0002-1041-5571</orcidid><orcidid>https://orcid.org/0000-0001-5494-7708</orcidid><orcidid>https://orcid.org/0000-0002-9241-1258</orcidid><orcidid>https://orcid.org/0000-0001-7935-0991</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 0785-3890
ispartof Annals of medicine (Helsinki), 2023-12, Vol.55 (1), p.2197290-2197290
issn 0785-3890
1365-2060
language eng
recordid cdi_proquest_miscellaneous_2800148453
source Taylor & Francis Open Access; MEDLINE; DOAJ Directory of Open Access Journals; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals; PubMed Central
subjects Acute kidney injury
Acute Kidney Injury - etiology
Acute Kidney Injury - therapy
cluster analysis
competing risk
Dialysis - adverse effects
Humans
Nephrology & Urology
Phenotype
Prospective Studies
recovery of function
renal replacement therapy
Retrospective Studies
Sepsis - complications
Sepsis - therapy
Sepsis-3
sequential organ failure assessment
title Unsupervised clustering identifies sub-phenotypes and reveals novel outcome predictors in patients with dialysis-requiring sepsis-associated acute kidney injury
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-13T20%3A45%3A00IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Unsupervised%20clustering%20identifies%20sub-phenotypes%20and%20reveals%20novel%20outcome%20predictors%20in%20patients%20with%20dialysis-requiring%20sepsis-associated%20acute%20kidney%20injury&rft.jtitle=Annals%20of%20medicine%20(Helsinki)&rft.au=Lai,%20Chun-Fu&rft.date=2023-12-12&rft.volume=55&rft.issue=1&rft.spage=2197290&rft.epage=2197290&rft.pages=2197290-2197290&rft.issn=0785-3890&rft.eissn=1365-2060&rft_id=info:doi/10.1080/07853890.2023.2197290&rft_dat=%3Cproquest_cross%3E2800148453%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2800148453&rft_id=info:pmid/37043222&rft_doaj_id=oai_doaj_org_article_084a7f1cf1ed4d55a8badf895bb7111c&rfr_iscdi=true