Gene signature for the prediction of the trajectories of sepsis-induced acute kidney injury

CMAISE Consortium

doi:10.1186/s13054-022-04234-3

Gene signature for the prediction of the trajectories of sepsis-induced acute kidney injury

CMAISE Consortium

Institute for Health Informatics

Research output: Contribution to journal › Article › peer-review

6 Scopus citations

Abstract

Background: Acute kidney injury (AKI) is a common complication in sepsis. However, the trajectories of sepsis-induced AKI and their transcriptional profiles are not well characterized. Methods: Sepsis patients admitted to centres participating in Chinese Multi-omics Advances In Sepsis (CMAISE) from November 2020 to December 2021 were enrolled, and gene expression in peripheral blood mononuclear cells was measured on Day 1. The renal function trajectory was measured by the renal component of the SOFA score (SOFA_renal) on Days 1 and 3. Transcriptional profiles on Day 1 were compared between these renal function trajectories, and a support vector machine (SVM) was developed to distinguish transient from persistent AKI. Results: A total of 172 sepsis patients were enrolled during the study period. The renal function trajectory was classified into four types: non-AKI (SOFA_renal = 0 on Days 1 and 3, n = 50), persistent AKI (SOFA_renal > 0 on Days 1 and 3, n = 62), transient AKI (SOFA_renal > 0 on Day 1 and SOFA_renal = 0 on Day 3, n = 50) and worsening AKI (SOFA_renal = 0 on Days 1 and SOFA_renal > 0 on Day 3, n = 10). The persistent AKI group showed severe organ dysfunction and prolonged requirements for organ support. The worsening AKI group showed the least organ dysfunction on day 1 but had higher serum lactate and prolonged use of vasopressors than the non-AKI and transient AKI groups. There were 2091 upregulated and 1,902 downregulated genes (adjusted p < 0.05) between the persistent and transient AKI groups, with enrichment in the plasma membrane complex, receptor complex, and T-cell receptor complex. A 43-gene SVM model was developed using the genetic algorithm, which showed significantly greater performance predicting persistent AKI than the model based on clinical variables in a holdout subset (AUC: 0.948 [0.912, 0.984] vs. 0.739 [0.648, 0.830]; p < 0.01 for Delong’s test). Conclusions: Our study identified four subtypes of sepsis-induced AKI based on kidney injury trajectories. The landscape of host response aberrations across these subtypes was characterized. An SVM model based on a gene signature was developed to predict renal function trajectories, and showed better performance than the clinical variable-based model. Future studies are warranted to validate the gene model in distinguishing persistent from transient AKI.

Original language	English (US)
Article number	398
Journal	Critical Care
Volume	26
Issue number	1
DOIs	https://doi.org/10.1186/s13054-022-04234-3
State	Published - Dec 2022

Bibliographical note

Funding Information:
Z.Z. received funding from the Health Science and Technology Plan of Zhejiang Province (2021KY745), the Fundamental Research Funds for the Central Universities (226-2022-00148), National natural science foundation of China (82272180) and the Project of Drug Clinical Evaluate Research of Chinese Pharmaceutical Association NO.CPA-Z06-ZC-2021-004. Y.H. received funding from the Key Research & Development project of Zhejiang Province (2021C03071), K.C. received funding from the Key Research & Development project of Zhejiang Province (2020C03019).

Funding Information:
The members of the CMAISE consortium were as follows: Yucai Hong, Lifeng Xing, Zhongheng Zhang (Sir Run Run Shaw Hospital, Zhejiang University School of Medicine); Senjun Jin (Department of Emergency, Zhejiang Provincial People’s Hospital, People’s Hospital of Hangzhou Medical College); Lin Chen, Kun Chen (Department of Critical Care Medicine, Affiliated Jinhua Hospital, Zhejiang University School of Medicine); Jian Sun (Department of Critical Care Medicine, Lishui Center Hospital); Yi Yang (Department of Emergency Medicine, The Second Hospital of Jiaxing); Xiaohong Jin (Department of Emergency Medicine, The Affiliated Wenling Hospital of Wenzhou Medical University); Min Yang (The 2nd Department of Intensive Care Unit, the Second Affiliated Hospital of Anhui Medical University); Chunmei Gui, Yingpu Yuan (Department of Critical Care Medicine, The First People’s Hospital of Changde City); Guangtao Dong (Department of Emergency Medicine, the First Affiliated Hospital of Harbin Medical University); Weizhong Zeng, Jing Zeng (Department of critical care medicine, Zhuzhou central hospital); Guoxin Hu, Lujun Qiao (Emergency Department, Shengli Oilfield Central Hospital); Jinhua Wang, Yonglin Xi (Department of critical care medicine, the Second Affiliated Hospital of Xi’an Medical University); Nan Wang, Minmin Wang (Department of critical care medicine, The Fourth Affiliated Hospital of Anhui Medical University, Anhui Medical University); Yan Teng, Junxia Hou (Department of critical care medicine, the first affiliated hospital of Xi'an Jiaotong University); Qiaojie Bi (Department of emergency, Qingdao municipal hospital, Qingdao university school of medicine); Gengsheng Zhang (Department of Critical Care Medicine, Second Affiliated Hospital, Zhejiang University School of Medicine); Junru Dai (Longyou People’s hospital, Longyou, Zhejiang). We would like to thank reviewers and Dr. Ketao Jin from Jinhua central hospital for their thoughtful comments and suggestions on our manuscript.

Publisher Copyright:
© 2022, The Author(s).

Keywords

Acute kidney injury
Genetic algorithms
RNA-seq
Sepsis
Support vector machine

PubMed: MeSH publication types

Journal Article

Access

10.1186/s13054-022-04234-3

OpenUrl availability

Full text

Cite this

@article{8d17aee6b2d44c11be720284b38871cf,

title = "Gene signature for the prediction of the trajectories of sepsis-induced acute kidney injury",

abstract = "Background: Acute kidney injury (AKI) is a common complication in sepsis. However, the trajectories of sepsis-induced AKI and their transcriptional profiles are not well characterized. Methods: Sepsis patients admitted to centres participating in Chinese Multi-omics Advances In Sepsis (CMAISE) from November 2020 to December 2021 were enrolled, and gene expression in peripheral blood mononuclear cells was measured on Day 1. The renal function trajectory was measured by the renal component of the SOFA score (SOFArenal) on Days 1 and 3. Transcriptional profiles on Day 1 were compared between these renal function trajectories, and a support vector machine (SVM) was developed to distinguish transient from persistent AKI. Results: A total of 172 sepsis patients were enrolled during the study period. The renal function trajectory was classified into four types: non-AKI (SOFArenal = 0 on Days 1 and 3, n = 50), persistent AKI (SOFArenal > 0 on Days 1 and 3, n = 62), transient AKI (SOFArenal > 0 on Day 1 and SOFArenal = 0 on Day 3, n = 50) and worsening AKI (SOFArenal = 0 on Days 1 and SOFArenal > 0 on Day 3, n = 10). The persistent AKI group showed severe organ dysfunction and prolonged requirements for organ support. The worsening AKI group showed the least organ dysfunction on day 1 but had higher serum lactate and prolonged use of vasopressors than the non-AKI and transient AKI groups. There were 2091 upregulated and 1,902 downregulated genes (adjusted p < 0.05) between the persistent and transient AKI groups, with enrichment in the plasma membrane complex, receptor complex, and T-cell receptor complex. A 43-gene SVM model was developed using the genetic algorithm, which showed significantly greater performance predicting persistent AKI than the model based on clinical variables in a holdout subset (AUC: 0.948 [0.912, 0.984] vs. 0.739 [0.648, 0.830]; p < 0.01 for Delong{\textquoteright}s test). Conclusions: Our study identified four subtypes of sepsis-induced AKI based on kidney injury trajectories. The landscape of host response aberrations across these subtypes was characterized. An SVM model based on a gene signature was developed to predict renal function trajectories, and showed better performance than the clinical variable-based model. Future studies are warranted to validate the gene model in distinguishing persistent from transient AKI.",

keywords = "Acute kidney injury, Genetic algorithms, RNA-seq, Sepsis, Support vector machine",

author = "{CMAISE Consortium} and Zhongheng Zhang and Lin Chen and Huiheng Liu and Yujing Sun and Pengfei Shui and Jian Gao and Decong Wang and Huilin Jiang and Yanling Li and Kun Chen and Yucai Hong and Lifeng Xing and Senjun Jin and Jian Sun and Yi Yang and Xiaohong Jin and Min Yang and Chunmei Gui and Yingpu Yuan and Guangtao Dong and Weizhong Zeng and Jing Zeng and Guoxin Hu and Lujun Qiao and Jinhua Wang and Yonglin Xi and Nan Wang and Minmin Wang and Yan Teng and Junxia Hou and Qiaojie Bi and Gengsheng Zhang and Junru Dai",

note = "Funding Information: Z.Z. received funding from the Health Science and Technology Plan of Zhejiang Province (2021KY745), the Fundamental Research Funds for the Central Universities (226-2022-00148), National natural science foundation of China (82272180) and the Project of Drug Clinical Evaluate Research of Chinese Pharmaceutical Association NO.CPA-Z06-ZC-2021-004. Y.H. received funding from the Key Research & Development project of Zhejiang Province (2021C03071), K.C. received funding from the Key Research & Development project of Zhejiang Province (2020C03019). Funding Information: The members of the CMAISE consortium were as follows: Yucai Hong, Lifeng Xing, Zhongheng Zhang (Sir Run Run Shaw Hospital, Zhejiang University School of Medicine); Senjun Jin (Department of Emergency, Zhejiang Provincial People{\textquoteright}s Hospital, People{\textquoteright}s Hospital of Hangzhou Medical College); Lin Chen, Kun Chen (Department of Critical Care Medicine, Affiliated Jinhua Hospital, Zhejiang University School of Medicine); Jian Sun (Department of Critical Care Medicine, Lishui Center Hospital); Yi Yang (Department of Emergency Medicine, The Second Hospital of Jiaxing); Xiaohong Jin (Department of Emergency Medicine, The Affiliated Wenling Hospital of Wenzhou Medical University); Min Yang (The 2nd Department of Intensive Care Unit, the Second Affiliated Hospital of Anhui Medical University); Chunmei Gui, Yingpu Yuan (Department of Critical Care Medicine, The First People{\textquoteright}s Hospital of Changde City); Guangtao Dong (Department of Emergency Medicine, the First Affiliated Hospital of Harbin Medical University); Weizhong Zeng, Jing Zeng (Department of critical care medicine, Zhuzhou central hospital); Guoxin Hu, Lujun Qiao (Emergency Department, Shengli Oilfield Central Hospital); Jinhua Wang, Yonglin Xi (Department of critical care medicine, the Second Affiliated Hospital of Xi{\textquoteright}an Medical University); Nan Wang, Minmin Wang (Department of critical care medicine, The Fourth Affiliated Hospital of Anhui Medical University, Anhui Medical University); Yan Teng, Junxia Hou (Department of critical care medicine, the first affiliated hospital of Xi'an Jiaotong University); Qiaojie Bi (Department of emergency, Qingdao municipal hospital, Qingdao university school of medicine); Gengsheng Zhang (Department of Critical Care Medicine, Second Affiliated Hospital, Zhejiang University School of Medicine); Junru Dai (Longyou People{\textquoteright}s hospital, Longyou, Zhejiang). We would like to thank reviewers and Dr. Ketao Jin from Jinhua central hospital for their thoughtful comments and suggestions on our manuscript. Publisher Copyright: {\textcopyright} 2022, The Author(s).",

year = "2022",

month = dec,

doi = "10.1186/s13054-022-04234-3",

language = "English (US)",

volume = "26",

journal = "Critical Care",

issn = "1364-8535",

publisher = "BioMed Central Ltd.",

number = "1",

}

TY - JOUR

T1 - Gene signature for the prediction of the trajectories of sepsis-induced acute kidney injury

AU - CMAISE Consortium

AU - Zhang, Zhongheng

AU - Chen, Lin

AU - Liu, Huiheng

AU - Sun, Yujing

AU - Shui, Pengfei

AU - Gao, Jian

AU - Wang, Decong

AU - Jiang, Huilin

AU - Li, Yanling

AU - Chen, Kun

AU - Hong, Yucai

AU - Xing, Lifeng

AU - Jin, Senjun

AU - Sun, Jian

AU - Yang, Yi

AU - Jin, Xiaohong

AU - Yang, Min

AU - Gui, Chunmei

AU - Yuan, Yingpu

AU - Dong, Guangtao

AU - Zeng, Weizhong

AU - Zeng, Jing

AU - Hu, Guoxin

AU - Qiao, Lujun

AU - Wang, Jinhua

AU - Xi, Yonglin

AU - Wang, Nan

AU - Wang, Minmin

AU - Teng, Yan

AU - Hou, Junxia

AU - Bi, Qiaojie

AU - Zhang, Gengsheng

AU - Dai, Junru

N1 - Funding Information: Z.Z. received funding from the Health Science and Technology Plan of Zhejiang Province (2021KY745), the Fundamental Research Funds for the Central Universities (226-2022-00148), National natural science foundation of China (82272180) and the Project of Drug Clinical Evaluate Research of Chinese Pharmaceutical Association NO.CPA-Z06-ZC-2021-004. Y.H. received funding from the Key Research & Development project of Zhejiang Province (2021C03071), K.C. received funding from the Key Research & Development project of Zhejiang Province (2020C03019). Funding Information: The members of the CMAISE consortium were as follows: Yucai Hong, Lifeng Xing, Zhongheng Zhang (Sir Run Run Shaw Hospital, Zhejiang University School of Medicine); Senjun Jin (Department of Emergency, Zhejiang Provincial People’s Hospital, People’s Hospital of Hangzhou Medical College); Lin Chen, Kun Chen (Department of Critical Care Medicine, Affiliated Jinhua Hospital, Zhejiang University School of Medicine); Jian Sun (Department of Critical Care Medicine, Lishui Center Hospital); Yi Yang (Department of Emergency Medicine, The Second Hospital of Jiaxing); Xiaohong Jin (Department of Emergency Medicine, The Affiliated Wenling Hospital of Wenzhou Medical University); Min Yang (The 2nd Department of Intensive Care Unit, the Second Affiliated Hospital of Anhui Medical University); Chunmei Gui, Yingpu Yuan (Department of Critical Care Medicine, The First People’s Hospital of Changde City); Guangtao Dong (Department of Emergency Medicine, the First Affiliated Hospital of Harbin Medical University); Weizhong Zeng, Jing Zeng (Department of critical care medicine, Zhuzhou central hospital); Guoxin Hu, Lujun Qiao (Emergency Department, Shengli Oilfield Central Hospital); Jinhua Wang, Yonglin Xi (Department of critical care medicine, the Second Affiliated Hospital of Xi’an Medical University); Nan Wang, Minmin Wang (Department of critical care medicine, The Fourth Affiliated Hospital of Anhui Medical University, Anhui Medical University); Yan Teng, Junxia Hou (Department of critical care medicine, the first affiliated hospital of Xi'an Jiaotong University); Qiaojie Bi (Department of emergency, Qingdao municipal hospital, Qingdao university school of medicine); Gengsheng Zhang (Department of Critical Care Medicine, Second Affiliated Hospital, Zhejiang University School of Medicine); Junru Dai (Longyou People’s hospital, Longyou, Zhejiang). We would like to thank reviewers and Dr. Ketao Jin from Jinhua central hospital for their thoughtful comments and suggestions on our manuscript. Publisher Copyright: © 2022, The Author(s).

PY - 2022/12

Y1 - 2022/12

N2 - Background: Acute kidney injury (AKI) is a common complication in sepsis. However, the trajectories of sepsis-induced AKI and their transcriptional profiles are not well characterized. Methods: Sepsis patients admitted to centres participating in Chinese Multi-omics Advances In Sepsis (CMAISE) from November 2020 to December 2021 were enrolled, and gene expression in peripheral blood mononuclear cells was measured on Day 1. The renal function trajectory was measured by the renal component of the SOFA score (SOFArenal) on Days 1 and 3. Transcriptional profiles on Day 1 were compared between these renal function trajectories, and a support vector machine (SVM) was developed to distinguish transient from persistent AKI. Results: A total of 172 sepsis patients were enrolled during the study period. The renal function trajectory was classified into four types: non-AKI (SOFArenal = 0 on Days 1 and 3, n = 50), persistent AKI (SOFArenal > 0 on Days 1 and 3, n = 62), transient AKI (SOFArenal > 0 on Day 1 and SOFArenal = 0 on Day 3, n = 50) and worsening AKI (SOFArenal = 0 on Days 1 and SOFArenal > 0 on Day 3, n = 10). The persistent AKI group showed severe organ dysfunction and prolonged requirements for organ support. The worsening AKI group showed the least organ dysfunction on day 1 but had higher serum lactate and prolonged use of vasopressors than the non-AKI and transient AKI groups. There were 2091 upregulated and 1,902 downregulated genes (adjusted p < 0.05) between the persistent and transient AKI groups, with enrichment in the plasma membrane complex, receptor complex, and T-cell receptor complex. A 43-gene SVM model was developed using the genetic algorithm, which showed significantly greater performance predicting persistent AKI than the model based on clinical variables in a holdout subset (AUC: 0.948 [0.912, 0.984] vs. 0.739 [0.648, 0.830]; p < 0.01 for Delong’s test). Conclusions: Our study identified four subtypes of sepsis-induced AKI based on kidney injury trajectories. The landscape of host response aberrations across these subtypes was characterized. An SVM model based on a gene signature was developed to predict renal function trajectories, and showed better performance than the clinical variable-based model. Future studies are warranted to validate the gene model in distinguishing persistent from transient AKI.

AB - Background: Acute kidney injury (AKI) is a common complication in sepsis. However, the trajectories of sepsis-induced AKI and their transcriptional profiles are not well characterized. Methods: Sepsis patients admitted to centres participating in Chinese Multi-omics Advances In Sepsis (CMAISE) from November 2020 to December 2021 were enrolled, and gene expression in peripheral blood mononuclear cells was measured on Day 1. The renal function trajectory was measured by the renal component of the SOFA score (SOFArenal) on Days 1 and 3. Transcriptional profiles on Day 1 were compared between these renal function trajectories, and a support vector machine (SVM) was developed to distinguish transient from persistent AKI. Results: A total of 172 sepsis patients were enrolled during the study period. The renal function trajectory was classified into four types: non-AKI (SOFArenal = 0 on Days 1 and 3, n = 50), persistent AKI (SOFArenal > 0 on Days 1 and 3, n = 62), transient AKI (SOFArenal > 0 on Day 1 and SOFArenal = 0 on Day 3, n = 50) and worsening AKI (SOFArenal = 0 on Days 1 and SOFArenal > 0 on Day 3, n = 10). The persistent AKI group showed severe organ dysfunction and prolonged requirements for organ support. The worsening AKI group showed the least organ dysfunction on day 1 but had higher serum lactate and prolonged use of vasopressors than the non-AKI and transient AKI groups. There were 2091 upregulated and 1,902 downregulated genes (adjusted p < 0.05) between the persistent and transient AKI groups, with enrichment in the plasma membrane complex, receptor complex, and T-cell receptor complex. A 43-gene SVM model was developed using the genetic algorithm, which showed significantly greater performance predicting persistent AKI than the model based on clinical variables in a holdout subset (AUC: 0.948 [0.912, 0.984] vs. 0.739 [0.648, 0.830]; p < 0.01 for Delong’s test). Conclusions: Our study identified four subtypes of sepsis-induced AKI based on kidney injury trajectories. The landscape of host response aberrations across these subtypes was characterized. An SVM model based on a gene signature was developed to predict renal function trajectories, and showed better performance than the clinical variable-based model. Future studies are warranted to validate the gene model in distinguishing persistent from transient AKI.

KW - Acute kidney injury

KW - Genetic algorithms

KW - RNA-seq

KW - Sepsis

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=85144598078&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85144598078&partnerID=8YFLogxK

U2 - 10.1186/s13054-022-04234-3

DO - 10.1186/s13054-022-04234-3

M3 - Article

C2 - 36544199

AN - SCOPUS:85144598078

SN - 1364-8535

VL - 26

JO - Critical Care

JF - Critical Care

IS - 1

M1 - 398

ER -

Gene signature for the prediction of the trajectories of sepsis-induced acute kidney injury

Abstract

Bibliographical note

Keywords

PubMed: MeSH publication types

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this