51
|
Zhang Z, Pan Q, Ge H, Xing L, Hong Y, Chen P. Deep learning-based clustering robustly identified two classes of sepsis with both prognostic and predictive values. EBioMedicine 2020; 62:103081. [PMID: 33181462 PMCID: PMC7658497 DOI: 10.1016/j.ebiom.2020.103081] [Citation(s) in RCA: 37] [Impact Index Per Article: 9.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/06/2020] [Revised: 09/19/2020] [Accepted: 10/07/2020] [Indexed: 02/07/2023] Open
Abstract
BACKGROUND Sepsis is a heterogenous syndrome and individualized management strategy is the key to successful treatment. Genome wide expression profiling has been utilized for identifying subclasses of sepsis, but the clinical utility of these subclasses was limited because of the classification instability, and the lack of a robust class prediction model with extensive external validation. The study aimed to develop a parsimonious class model for the prediction of class membership and validate the model for its prognostic and predictive capability in external datasets. METHODS The Gene Expression Omnibus (GEO) and ArrayExpress databases were searched from inception to April 2020. Datasets containing whole blood gene expression profiling in adult sepsis patients were included. Autoencoder was used to extract representative features for k-means clustering. Genetic algorithms (GA) were employed to derive a parsimonious 5-gene class prediction model. The class model was then applied to external datasets (n = 780) to evaluate its prognostic and predictive performance. FINDINGS A total of 12 datasets involving 1613 patients were included. Two classes were identified in the discovery cohort (n = 685). Class 1 was characterized by immunosuppression with higher mortality than class 2 (21.8% [70/321] vs. 12.1% [44/364]; p < 0.01 for Chi-square test). A 5-gene class model (C14orf159, AKNA, PILRA, STOM and USP4) was developed with GA. In external validation cohorts, the 5-gene class model (AUC: 0.707; 95% CI: 0.664 - 0.750) performed better in predicting mortality than sepsis response signature (SRS) endotypes (AUC: 0.610; 95% CI: 0.521 - 0.700), and performed equivalently to the APACHE II score (AUC: 0.681; 95% CI: 0.595 - 0.767). In the dataset E-MTAB-7581, the use of hydrocortisone was associated with increased risk of mortality (OR: 3.15 [1.13, 8.82]; p = 0.029) in class 2. The effect was not statistically significant in class 1 (OR: 1.88 [0.70, 5.09]; p = 0.211). INTERPRETATION Our study identified two classes of sepsis that showed different mortality rates and responses to hydrocortisone therapy. Class 1 was characterized by immunosuppression with higher mortality rate than class 2. We further developed a 5-gene class model to predict class membership. FUNDING The study was funded by the National Natural Science Foundation of China (Grant No. 81,901,929).
Collapse
Affiliation(s)
- Zhongheng Zhang
- Department of Emergency Medicine, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou, 310016, China.
| | - Qing Pan
- College of Information Engineering, Zhejiang University of Technology, 310023, Hangzhou, China.
| | - Huiqing Ge
- Department of Respiratory Care, Sir Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou, China.
| | - Lifeng Xing
- Department of Emergency Medicine, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou, 310016, China.
| | - Yucai Hong
- Department of Emergency Medicine, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou, 310016, China
| | - Pengpeng Chen
- Department of Emergency Medicine, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou, 310016, China.
| |
Collapse
|
52
|
Thau MR, Bhatraju PK. Sub-Phenotypes of Acute Kidney Injury: Do We Have Progress for Personalizing Care? Nephron Clin Pract 2020; 144:677-679. [PMID: 33091901 PMCID: PMC7708595 DOI: 10.1159/000511321] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/22/2020] [Accepted: 09/02/2020] [Indexed: 11/19/2022] Open
Abstract
Acute kidney injury (AKI) is the most common form of organ dysfunction occurring in patients admitted to the intensive care unit and contributes significantly to poor long-term outcomes. Despite this public health impact, no effective pharmacotherapy exists for AKI. One reason may be that heterogeneity is present within AKI as currently defined, thereby concealing unique pathophysiologic processes specific to certain AKI populations. Supporting this notion, we and others have shown that diversity within the AKI clinical syndrome exists, and the "one-size-fits-all" approach by current diagnostic guidelines may not be ideal. A "precision medicine" approach that exploits an individual's genetic, biologic, and clinical characteristics to identify AKI sub-phenotypes may overcome such limitations. Identification of AKI sub-phenotypes may address a critical unmet clinical need in AKI by (1) improving risk prognostication, (2) identifying novel pathophysiology, and (3) informing a patient's likelihood of responding to current therapeutics or establishing new therapeutic targets to prevent and treat AKI. This review discusses the current state of phenotyping AKI and future directions.
Collapse
Affiliation(s)
- Matthew R Thau
- Division of Pulmonary, Critical Care and Sleep Medicine, Department of Medicine, University of Washington, Seattle, Washington, USA
| | - Pavan K Bhatraju
- Division of Pulmonary, Critical Care and Sleep Medicine, Department of Medicine, University of Washington, Seattle, Washington, USA,
- Division of Nephrology, Department of Medicine, Kidney Research Institute, University of Washington, Seattle, Washington, USA,
| |
Collapse
|
53
|
Zhang Z, Chen L, Xu P, Xing L, Hong Y, Chen P. Gene correlation network analysis to identify regulatory factors in sepsis. J Transl Med 2020; 18:381. [PMID: 33032623 PMCID: PMC7545567 DOI: 10.1186/s12967-020-02561-z] [Citation(s) in RCA: 24] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/26/2020] [Accepted: 10/03/2020] [Indexed: 02/07/2023] Open
Abstract
BACKGROUND AND OBJECTIVES Sepsis is a leading cause of mortality and morbidity in the intensive care unit. Regulatory mechanisms underlying the disease progression and prognosis are largely unknown. The study aimed to identify master regulators of mortality-related modules, providing potential therapeutic target for further translational experiments. METHODS The dataset GSE65682 from the Gene Expression Omnibus (GEO) database was utilized for bioinformatic analysis. Consensus weighted gene co-expression netwoek analysis (WGCNA) was performed to identify modules of sepsis. The module most significantly associated with mortality were further analyzed for the identification of master regulators of transcription factors and miRNA. RESULTS A total number of 682 subjects with various causes of sepsis were included for consensus WGCNA analysis, which identified 27 modules. The network was well preserved among different causes of sepsis. Two modules designated as black and light yellow module were found to be associated with mortality outcome. Key regulators of the black and light yellow modules were the transcription factor CEBPB (normalized enrichment score = 5.53) and ETV6 (NES = 6), respectively. The top 5 miRNA regulated the most number of genes were hsa-miR-335-5p (n = 59), hsa-miR-26b-5p (n = 57), hsa-miR-16-5p (n = 44), hsa-miR-17-5p (n = 42), and hsa-miR-124-3p (n = 38). Clustering analysis in 2-dimension space derived from manifold learning identified two subclasses of sepsis, which showed significant association with survival in Cox proportional hazard model (p = 0.018). CONCLUSIONS The present study showed that the black and light-yellow modules were significantly associated with mortality outcome. Master regulators of the module included transcription factor CEBPB and ETV6. miRNA-target interactions identified significantly enriched miRNA.
Collapse
Affiliation(s)
- Zhongheng Zhang
- grid.13402.340000 0004 1759 700XDepartment of Emergency Medicine, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, No 3, East Qingchun Road, Hangzhou, 310016 Zhejiang Province China
| | - Lin Chen
- grid.13402.340000 0004 1759 700XDepartment of Critical Care Medicine, Affiliated Jinhua Hospital, Zhejiang University School of Medicine, Jinhua, China
| | - Ping Xu
- Emergency Department, Zigong Fourth People’s Hospital, 19 Tanmulin Road, Zigong, Sichuan China
| | - Lifeng Xing
- grid.13402.340000 0004 1759 700XDepartment of Emergency Medicine, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, No 3, East Qingchun Road, Hangzhou, 310016 Zhejiang Province China
| | - Yucai Hong
- grid.13402.340000 0004 1759 700XDepartment of Emergency Medicine, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, No 3, East Qingchun Road, Hangzhou, 310016 Zhejiang Province China
| | - Pengpeng Chen
- grid.13402.340000 0004 1759 700XDepartment of Emergency Medicine, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, No 3, East Qingchun Road, Hangzhou, 310016 Zhejiang Province China
| |
Collapse
|
54
|
Chaudhary K, Vaid A, Duffy Á, Paranjpe I, Jaladanki S, Paranjpe M, Johnson K, Gokhale A, Pattharanitima P, Chauhan K, O'Hagan R, Van Vleck T, Coca SG, Cooper R, Glicksberg B, Bottinger EP, Chan L, Nadkarni GN. Utilization of Deep Learning for Subphenotype Identification in Sepsis-Associated Acute Kidney Injury. Clin J Am Soc Nephrol 2020; 15:1557-1565. [PMID: 33033164 PMCID: PMC7646246 DOI: 10.2215/cjn.09330819] [Citation(s) in RCA: 59] [Impact Index Per Article: 14.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/11/2019] [Accepted: 08/07/2020] [Indexed: 11/23/2022]
Abstract
BACKGROUND AND OBJECTIVES Sepsis-associated AKI is a heterogeneous clinical entity. We aimed to agnostically identify sepsis-associated AKI subphenotypes using deep learning on routinely collected data in electronic health records. DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS We used the Medical Information Mart for Intensive Care III database, which consists of electronic health record data from intensive care units in a tertiary care hospital in the United States. We included patients ≥18 years with sepsis who developed AKI within 48 hours of intensive care unit admission. We then used deep learning to utilize all available vital signs, laboratory measurements, and comorbidities to identify subphenotypes. Outcomes were mortality 28 days after AKI and dialysis requirement. RESULTS We identified 4001 patients with sepsis-associated AKI. We utilized 2546 combined features for K-means clustering, identifying three subphenotypes. Subphenotype 1 had 1443 patients, and subphenotype 2 had 1898 patients, whereas subphenotype 3 had 660 patients. Subphenotype 1 had the lowest proportion of liver disease and lowest Simplified Acute Physiology Score II scores compared with subphenotypes 2 and 3. The proportions of patients with CKD were similar between subphenotypes 1 and 3 (15%) but highest in subphenotype 2 (21%). Subphenotype 1 had lower median bilirubin levels, aspartate aminotransferase, and alanine aminotransferase compared with subphenotypes 2 and 3. Patients in subphenotype 1 also had lower median lactate, lactate dehydrogenase, and white blood cell count than patients in subphenotypes 2 and 3. Subphenotype 1 also had lower creatinine and BUN than subphenotypes 2 and 3. Dialysis requirement was lowest in subphenotype 1 (4% versus 7% [subphenotype 2] versus 26% [subphenotype 3]). The mortality 28 days after AKI was lowest in subphenotype 1 (23% versus 35% [subphenotype 2] versus 49% [subphenotype 3]). After adjustment, the adjusted odds ratio for mortality for subphenotype 3, with subphenotype 1 as a reference, was 1.9 (95% confidence interval, 1.5 to 2.4). CONCLUSIONS Utilizing routinely collected laboratory variables, vital signs, and comorbidities, we were able to identify three distinct subphenotypes of sepsis-associated AKI with differing outcomes.
Collapse
Affiliation(s)
- Kumardeep Chaudhary
- Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, New York
| | - Akhil Vaid
- Hasso Plattner Institute of Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, New York
| | - Áine Duffy
- Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, New York
| | - Ishan Paranjpe
- Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, New York
| | - Suraj Jaladanki
- Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, New York
| | - Manish Paranjpe
- Harvard Medical School, Boston, Massachusetts.,Cardiovascular Disease Initiative, Broad Institute of MIT and Harvard, Cambridge, Massachusetts
| | - Kipp Johnson
- Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, New York
| | - Avantee Gokhale
- Division of Nephrology, Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, New York
| | - Pattharawin Pattharanitima
- Division of Nephrology, Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, New York
| | - Kinsuk Chauhan
- Division of Nephrology, Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, New York
| | - Ross O'Hagan
- Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, New York
| | - Tielman Van Vleck
- Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, New York
| | - Steven G Coca
- Division of Nephrology, Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, New York
| | - Richard Cooper
- Department of Public Health Sciences, Loyola University School of Medicine, Chicago, Illinois
| | - Benjamin Glicksberg
- Hasso Plattner Institute of Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, New York
| | - Erwin P Bottinger
- Hasso Plattner Institute of Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, New York
| | - Lili Chan
- Division of Nephrology, Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, New York
| | - Girish N Nadkarni
- Hasso Plattner Institute of Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, New York .,Division of Nephrology, Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, New York
| |
Collapse
|