Two subphenotypes of septic acute kidney injury are associated with different 90-day mortality and renal recovery

Wiersema, Renske; Jukarainen, Sakari; Vaara, Suvi T.; Poukkanen, Meri; Lakkisto, Päivi; Wong, Hector R.; Linder, Adam; Horst, Iwan C. C. van der; Pettilä, Ville

doi:10.1186/s13054-020-02866-x

Cited by 63 publications

(74 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… [10] ). Others also identified several subphenotypes by utilizing large clinical database and showed that these subphenotypes can have important implications for clinical treatment and trial design [ 3 , 11 , 12 ]. However, these studies input routinely collected clinical data as features for clustering analysis.…”

Section: Introductionmentioning

confidence: 99%

Deep learning-based clustering robustly identified two classes of sepsis with both prognostic and predictive values

Zhang

Pan

et al. 2020

eBioMedicine

View full text Add to dashboard Cite

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).

show abstract

Section: Introductionmentioning

confidence: 99%

Deep learning-based clustering robustly identified two classes of sepsis with both prognostic and predictive values

Zhang

Pan

et al. 2020

eBioMedicine

View full text Add to dashboard Cite

show abstract

“…The approach has recently been increasingly used in the medical field. LCA has been extensively used to identify subphenotypes of disease [13,14,33,34], but has not been highly utilized in the risk prediction field. In general, this is the first study that used the LCA method to identify the subpopulation at high risk of incident diabetes among Chinese adults.…”

Section: Discussionmentioning

confidence: 99%

Applying latent class analysis to risk stratification of incident diabetes among Chinese adults

Chen

et al. 2021

Diabetes Research and Clinical Practice

View full text Add to dashboard Cite

To use latent class analysis to identify unobservable subpopulations amongst the heterogeneous population and explore the relationship between subpopulations and incident diabetes among Chinese adults. Methods: The retrospective study included 32,312 Chinese adults without diabetes at baseline. Latent class indicators included demographic and clinical variables. The outcome was incident diabetes. The relationship between latent class and outcome was evaluated with Cox proportional hazard regression analysis.Results: After screening, the two-class latent class model best fits the population. Participants in class 2 are characterized by higher age, body mass index, systolic and diastolic blood pressure, fasting plasma glucose, total cholesterol, triglyceride, low-density lipoprotein cholesterol, serum creatinine, serum urea nitrogen, alanine aminotransferase, and a higher proportion of males, ever/current smokers and drinkers, but lower high-density lipoprotein cholesterol and a lower proportion of family history of diabetes. The risk of diabetes in class 2 was 5.451 times (HR: 6.451, 95%CI: 4.179-9.960, P < 0.00001) and 5.264 times (HR: 6.264, 95%CI: 4.680-8.385, P < 0.00001) higher than that in class 1 during 3-year and 5year follow-up, respectively. Conclusions:We used latent class analysis to identify two distinct subpopulations with differential risk of diabetes during 3-year and 5-year follow-up.

show abstract

“…Since the upregulation of the black module is significantly associated with mortality, drugs targeting these sites may improve the survival outcome. Third, although sepsis is a heterogeneous syndrome [34][35][36][37][38], different types of sepsis share some common important immune regulatory pathways.…”

Section: Discussionmentioning

confidence: 99%

Gene correlation network analysis to identify regulatory factors in sepsis

Zhang

Chen

et al. 2020

J Transl Med

View full text Add to dashboard Cite

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.

show abstract

Two subphenotypes of septic acute kidney injury are associated with different 90-day mortality and renal recovery

Cited by 63 publications

References 46 publications

Deep learning-based clustering robustly identified two classes of sepsis with both prognostic and predictive values

Deep learning-based clustering robustly identified two classes of sepsis with both prognostic and predictive values

Applying latent class analysis to risk stratification of incident diabetes among Chinese adults

Gene correlation network analysis to identify regulatory factors in sepsis

Contact Info

Product

Resources

About