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

Identifying septic shock subgroups to tailor fluid strategies through multi-omics integration

Fluid management remains a critical challenge in the treatment of septic shock, with individualized approaches lacking. This study aims to develop a statistical model based on transcriptomics to identify subgroups of septic shock patients with varied responses to fluid strategy. The study encompasses 494 septic shock patients. A benefit score is derived from the transcriptome space, with higher values indicating greater benefits from restrictive fluid strategy. Adherence to the recommended strategy is associated with a hazard ratio of 0.82 (95% confidence interval: 0.64-0.92). When applied to the baseline hospital mortality rate of 16%, adherence to the recommended fluid strategy could potentially lower this rate to 13%. A proteomic signature comprising six proteins is developed to predict the benefit score, yielding an area under the curve of 0.802 (95% confidence interval: 0.752-0.846) in classifying patients who may benefit from a restrictive strategy. In this work, we develop a proteomic signature with potential utility in guiding fluid strategy for septic shock patients.

SAFE-MIL: a statistically interpretable framework for screening potential targeted therapy patients based on risk estimation

Patients with the target gene mutation frequently derive significant clinical benefits from target therapy. However, differences in the abundance level of mutations among patients resulted in varying survival benefits, even among patients with the same target gene mutations. Currently, there is a lack of rational and interpretable models to assess the risk of treatment failure. In this study, we investigated the underlying coupled factors contributing to variations in medication sensitivity and established a statistically interpretable framework, named SAFE-MIL, for risk estimation. We first constructed an effectiveness label for each patient from the perspective of exploring the optimal grouping of patients' positive judgment values and sampled patients into 600 and 1,000 groups, respectively, based on multi-instance learning (MIL). A novel and interpretable loss function was further designed based on the Hosmer-Lemeshow test for this framework. By integrating multi-instance learning with the Hosmer-Lemeshow test, SAFE-MIL is capable of accurately estimating the risk of drug treatment failure across diverse patient cohorts and providing the optimal threshold for assessing the risk stratification simultaneously. We conducted a comprehensive case study involving 457 non-small cell lung cancer patients with EGFR mutations treated with EGFR tyrosine kinase inhibitors. Results demonstrate that SAFE-MIL outperforms traditional regression methods with higher accuracy and can accurately assess patients' risk stratification. This underscores its ability to accurately capture inter-patient variability in risk while providing statistical interpretability. SAFE-MIL is able to effectively guide clinical decision-making regarding the use of drugs in targeted therapy and provides an interpretable computational framework for other patient stratification problems. The SAFE-MIL framework has proven its effectiveness in capturing inter-patient variability in risk and providing statistical interpretability. It outperforms traditional regression methods and can effectively guide clinical decision-making in the use of drugs for targeted therapy. SAFE-MIL offers a valuable interpretable computational framework that can be applied to other patient stratification problems, enhancing the precision of risk assessment in personalized medicine. The source code for SAFE-MIL is available for further exploration and application at https://github.com/Nevermore233/SAFE-MIL.

Comprehensive analysis of sialylation-related genes and construct the prognostic model in sepsis

Sepsis, a life-threatening syndrome, continues to be a significant public health issue worldwide. Sialylation is a hot potential marker that affects the surface of a variety of cells. However, the role of genes related to sialylation and sepsis has not been fully explored. Bulk RNA-seq data sets (GSE66099 and GSE65682) were obtained from the open-access databases GEO. The classification of sepsis samples into subtypes was achieved by employing the R package "ConsensusClusterPlus" on the bulk RNA-seq data. Hub genes were discerned through the application of the R package "limma" and univariate regression analysis, with the calculation of risk scores carried out using the R package "survminer". To identify the best learning method and construct a prognostic model, we used 21 different combinations of machine learning, and C-index ranking results of these combinations have been showed. ROC curves, time-dependent ROC curves, and Kaplan-Meier curves were utilized to evaluate the diagnostic accuracy of the model. The R packages "ESTIMATE" and "GSVA" were employed to quantify the fractions of immune cell infiltration in each sample. The bulk RNA-seq samples were categorized into two distinct sepsis subtypes utilizing 14 prognosis-related sialylation genes. A total of 20 differentially expressed genes (DEGs) were identified as being associated with the relationship between sepsis and sialylation. The RSF was used to identify key genes with importance scores higher than 0.01. The nine hub genes (SLA2A1, TMCC2, TFRC, RHAG, FKBP1B, KLF1, PILRA, ARL4A, and GYPA) with the importance values greater than 0.01 was selected for constructing the prognostic model. This research offers some understanding of the relationship between sepsis and sialylation. Besides, it contains one predictive model that might develop into diagnostic biomarkers for sepsis.

Informative Subtyping of Patients with Sepsis

Sepsis pathobiology is complex. Heterogeneity refers to the clinical and biological variation within sepsis cohorts. Sepsis subtypes refer to subpopulations within sepsis cohorts derived based on these observable variations and latent features. The overarching goal of such endeavors is to enable precision immunomodulation. However, we are yet to identify immune endotypes of sepsis to achieve this goal. The sepsis subtyping field is just starting to take shape. The current subtypes in the literature do not have a core set of shared features between studies. Thus, in this narrative review, we reason that there is a need to a priori state the purpose of sepsis subtyping and minimum set of features that would be required to achieve the goal of precision immunomodulation for future sepsis.

Identification of four mitochondria-related genes in sepsis based on RNA sequencing technology

OBJECTIVES

The purpose of this study was to identify and analyze the mitochondrial genes associated with sepsis patients in order to elucidate the underlying mechanism of sepsis immunity and provide new ideas for the clinical treatment of sepsis.

METHODS

The hospitalized cases of sepsis (n = 20) and systemic inflammatory response syndrome (SIRS) (n = 12) admitted to the Emergency Intensive Care Unit (EICU) of the Affiliated Hospital of Southwest Medical University from January 2019 to December 2019 were collected consecutively. RNA-seq was used to sequence the RNA (mRNA) of peripheral blood cells. Bioinformatics techniques were used to screen and identify differentially expressed RNAs, with an absolute value of fold change (FC) greater than or equal to 1.2 and a false discovery rate (FDR) less than 0.05. At the same time, mitochondrial genes were obtained from the MitoCarta 3.0 database. Differential genes were then intersected with mitochondrial genes. The resulting crossover genes were subjected to GO, KEGG, and PPI analysis. Subsequently, the GSE65682 dataset was downloaded from the GEO database for survival analysis to assess the prognostic value of core genes, and GSE67652 was downloaded for ROC curve analysis to validate the diagnostic value of core genes. Finally, the localization of core genes was clarified through 10X single-cell sequencing.

RESULTS

The crossing of 314 sepsis differential genes and 1136 mitochondrial genes yielded 28 genes. GO and KEGG analysis showed that the crossover genes were mainly involved in the mitochondrion, mitochondrial matrix, and mitochondrial inner membrane. Survival analysis screened four genes that were significantly negatively associated with the prognosis of sepsis, namely FIS1, FKBP8, GLRX5, and GUK1. A comparison of peripheral blood RNA-seq results between the sepsis group and the SIRS group showed that the expression levels of these four genes were significantly decreased in the sepsis group compared to the SIRS group. ROC curve analysis based on GSE67652 indicates these four genes' high sensitivity and specificity for sepsis detection. Additionally, single-cell RNA sequencing found that the core genes were mainly expressed in macrophages, T cells, and B cells.

CONCLUSIONS

Mitochondria-related genes (FIS1, FKBP8, GLRX5, GUK1) were underexpressed in the sepsis group, negatively correlated with survival, and mainly distributed in immune cells. This finding may guide studying the immune-related mechanisms of sepsis. This study protocol was reviewed by the Ethics Committee of the Affiliated Hospital of Southwest Medical University (ethics number: KY2018029), the clinical trial registration number is ChiCTR1900021261, and the registration date is February 4, 2019.

Machine learning reveals ferroptosis features and a novel ferroptosis classifier in patients with sepsis

OBJECTIVE

Sepsis is an organ malfunction disease that may become fatal and is commonly accompanied by severe complications such as multiorgan dysfunction. Patients who are already hospitalized have a high risk of death due to sepsis. Even though early diagnosis is very important, the technology and clinical approaches that are now available are inadequate. Hence, there is an immediate necessity to investigate biological markers that are sensitive, specific, and reliable for the prompt detection of sepsis to reduce mortality and improve patient prognosis. Mounting research data indicate that ferroptosis contributes to the occurrence, development, and prevention of sepsis. However, the specific regulatory mechanism of ferroptosis remains to be elucidated. This research evaluated the expression profiles of ferroptosis-related genes (FRGs) and the diagnostic significance of the ferroptosis-related classifiers in sepsis.

METHODS AND RESULTS

We collected three peripheral blood data sets from septic patients, integrated the clinical examination data and mRNA expression profile of these patients, and identified 13 FRGs in sepsis through a co-expression network and differential analysis. Then, an optimal classifier tool for sepsis was constructed by integrating a variety of machine learning algorithms. Two key genes, ATG16L1 and SRC, were shown to be shared between the algorithms, and thus were identified as the FRG signature of classifier. The tool exhibited satisfactory diagnostic efficiency in the training data set (AUC = 0.711) and two external verification data sets (AUC = 0.961; AUC = 0.913). In the rat cecal ligation puncture sepsis model, in vivo experiments verified the involvement of ATG16L1 and SRC in the early sepsis process.

CONCLUSION

These findings confirm that FRGs may participate in the development of sepsis, the ferroptosis related classifiers can provide a basis for the development of new strategies for the early diagnosis of sepsis and the discovery of new potential therapeutic targets for life-threatening infections.

Identification and validation of sepsis subphenotypes using time-series data

Purpose

The recognition of sepsis as a heterogeneous syndrome necessitates identifying distinct subphenotypes to select targeted treatment.

Methods

Patients with sepsis from the MIMIC-IV database (2008-2019) were randomly divided into a development cohort (80%) and an internal validation cohort (20%). Patients with sepsis from the ICU database of Peking University People's Hospital (2008-2022) were included in the external validation cohort. Time-series k-means clustering analysis and dynamic time warping was performed to develop and validate sepsis subphenotypes by analyzing the trends of 21 vital signs and laboratory indicators within 24 h after sepsis onset. Inflammatory biomarkers were compared in the ICU database of Peking University People's Hospital, whereas treatment heterogeneity was compared in the MIMIC-IV database.

Findings

Three sub-phenotypes were identified in the development cohort. Type A patients (N = 2525, 47%) exhibited stable vital signs and fair organ function, type B (N = 1552, 29%) was exhibited an obvious inflammatory response and stable organ function, and type C (N = 1251, 24%) exhibited severely impaired organ function with a deteriorating tendency. Type C demonstrated the highest mortality rate (33%) and levels of inflammatory biomarkers, followed by type B (24%), whereas type A exhibited the lowest mortality rate (11%) and levels of inflammatory biomarkers. These subphenotypes were confirmed in both the internal and external cohorts, demonstrating similar features and comparable mortality rates. In type C patients, survivors had significantly lower fluid intake within 24 h after sepsis onset (median 2891 mL, interquartile range (IQR) 1530-5470 mL) than that in non-survivors (median 4342 mL, IQR 2189-7305 mL). For types B and C, survivors showed a higher proportion of indwelling central venous catheters (p < 0.05).

Conclusion

Three novel phenotypes of patients with sepsis were identified and validated using time-series data, revealing significant heterogeneity in inflammatory biomarkers, treatments, and consistency across cohorts.

Using Mendelian randomization provides genetic insights into potential targets for sepsis treatment

Sepsis is recognized as a major contributor to the global disease burden, but there is a lack of specific and effective therapeutic agents. Utilizing Mendelian randomization (MR) methods alongside evidence of causal genetics presents a chance to discover novel targets for therapeutic intervention. MR approach was employed to investigate potential drug targets for sepsis. Pooled statistics from IEU-B-4980 comprising 11,643 cases and 474,841 controls were initially utilized, and the findings were subsequently replicated in the IEU-B-69 (10,154 cases and 454,764 controls). Causal associations were then validated through colocalization. Furthermore, a range of sensitivity analyses, including MR-Egger intercept tests and Cochran's Q tests, were conducted to evaluate the outcomes of the MR analyses. Three drug targets (PSMA4, IFNAR2, and LY9) exhibited noteworthy MR outcomes in two separate datasets. Notably, PSMA4 demonstrated not only an elevated susceptibility to sepsis (OR 1.32, 95% CI 1.20-1.45, p = 1.66E-08) but also exhibited a robust colocalization with sepsis (PPH4 = 0.74). According to the present MR analysis, PSMA4 emerges as a highly encouraging pharmaceutical target for addressing sepsis. Suppression of PSMA4 could potentially decrease the likelihood of sepsis.

Machine learning-derived blood culture classification with both predictive and prognostic values in the intensive care unit: A retrospective cohort study

OBJECTIVES

Diagnosis and management of intensive care unit (ICU)-acquired bloodstream infections are often based on positive blood culture results. This retrospective cohort study aimed to develop a classification model using data-driven characterisation to optimise the management of intensive care patients with blood cultures.

SETTING, METHODOLOGY/DESIGN

An unsupervised clustering model was developed based on the clinical characteristics of patients with blood cultures in the Medical Information Mart for Intensive Care (MIMIC)-IV database (n = 2451). It was tested using the data from the MIMIC-III database (n = 2047).

MAIN OUTCOME MEASURES

The prognosis, blood culture outcomes, antimicrobial interventions, and trajectories of infection indicators were compared between clusters.

RESULTS

Four clusters were identified using machine learning-based k-means clustering based on data obtained 48 h before the first blood culture sampling. Cluster γ was associated with the highest 28-day mortality rate, followed by clusters α, δ, and β. Cluster γ had a higher fungal isolation rate than cluster β (P < 0.05). Cluster δ was associated with a higher isolation rate of Gram-negative organisms and fungi (P < 0.05). Patients in clusters γ and δ underwent more femoral site vein catheter placements than those in cluster β (P < 0.001, all). Patients with a duration of antibiotics treatment of 4, 6, and 7 days in clusters α, δ, and γ, respectively, had the lowest 28-day mortality rate.

CONCLUSIONS

Machine learning identified four clusters of intensive care patients with blood cultures, which yielded different prognoses, blood culture outcomes, and optimal duration of antibiotic treatment. Such data-driven blood culture classifications suggest further investigation should be undertaken to optimise treatment and improve care.

IMPLICATIONS FOR CLINICAL PRACTICE

Intensive care unit-acquired bloodstream infections are heterogeneous. Meaningful classifications associated with outcomes should be described. Using machine learning and cluster analysis could help in understanding heterogeneity. Data-driven blood culture classification could identify distinct physiological states and prognoses before deciding on blood culture sampling, optimise treatment, and improve care.

Whole blood transcriptomics identifies subclasses of pediatric septic shock

BACKGROUND

Sepsis is a highly heterogeneous syndrome, which has hindered the development of effective therapies. This has prompted investigators to develop a precision medicine approach aimed at identifying biologically homogenous subgroups of patients with septic shock and critical illnesses. Transcriptomic analysis can identify subclasses derived from differences in underlying pathophysiological processes that may provide the basis for new targeted therapies. The goal of this study was to elucidate pathophysiological pathways and identify pediatric septic shock subclasses based on whole blood RNA expression profiles.

METHODS

The subjects were critically ill children with cardiopulmonary failure who were a part of a prospective randomized insulin titration trial to treat hyperglycemia. Genome-wide expression profiling was conducted using RNA sequencing from whole blood samples obtained from 46 children with septic shock and 52 mechanically ventilated noninfected controls without shock. Patients with septic shock were allocated to subclasses based on hierarchical clustering of gene expression profiles, and we then compared clinical characteristics, plasma inflammatory markers, cell compositions using GEDIT, and immune repertoires using Imrep between the two subclasses.

RESULTS

Patients with septic shock depicted alterations in innate and adaptive immune pathways. Among patients with septic shock, we identified two subtypes based on gene expression patterns. Compared with Subclass 2, Subclass 1 was characterized by upregulation of innate immunity pathways and downregulation of adaptive immunity pathways. Subclass 1 had significantly worse clinical outcomes despite the two classes having similar illness severity on initial clinical presentation. Subclass 1 had elevated levels of plasma inflammatory cytokines and endothelial injury biomarkers and demonstrated decreased percentages of CD4 T cells and B cells and less diverse T cell receptor repertoires.

CONCLUSIONS

Two subclasses of pediatric septic shock patients were discovered through genome-wide expression profiling based on whole blood RNA sequencing with major biological and clinical differences. Trial Registration This is a secondary analysis of data generated as part of the observational CAF-PINT ancillary of the HALF-PINT study (NCT01565941). Registered March 29, 2012.

N6-methyladenosine modification: Regulatory mechanisms and therapeutic potential in sepsis

Sepsis is a life-threatening organ dysfunction caused by a dysregulated host response to infection and is characterized by multiple biological and clinical features. N6-methyladenosine (m6A) modification is the most common type of RNA modifications in eukaryotes and plays an important regulatory role in various biological processes. Recently, m6A modification has been found to be involved in the regulation of immune responses in sepsis. In addition, several studies have shown that m6A modification is involved in sepsis-induced multiple organ dysfunctions, including cardiovascular dysfunction, acute lung injury (ALI), acute kidney injury (AKI) and etc. Considering the complex pathogenesis of sepsis and the lack of specific therapeutic drugs, m6A modification may be the important bond in the pathophysiological process of sepsis and even therapeutic targets. This review systematically highlights the recent advances regarding the roles of m6A modification in sepsis and sheds light on their use as treatment targets for sepsis.

The two-stage molecular scenery of SARS-CoV-2 infection with implications to disease severity: An in-silico quest

Introduction

The two-stage molecular profile of the progression of SARS-CoV-2 (SCOV2) infection is explored in terms of five key biological/clinical questions: (a) does SCOV2 exhibits a two-stage infection profile? (b) SARS-CoV-1 (SCOV1) vs. SCOV2: do they differ? (c) does and how SCOV2 differs from Influenza/INFL infection? (d) does low viral-load and (e) does COVID-19 early host response relate to the two-stage SCOV2 infection profile? We provide positive answers to the above questions by analyzing the time-series gene-expression profiles of preserved cell-lines infected with SCOV1/2 or, the gene-expression profiles of infected individuals with different viral-loads levels and different host-response phenotypes.

Methods

Our analytical methodology follows an in-silico quest organized around an elaborate multi-step analysis pipeline including: (a) utilization of fifteen gene-expression datasets from NCBI's gene expression omnibus/GEO repository; (b) thorough designation of SCOV1/2 and INFL progression stages and COVID-19 phenotypes; (c) identification of differentially expressed genes (DEGs) and enriched biological processes and pathways that contrast and differentiate between different infection stages and phenotypes; (d) employment of a graph-based clustering process for the induction of coherent groups of networked genes as the representative core molecular fingerprints that characterize the different SCOV2 progression stages and the different COVID-19 phenotypes. In addition, relying on a sensibly selected set of induced fingerprint genes and following a Machine Learning approach, we devised and assessed the performance of different classifier models for the differentiation of acute respiratory illness/ARI caused by SCOV2 or other infections (diagnostic classifiers), as well as for the prediction of COVID-19 disease severity (prognostic classifiers), with quite encouraging results.

Results

The central finding of our experiments demonstrates the down-regulation of type-I interferon genes (IFN-1), interferon induced genes (ISGs) and fundamental innate immune and defense biological processes and molecular pathways during the early SCOV2 infection stages, with the inverse to hold during the later ones. It is highlighted that upregulation of these genes and pathways early after infection may prove beneficial in preventing subsequent uncontrolled hyperinflammatory and potentially lethal events.

Discussion

The basic aim of our study was to utilize in an intuitive, efficient and productive way the most relevant and state-of-the-art bioinformatics methods to reveal the core molecular mechanisms which govern the progression of SCOV2 infection and the different COVID-19 phenotypes.

A simplified machine learning model utilizing platelet-related genes for predicting poor prognosis in sepsis

Background

Thrombocytopenia is a known prognostic factor in sepsis, yet the relationship between platelet-related genes and sepsis outcomes remains elusive. We developed a machine learning (ML) model based on platelet-related genes to predict poor prognosis in sepsis. The model underwent rigorous evaluation on six diverse platforms, ensuring reliable and versatile findings.

Methods

A retrospective analysis of platelet data from 365 sepsis patients confirmed the predictive role of platelet count in prognosis. We employed COX analysis, Least Absolute Shrinkage and Selection Operator (LASSO) and Support Vector Machine (SVM) techniques to identify platelet-related genes from the GSE65682 dataset. Subsequently, these genes were trained and validated on six distinct platforms comprising 719 patients, and compared against the Acute Physiology and Chronic Health Evaluation II (APACHE II) and Sequential Organ-Failure Assessment (SOFA) score.

Results

A PLT count <100×109/L independently increased the risk of death in sepsis patients (OR = 2.523; 95% CI: 1.084-5.872). The ML model, based on five platelet-related genes, demonstrated impressive area under the curve (AUC) values ranging from 0.5 to 0.795 across various validation platforms. On the GPL6947 platform, our ML model outperformed the APACHE II score with an AUC of 0.795 compared to 0.761. Additionally, by incorporating age, the model's performance was further improved to an AUC of 0.812. On the GPL4133 platform, the initial AUC of the machine learning model based on five platelet-related genes was 0.5. However, after including age, the AUC increased to 0.583. In comparison, the AUC of the APACHE II score was 0.604, and the AUC of the SOFA score was 0.542.

Conclusion

Our findings highlight the broad applicability of this ML model, based on platelet-related genes, in facilitating early treatment decisions for sepsis patients with poor outcomes. Our study paves the way for advancements in personalized medicine and improved patient care.

The application of artificial intelligence in the management of sepsis

Sepsis is a complex and heterogeneous syndrome that remains a serious challenge to healthcare worldwide. Patients afflicted by severe sepsis or septic shock are customarily placed under intensive care unit (ICU) supervision, where a multitude of apparatus is poised to produce high-granularity data. This reservoir of high-quality data forms the cornerstone for the integration of AI into clinical practice. However, existing reviews currently lack the inclusion of the latest advancements. This review examines the evolving integration of artificial intelligence (AI) in sepsis management. Applications of artificial intelligence include early detection, subtyping analysis, precise treatment and prognosis assessment. AI-driven early warning systems provide enhanced recognition and intervention capabilities, while profiling analyzes elucidate distinct sepsis manifestations for targeted therapy. Precision medicine harnesses the potential of artificial intelligence for pathogen identification, antibiotic selection, and fluid optimization. In conclusion, the seamless amalgamation of artificial intelligence into the domain of sepsis management heralds a transformative shift, ushering in novel prospects to elevate diagnostic precision, therapeutic efficacy, and prognostic acumen. As AI technologies develop, their impact on shaping the future of sepsis care warrants ongoing research and thoughtful implementation.

Exploring the Role of Different Cell-Death-Related Genes in Sepsis Diagnosis Using a Machine Learning Algorithm

Sepsis, a disease caused by severe infection, has a high mortality rate. At present, there is a lack of reliable algorithmic models for biomarker mining and diagnostic model construction for sepsis. Programmed cell death (PCD) has been shown to play a vital role in disease occurrence and progression, and different PCD-related genes have the potential to be targeted for the treatment of sepsis. In this paper, we analyzed PCD-related genes in sepsis. Implicated PCD processes include apoptosis, necroptosis, ferroptosis, pyroptosis, netotic cell death, entotic cell death, lysosome-dependent cell death, parthanatos, autophagy-dependent cell death, oxeiptosis, and alkaliptosis. We screened for diagnostic-related genes and constructed models for diagnosing sepsis using multiple machine-learning models. In addition, the immune landscape of sepsis was analyzed based on the diagnosis-related genes that were obtained. In this paper, 10 diagnosis-related genes were screened for using machine learning algorithms, and diagnostic models were constructed. The diagnostic model was validated in the internal and external test sets, and the Area Under Curve (AUC) reached 0.7951 in the internal test set and 0.9627 in the external test set. Furthermore, we verified the diagnostic gene via a qPCR experiment. The diagnostic-related genes and diagnostic genes obtained in this paper can be utilized as a reference for clinical sepsis diagnosis. The results of this study can act as a reference for the clinical diagnosis of sepsis and for target discovery for potential therapeutic drugs.

Whole Blood Transcriptomics Identifies Subclasses of Pediatric Septic Shock

Background

Sepsis is a highly heterogeneous syndrome, that has hindered the development of effective therapies. This has prompted investigators to develop a precision medicine approach aimed at identifying biologically homogenous subgroups of patients with septic shock and critical illnesses. Transcriptomic analysis can identify subclasses derived from differences in underlying pathophysiological processes that may provide the basis for new targeted therapies. The goal of this study was to elucidate pathophysiological pathways and identify pediatric septic shock subclasses based on whole blood RNA expression profiles.

Methods

The subjects were critically ill children with cardiopulmonary failure who were a part of a prospective randomized insulin titration trial to treat hyperglycemia. Genome-wide expression profiling was conducted using RNA-sequencing from whole blood samples obtained from 46 children with septic shock and 52 mechanically ventilated noninfected controls without shock. Patients with septic shock were allocated to subclasses based on hierarchical clustering of gene expression profiles, and we then compared clinical characteristics, plasma inflammatory markers, cell compositions using GEDIT, and immune repertoires using Imrep between the two subclasses.

Results

Patients with septic shock depicted alterations in innate and adaptive immune pathways. Among patients with septic shock, we identified two subtypes based on gene expression patterns. Compared with Subclass 2, Subclass 1 was characterized by upregulation of innate immunity pathways and downregulation of adaptive immunity pathways. Subclass 1 had significantly worse clinical outcomes despite the two classes having similar illness severity on initial clinical presentation. Subclass 1 had elevated levels of plasma inflammatory cytokines and endothelial injury biomarkers and demonstrated decreased percentages of CD4 T cells and B cells, and less diverse T-Cell receptor repertoires.

Conclusions

Two subclasses of pediatric septic shock patients were discovered through genome-wide expression profiling based on whole blood RNA sequencing with major biological and clinical differences.

Trial Registration

This is a secondary analysis of data generated as part of the observational CAF PINT ancillary of the HALF PINT study (NCT01565941). Registered 29 March 2012.

Classification of subtypes and identification of dysregulated genes in sepsis

Background

Sepsis is a clinical syndrome with high mortality. Subtype identification in sepsis is meaningful for improving the diagnosis and treatment of patients. The purpose of this research was to identify subtypes of sepsis using RNA-seq datasets and further explore key genes that were deregulated during the development of sepsis.

Methods

The datasets GSE95233 and GSE13904 were obtained from the Gene Expression Omnibus database. Differential analysis of the gene expression matrix was performed between sepsis patients and healthy controls. Intersection analysis of differentially expressed genes was applied to identify common differentially expressed genes for enrichment analysis and gene set variation analysis. Obvious differential pathways between sepsis patients and healthy controls were identified, as were developmental stages during sepsis. Then, key dysregulated genes were revealed by short time-series analysis and the least absolute shrinkage and selection operator model. In addition, the MCPcounter package was used to assess infiltrating immunocytes. Finally, the dysregulated genes identified were verified using 69 clinical samples.

Results

A total of 898 common differentially expressed genes were obtained, which were chiefly related to increased metabolic responses and decreased immune responses. The two differential pathways (angiogenesis and myc targets v2) were screened on the basis of gene set variation analysis scores. Four subgroups were identified according to median expression of angiogenesis and myc target v2 genes: normal, myc target v2, mixed-quiescent, and angiogenesis. The genes CHPT1, CPEB4, DNAJC3, MAFG, NARF, SNX3, S100A9, S100A12, and METTL9 were recognized as being progressively dysregulated in sepsis. Furthermore, most types of immune cells showed low infiltration in sepsis patients and had a significant correlation with the key genes. Importantly, all nine key genes were highly expressed in sepsis patients.

Conclusion

This study revealed novel insight into sepsis subtypes and identified nine dysregulated genes associated with immune status in the development of sepsis. This study provides potential molecular targets for the diagnosis and treatment of sepsis.

Research Hotspots and Trends of Deep Learning in Critical Care Medicine: A Bibliometric and Visualized Study

Background

Interest in the application of deep learning (DL) in critical care medicine (CCM) is growing rapidly. However, comprehensive bibliometric research that analyze and measure the global literature is still lacking.

Objective

The present study aimed to systematically evaluate the research hotspots and trends of DL in CCM worldwide based on the output of publications, cooperative relationships of research, citations, and the co-occurrence of keywords.

Methods

A total of 1708 articles in all were obtained from Web of Science. Bibliometric analysis was performed by Bibliometrix package in R software (4.2.2), Microsoft Excel 2019, VOSviewer (1.6.18), and CiteSpace (5.8.R3).

Results

The annual publications increased steeply in the past five years, accounting for 95.67% (1634/1708) of all the included literature. China and USA contributed to approximately 71.66% (1244/1708) of all publications. Seven of the top ten most productive organizations rank in the top 100 universities globally. Hot spots in research on the application of DL in CCM have focused on classifying disease phenotypes, predicting early signs of clinical deterioration, and forecasting disease progression, prognosis, and death. Convolutional neural networks, long and short-term memory networks, recurrent neural networks, transformer models, and attention mechanisms were all commonly used DL technologies.

Conclusion

Hot spots in research on the application of DL in CCM have focused on classifying disease phenotypes, predicting early signs of clinical deterioration, and forecasting disease progression, prognosis, and death. Extensive collaborative research to improve the maturity and robustness of the model remains necessary to make DL-based model applications sufficiently compelling for conventional CCM practice.

Sepsis Prediction by Using a Hybrid Metaheuristic Algorithm: A Novel Approach for Optimizing Deep Neural Networks

The early diagnosis of sepsis reduces the risk of the patient's death. Gradient-based algorithms are applied to the neural network models used in the estimation of sepsis in the literature. However, these algorithms become stuck at the local minimum in solution space. In recent years, swarm intelligence and an evolutionary approach have shown proper results. In this study, a novel hybrid metaheuristic algorithm was proposed for optimization with regard to the weights of the deep neural network and applied for the early diagnosis of sepsis. The proposed algorithm aims to reach the global minimum with a local search strategy capable of exploring and exploiting particles in Particle Swarm Optimization (PSO) and using the mental search operator of the Human Mental Search algorithm (HMS). The benchmark functions utilized to compare the performance of HMS, PSO, and HMS-PSO revealed that the proposed approach is more reliable, durable, and adjustable than other applied algorithms. HMS-PSO is integrated with a deep neural network (HMS-PSO-DNN). The study focused on predicting sepsis with HMS-PSO-DNN, utilizing a dataset of 640 patients aged 18 to 60. The HMS-PSO-DNN model gave a better mean squared error (MSE) result than other algorithms in terms of accuracy, robustness, and performance. We obtained the MSE value of 0.22 with 30 independent runs.

Machine Learning Models for the Identification of Prognostic and Predictive Cancer Biomarkers: A Systematic Review

The identification of biomarkers plays a crucial role in personalized medicine, both in the clinical and research settings. However, the contrast between predictive and prognostic biomarkers can be challenging due to the overlap between the two. A prognostic biomarker predicts the future outcome of cancer, regardless of treatment, and a predictive biomarker predicts the effectiveness of a therapeutic intervention. Misclassifying a prognostic biomarker as predictive (or vice versa) can have serious financial and personal consequences for patients. To address this issue, various statistical and machine learning approaches have been developed. The aim of this study is to present an in-depth analysis of recent advancements, trends, challenges, and future prospects in biomarker identification. A systematic search was conducted using PubMed to identify relevant studies published between 2017 and 2023. The selected studies were analyzed to better understand the concept of biomarker identification, evaluate machine learning methods, assess the level of research activity, and highlight the application of these methods in cancer research and treatment. Furthermore, existing obstacles and concerns are discussed to identify prospective research areas. We believe that this review will serve as a valuable resource for researchers, providing insights into the methods and approaches used in biomarker discovery and identifying future research opportunities.

Constructing metabolism-protein interaction relationship to identify glioma prognosis using deep learning

Glioma is heterogeneous disease that requires classification into subtypes with similar clinical phenotypes, prognosis or treatment responses. Metabolic-protein interaction (MPI) can provide meaningful insights into cancer heterogeneity. Moreover, the potential of lipids and lactate for identifying prognostic subtypes of glioma remains relatively unexplored. Therefore, we proposed a method to construct an MPI relationship matrix (MPIRM) based on a triple-layer network (Tri-MPN) combined with mRNA expression, and processed the MPIRM by deep learning to identify glioma prognostic subtypes. These Subtypes with significant differences in prognosis were detected in glioma (p-value < 2e-16, 95% CI). These subtypes had a strong correlation in immune infiltration, mutational signatures and pathway signatures. This study demonstrated the effectiveness of node interaction from MPI networks in understanding the heterogeneity of glioma prognosis.

Identification of Key MicroRNAs and Genes between Colorectal Adenoma and Colorectal Cancer via Deep Learning on GEO Databases and Bioinformatics

Background

Deep learning techniques are gaining momentum in medical research. Colorectal adenoma (CRA) is a precancerous lesion that may develop into colorectal cancer (CRC) and its etiology and pathogenesis are unclear. This study aims to identify transcriptome differences between CRA and CRC via deep learning on Gene Expression Omnibus (GEO) databases and bioinformatics in the Chinese population.

Methods

In this study, three microarray datasets from the GEO database were used to identify the differentially expressed genes (DEGs) and differentially expressed miRNAs (DEMs) in CRA and CRC. The FunRich software was performed to predict the targeted mRNAs of DEMs. The targeted mRNAs were overlapped with DEGs to determine the key DEGs. Molecular mechanisms of CRA and CRC were evaluated using enrichment analysis. Cytoscape was used to construct protein-protein interaction (PPI) and miRNA-mRNA regulatory networks. We analyzed the expression of key DEMs and DEGs, their prognosis, and correlation with immune infiltration based on the Kaplan-Meier plotter, UALCAN, and TIMER databases.

Results

A total of 38 DEGs are obtained after the intersection, including 11 upregulated genes and 27 downregulated genes. The DEGs were involved in the pathways, including epithelial-to-mesenchymal transition, sphingolipid metabolism, and intrinsic pathway for apoptosis. The expression of has-miR-34c (P = 0.036), hsa-miR-320a (P = 0.045), and has-miR-338 (P = 0.0063) was correlated with the prognosis of CRC patients. The expression levels of BCL2, PPM1L, ARHGAP44, and PRKACB in CRC tissues were significantly lower than normal tissues (P < 0.001), while the expression levels of TPD52L2 and WNK4 in CRC tissues were significantly higher than normal tissues (P < 0.01). These key genes are significantly associated with the immune infiltration of CRC.

Conclusion

This preliminary study will help identify patients with CRA and early CRC and establish prevention and monitoring strategies to reduce the incidence of CRC.

Research frontiers and trends in the application of artificial intelligence to sepsis: A bibliometric analysis

Background

With the increasing interest of academics in the application of artificial intelligence to sepsis, thousands of papers on this field had been published in the past few decades. It is difficult for researchers to understand the themes and latest research frontiers in this field from a multi-dimensional perspective. Consequently, the purpose of this study is to analyze the relevant literature in the application of artificial intelligence to sepsis through bibliometrics software, so as to better understand the development status, study the core hotspots and future development trends of this field.

Methods

We collected relevant publications in the application of artificial intelligence to sepsis from the Web of Science Core Collection in 2000 to 2021. The type of publication was limited to articles and reviews, and language was limited to English. Research cooperation network, journals, cited references, keywords in this field were visually analyzed by using CiteSpace, VOSviewer, and COOC software.

Results

A total of 8,481 publications in the application of artificial intelligence to sepsis between 2000 and 2021 were included, involving 8,132 articles and 349 reviews. Over the past 22 years, the annual number of publications had gradually increased exponentially. The USA was the most productive country, followed by China. Harvard University, Schuetz, Philipp, and Intensive Care Medicine were the most productive institution, author, and journal, respectively. Vincent, Jl and Critical Care Medicine were the most cited author and cited journal, respectively. Several conclusions can be drawn from the analysis of the cited references, including the following: screening and identification of sepsis biomarkers, treatment and related complications of sepsis, and precise treatment of sepsis. Moreover, there were a spike in searches relating to machine learning, antibiotic resistance and accuracy based on burst detection analysis.

Conclusion

This study conducted a comprehensive and objective analysis of the publications on the application of artificial intelligence in sepsis. It can be predicted that precise treatment of sepsis through machine learning technology is still research hotspot in this field.

Identification of two robust subclasses of sepsis with both prognostic and therapeutic values based on machine learning analysis

Background

Sepsis is a heterogeneous syndrome with high morbidity and mortality. Optimal and effective classifications are in urgent need and to be developed.

Methods and results

A total of 1,936 patients (sepsis samples, n=1,692; normal samples, n=244) in 7 discovery datasets were included to conduct weighted gene co-expression network analysis (WGCNA) to filter out candidate genes related to sepsis. Then, two subtypes of sepsis were classified in the training sepsis set (n=1,692), the Adaptive and Inflammatory, using K-means clustering analysis on 90 sepsis-related features. We validated these subtypes using 617 samples in 5 independent datasets and the merged 5 sets. Cibersort method revealed the Adaptive subtype was related to high infiltration levels of T cells and natural killer (NK) cells and a better clinical outcome. Immune features were validated by single-cell RNA sequencing (scRNA-seq) analysis. The Inflammatory subtype was associated with high infiltration of macrophages and a disadvantageous prognosis. Based on functional analysis, upregulation of the Toll-like receptor signaling pathway was obtained in Inflammatory subtype and NK cell-mediated cytotoxicity and T cell receptor signaling pathway were upregulated in Adaptive group. To quantify the cluster findings, a scoring system, called, risk score, was established using four datasets (n=980) in the discovery cohorts based on least absolute shrinkage and selection operator (LASSO) and logistic regression and validated in external sets (n=760). Multivariate logistic regression analysis revealed the risk score was an independent predictor of outcomes of sepsis patients (OR [odds ratio], 2.752, 95% confidence interval [CI], 2.234-3.389, P<0.001), when adjusted by age and gender. In addition, the validation sets confirmed the performance (OR, 1.638, 95% CI, 1.309-2.048, P<0.001). Finally, nomograms demonstrated great discriminatory potential than that of risk score, age and gender (training set: AUC=0.682, 95% CI, 0.643-0.719; validation set: AUC=0.624, 95% CI, 0.576-0.664). Decision curve analysis (DCA) demonstrated that the nomograms were clinically useful and had better discriminative performance to recognize patients at high risk than the age, gender and risk score, respectively.

Conclusions

In-depth analysis of a comprehensive landscape of the transcriptome characteristics of sepsis might contribute to personalized treatments and prediction of clinical outcomes.

Data science in the intensive care unit

In this editorial, we comment on the current development and deployment of data science in intensive care units (ICUs). Data in ICUs can be classified into qualitative and quantitative data with different technologies needed to translate and interpret them. Data science, in the form of artificial intelligence (AI), should find the right interaction between physicians, data and algorithm. For individual patients and physicians, sepsis and mechanical ventilation have been two important aspects where AI has been extensively studied. However, major risks of bias, lack of generalizability and poor clinical values remain. AI deployment in the ICUs should be emphasized more to facilitate AI development. For ICU management, AI has a huge potential in transforming resource allocation. The coronavirus disease 2019 pandemic has given opportunities to establish such systems which should be investigated further. Ethical concerns must be addressed when designing such AI.

Integrated Analysis of Gene Co-Expression Network and Prediction Model Indicates Immune-Related Roles of the Identified Biomarkers in Sepsis and Sepsis-Induced Acute Respiratory Distress Syndrome

Sepsis is a series of clinical syndromes caused by immunological response to severe infection. As the most important and common complication of sepsis, acute respiratory distress syndrome (ARDS) is associated with poor outcomes and high medical expenses. However, well-described studies of analysis-based researches, especially related bioinformatics analysis on revealing specific targets and underlying molecular mechanisms of sepsis and sepsis-induced ARDS (sepsis/se-ARDS), still remain limited and delayed despite the era of data-driven medicine. In this report, weight gene co-expression network based on data from a public database was constructed to identify the key modules and screen the hub genes. Functional annotation by enrichment analysis of the modular genes also demonstrated the key biological processes and signaling pathway; among which, extensive immune-involved enrichment was remarkably associated with sepsis/se-ARDS. Based on the differential expression analysis, least absolute shrink and selection operator, and multivariable logistic regression analysis of the screened hub genes, SIGLEC9, TSPO, CKS1B and PTTG3P were identified as the candidate biomarkers for the further analysis. Accordingly, a four-gene-based model for diagnostic prediction assessment was established and then developed by sepsis/se-ARDS risk nomogram, whose efficiency was verified by calibration curves and decision curve analyses. In addition, various machine learning algorithms were also applied to develop extra models based on the four genes. Receiver operating characteristic curve analysis proved the great diagnostic and predictive performance of these models, and the multivariable logistic regression of the model was still found to be the best as further verified again by the internal test, training, and external validation cohorts. During the development of sepsis/se-ARDS, the expressions of the identified biomarkers including SIGLEC9, TSPO, CKS1B and PTTG3P were all regulated remarkably and generally exhibited notable correlations with the stages of sepsis/se-ARDS. Moreover, the expression levels of these four genes were substantially correlated during sepsis/se-ARDS. Analysis of immune infiltration showed that multiple immune cells, neutrophils and monocytes in particular, might be closely involved in the process of sepsis/se-ARDS. Besides, SIGLEC9, TSPO, CKS1B and PTTG3P were considerably correlated with the infiltration of various immune cells including neutrophils and monocytes during sepsis/se-ARDS. The discovery of relevant gene co-expression network and immune signatures might provide novel insights into the pathophysiology of sepsis/se-ARDS.

The landscape of isoform switches in sepsis: a multicenter cohort study

Sepsis is caused by an uncontrolled inflammatory response, whose underlying mechanisms are not fully understood. It is well known that the majority of human genes can be expressed as alternative isoforms. While isoform switching is implicated in many diseases and is particularly prominent in cancer, it has never been reported in the context of sepsis. Patients presented to the emergency department of three tertiary care hospitals from January 2020 to December 2020 were enrolled. Clinical variables and genome-wide transcriptome of peripheral blood mononuclear cells (PBMC) were obtained. Isoform switching analysis were performed to identify significant isoform switches and relevant biological consequences. A total of 48 subjects with sepsis, involving 42 survivors and 6 non-survivors, admitted to the emergency department of three tertiary care hospitals were enrolled in this study. PBMCs were extracted for RNA sequencing (RNA-seq). Patients (n = 4) with mild stroke or acute coronary syndrome without infection were enrolled in this study as controls. The most frequent functional changes resulting from isoform switching were changes affecting the open reading frame, protein domains and intron retention. Many genes without differences in gene expression showed significant isoform switching. Many genes with significant isoform switches ([Formula: see text]> 0.1) were associated with higher mortality risk, including PIGS, CASP3, LITAF, HBB and RUVBL2. The study for the first time described the landscape of isoform switching in sepsis, including differentially expressed isoform fractions between patients with and without sepsis and survivors and nonsurvivors. The biological consequences of isoform switching, including protein domain loss, signal peptide gain, and intron retention, were identified.

Integrated Single Cell and Bulk RNA-Seq Analysis Revealed Immunomodulatory Effects of Ulinastatin in Sepsis: A Multicenter Cohort Study

Sepsis is a leading cause of morbidity and mortality in the intensive care unit, which is caused by unregulated inflammatory response leading to organ injuries. Ulinastatin (UTI), an immunomodulatory agent, is widely used in clinical practice and is associated with improved outcomes in sepsis. But its underlying mechanisms are largely unknown. Our study integrated bulk and single cell RNA-seq data to systematically explore the potential mechanisms of the effects of UTI in sepsis. After adjusting for potential confounders in the negative binomial regression model, there were more genes being downregulated than being upregulated in the UTI group. These down-regulated genes were enriched in the neutrophil involved immunity such as neutrophil activation and degranulation, indicating the immunomodulatory effects of UTI is mediated via regulation of neutrophil activity. By deconvoluting the bulk RNA-seq samples to obtain fractions of cell types, the Myeloid-derived suppressor cells (MDSC) were significantly expanded in the UTI treated samples. Further cell-cell communication analysis revealed some signaling pathways such as ANEEXIN, GRN and RESISTIN that might be involved in the immunomodulatory effects of UTI. The study provides a comprehensive reference map of transcriptional states of sepsis treated with UTI, as well as a general framework for studying UTI-related mechanisms.

A novel prognostic model for predicting the mortality risk of patients with sepsis-related acute respiratory failure: a cohort study using the MIMIC-IV database

OBJECTIVES

Acute respiratory failure increases short-term mortality in sepsis patients. Hence, in this study, we aimed to develop a novel model for predicting the risk of hospital mortality in sepsis patients with acute respiratory failure.

METHODS

From the Medical Information Mart for Intensive Care (MIMIC)-IV database, we developed a matched cohort of adult sepsis patients with acute respiratory failure. After applying a multivariate COX regression analysis, we developed a nomogram based on the identified risk factors of mortality. Further, we evaluated the ability of the nomogram in predicting individual hospital death by the area under a receiver operating characteristic (ROC) curve.

RESULTS

A total of 663 sepsis patients with acute respiratory failure were included in this study. Systolic blood pressure, neutrophil percentage, white blood cells count, mechanical ventilation, partial pressure of oxygen < 60 mmHg, abdominal cavity infection, Klebsiella pneumoniae and Acinetobacter baumannii infection, and immunosuppressive diseases were the independent risk factors of mortality in sepsis patients with acute respiratory failure. The area under the ROC curve of the nomogram was 0.880 (95% CI: 0.851-0.908), which provided significantly higher discrimination compared to that of the simplified acute physiology score II [0.656 (95% CI: 0.612-0.701)].

CONCLUSION

The model shows a good performance in predicting the mortality risk of patients with sepsis-related acute respiratory failure. Hence, this model can be used to evaluate the short-term prognosis of critically ill patients with sepsis and acute respiratory failure.

Methods for Phenotyping Adult Patients in Sepsis and Septic Shock: A Scoping Review

Despite its heterogeneous phenotypes, sepsis or life-threatening dysfunction in response to infection is often treated empirically. Identifying patient subgroups with unique pathophysiology and treatment response is critical to the advancement of sepsis care. However, phenotyping methods and results are as heterogeneous as the disease itself. This scoping review evaluates the prognostic capabilities and treatment implications of adult sepsis and septic shock phenotyping methods.

DATA SOURCES

Medline and Embase.

STUDY SELECTION

We included clinical studies that described sepsis or septic shock and used any clustering method to identify sepsis phenotypes. We excluded conference abstracts, literature reviews, comments, letters to the editor, and in vitro studies. We assessed study quality using a validated risk of bias tool for observational cohort and cross-sectional studies.

DATA EXTRACTION

We extracted population, methodology, validation, and phenotyping characteristics from 17 studies.

DATA SYNTHESIS

Sepsis phenotyping methods most frequently grouped patients based on the degree of inflammatory response and coagulopathy using clinical, nongenomic variables. Five articles clustered patients based on genomic or transcriptomic data. Seven articles generated patient subgroups with differential response to sepsis treatments. Cluster clinical characteristics and their associations with mortality and treatment response were heterogeneous across studies, and validity was evaluated in nine of 17 articles, hindering pooled analysis of results and derivation of universal truths regarding sepsis phenotypes, their prognostic capabilities, and their associations with treatment response.

CONCLUSIONS

Sepsis phenotyping methods can identify high-risk patients and those with high probability of responding well to targeted treatments. Research quality was fair, but achieving generalizability and clinical impact of sepsis phenotyping will require external validation and direct comparison with alternative approaches.

Identification of Hub Genes With Differential Correlations in Sepsis

As a multifaceted syndrome, sepsis leads to high risk of death worldwide. It is difficult to be intervened due to insufficient biomarkers and potential targets. The reason is that regulatory mechanisms during sepsis are poorly understood. In this study, expression profiles of sepsis from GSE134347 were integrated to construct gene interaction network through weighted gene co-expression network analysis (WGCNA). R package DiffCorr was utilized to evaluate differential correlations and identify significant differences between sepsis and healthy tissues. As a result, twenty-six modules were detected in the network, among which blue and darkred modules exhibited the most significant associations with sepsis. Finally, we identified some novel genes with opposite correlations including ZNF366, ZMYND11, SVIP and UBE2H. Further biological analysis revealed their promising roles in sepsis management. Hence, differential correlations-based algorithm was firstly established for the discovery of appealing regulators in sepsis.

Gene Expression Scoring of Immune Activity Levels for Precision Use of Hydrocortisone in Vasodilatory Shock

PURPOSE

Among patients with vasodilatory shock, gene expression scores may identify different immune states. We aimed to test whether such scores are robust in identifying patients' immune state and predicting response to hydrocortisone treatment in vasodilatory shock.

MATERIALS AND METHODS

We selected genes to generate continuous scores to define previously established subclasses of sepsis. We used these scores to identify a patient's immune state. We evaluated the potential for these states to assess the differential effect of hydrocortisone in two randomized clinical trials of hydrocortisone versus placebo in vasodilatory shock.

RESULTS

We initially identified genes associated with immune-adaptive, immune-innate, immune-coagulant functions. From these genes, 15 were most relevant to generate expression scores related to each of the functions. These scores were used to identify patients as immune-adaptive prevalent (IA-P) and immune-innate prevalent (IN-P). In IA-P patients, hydrocortisone therapy increased 28-day mortality in both trials (43.3% vs 14.7%, P = 0.028) and (57.1% vs 0.0%, P = 0.99). In IN-P patients, this effect was numerically reversed.

CONCLUSIONS

Gene expression scores identified the immune state of vasodilatory shock patients, one of which (IA-P) identified those who may be harmed by hydrocortisone. Gene expression scores may help advance the field of personalized medicine.

Hypermagnesaemia, but Not Hypomagnesaemia, Is a Predictor of Inpatient Mortality in Critically Ill Children with Sepsis

Objective

The effect of serum magnesium on the prognosis of children with sepsis in the pediatric intensive care unit (PICU) is unclear. This study was designed to assess the risk of inpatient mortality for children with sepsis in the PICU based on serum magnesium levels at admission.

Methods

We collected patients' clinical information from the Pediatric Intensive Care database and then performed locally weighted scatterplot smoothing (LOWESS) analysis, Kaplan–Meier analysis, and multivariate logistic regression to determine the relationship between admission serum magnesium and inpatient mortality in children with sepsis.

Results

A total of 974 critically ill children with sepsis were included, with 246 patients in the hypomagnesemia group, 666 in the normal group, and 62 in the hypermagnesemia group. The chi-square test suggested that the hypermagnesemia group had higher in-hospital mortality than the normal group (14.5% vs. 2.4%, P < 0.001). Kaplan–Meier curves revealed that the 30-day overall survival rate was lower in the hypermagnesaemia group than in the normal group (P < 0.001). The multivariate logistic regression model revealed that hypermagnesaemia was a risk factor related to inpatient mortality (odds ratio 4.22, 95% CI 1.55-11.50), while hypomagnesaemia was not a significant factor for inpatient mortality (odds ratio 0.78, 95% CI 0.26-2.32).

Conclusion

Hypermagnesaemia, but not hypomagnesaemia, is a predictor of inpatient mortality in critically ill children with sepsis.

Cluster analysis integrating age and body temperature for mortality in patients with sepsis: a multicenter retrospective study

It is not clear whether mortality is associated with body temperature (BT) in older sepsis patients. This study aimed to evaluate the mortality rates in sepsis patients according to age and BT and identify the risk factors for mortality. We investigated the clusters using a machine learning method based on a combination of age and BT, and identified the mortality rates according to these clusters. This retrospective multicenter study was conducted at five hospitals in Korea. Data of sepsis patients aged ≥ 18 years who were admitted to the intensive care unit between January 1, 2011 and April 30, 2021 were collected. BT was divided into three groups (hypothermia < 36 °C, normothermia 36‒38 °C, and hyperthermia > 38 °C), and age groups were divided using a 75-year age threshold. Kaplan‒Meier analysis was performed to assess the cumulative mortality over 90 days. A K-means clustering algorithm using age and BT was used to characterize phenotypes. During the study period, 15,574 sepsis patients were enrolled. Overall, 90-day mortality was 20.5%. Kaplan‒Meier survival analyses demonstrated that 90-day mortality rates were 27.4%, 19.6%, and 11.9% in the hypothermia, normothermia, and hyperthermia groups, respectively, in those ≥ 75 years old (Log-rank p < 0.001). Cluster analysis demonstrated three groups: Cluster A (relatively older age and lower BT), Cluster B (relatively younger age and wide range of BT), and Cluster C (relatively higher BT than Cluster A). Kaplan‒Meier curve analysis showed that the 90-day mortality rates of Cluster A was significantly higher than those of Clusters B and C (24.2%, 17.1%, and 17.0%, respectively; Log-rank p < 0.001). The 90-day mortality rate correlated inversely with BT groups among sepsis patients in either age group (< 75 and ≥ 75 years). Clustering analysis revealed that the mortality rate was higher in the cluster of patients with relatively older age and lower BT.

Added value of systemic inflammation markers in predicting pulmonary infection in stroke patients: A retrospective study by machine learning analysis

Exploring candidate markers to predict the clinical outcomes of pulmonary infection in stroke patients have a high unmet need. This study aimed to develop machine learning (ML)-based predictive models for pulmonary infection.Between January 2008 and April 2021, a retrospective analysis of 1397 stroke patients who had CT angiography from skull to diaphragm (including CT of the chest) within 24 hours of symptom onset. A total of 21 variables were included, and the prediction model of pulmonary infection was established by multiple ML-based algorithms. Risk factors for pulmonary infection were determined by the feature selection method. Area under the curve (AUC) and decision curve analysis were used to determine the model with the best resolution and to assess the net clinical benefits associated with the use of predictive models, respectively.A total of 889 cases were included in this study as a training group, while 508 cases were as a validation group. The feature selection indicated the top 6 predictors were procalcitonin, C-reactive protein, soluble interleukin-2 receptor, consciousness disorder, dysphagia, and invasive procedure. The AUCs of the 5 models ranged from 0.78 to 0.87 in the training cohort. When the ML-based models were applied to the validation set, the results also remained reconcilable, and the AUC was between 0.891 and 0.804. The decision curve analysis also showed performed better than positive line and negative line, indicating the favorable predictive performance and clinical values of the models.By incorporating clinical characteristics and systemic inflammation markers, it is feasible to develop ML-based models for the presence and consequences of signs of pulmonary infection in stroke patients, and the use of the model may be greatly beneficial to clinicians in risk stratification and management decisions.

Functional Role of AKNA: A Scoping Review

Human akna encodes an AT-hook transcription factor whose expression participates in various cellular processes. We conducted a scoping review on the literature regarding the functional role of AKNA according to the evidence found in human and in vivo and in vitro models, stringently following the "PRISMA-ScR" statement recommendations.

METHODS

We undertook an independent PubMed literature search using the following search terms, AKNA OR AKNA ADJ gene OR AKNA protein, human OR AKNA ADJ functions. Observational and experimental articles were considered. The selected studies were categorized using a pre-determined data extraction form. A narrative summary of the evidence was produced.

RESULTS

AKNA modulates the expression of CD40 and CD40L genes in immune system cells. It is a negative regulator of inflammatory processes as evidenced by knockout mouse models and observational studies for several autoimmune and inflammatory diseases. Furthermore, AKNA contributes to the de-regulation of the immune system in cancer, and it has been proposed as a susceptibility genetic factor and biomarker in CC, GC, and HNSCC. Finally, AKNA regulates neurogenesis by destabilizing the microtubules dynamics.

CONCLUSION

Our results provide evidence for the role of AKNA in various cellular processes, including immune response, inflammation, development, cancer, autoimmunity, and neurogenesis.

Individualized Mechanical power-based ventilation strategy for acute respiratory failure formalized by finite mixture modeling and dynamic treatment regimen

BACKGROUND

Mechanical ventilation (MV) is the key to the successful treatment of acute respiratory failure (ARF) in the intensive care unit (ICU). The study aims to formalize the concept of individualized MV strategy with finite mixture modeling (FMM) and dynamic treatment regime (DTR).

METHODS

ARF patients requiring MV for over 48 h from 2008 to 2019 were included. FMM was conducted to identify classes of ARF. Static and dynamic mechanical power (MP_static and MP_dynamic) and relevant clinical variables were calculated/collected from hours 0 to 48 at an interval of 8 h. Δ M P was calculated as the difference between actual and optimal MP.

FINDINGS

A total of 8768 patients were included for analysis with a mortality rate of 27%. FFM identified three classes of ARF, namely, the class 1 (baseline), class 2 (critical) and class 3 (refractory respiratory failure). The effect size of MP_static on mortality is the smallest in class 1 (HR for every 5 Joules/min increase: 1.29; 95% CI: 1.15 to 1.45; p < 0.001) and the largest in class 3 (HR for every 5 Joules/min increase: 1.83; 95% CI: 1.52 to 2.20; p < 0.001).

INTERPRETATION

MP has differing therapeutic effects for subtypes of ARF. Optimal MP estimated by DTR model may help to improve survival outcome.

FUNDING

The study was funded by Health Science and Technology Plan of Zhejiang Province (2021KY745), Key Research & Development project of Zhejiang Province (2021C03071) and Yilu "Gexin" - Fluid Therapy Research Fund Project (YLGX-ZZ-2,020,005).

Deep learning predicts gene expression as an intermediate data modality to identify susceptibility patterns in Mycobacterium tuberculosis infected Diversity Outbred mice

BACKGROUND

Machine learning sustains successful application to many diagnostic and prognostic problems in computational histopathology. Yet, few efforts have been made to model gene expression from histopathology. This study proposes a methodology which predicts selected gene expression values (microarray) from haematoxylin and eosin whole-slide images as an intermediate data modality to identify fulminant-like pulmonary tuberculosis ('supersusceptible') in an experimentally infected cohort of Diversity Outbred mice (n=77).

METHODS

Gradient-boosted trees were utilized as a novel feature selector to identify gene transcripts predictive of fulminant-like pulmonary tuberculosis. A novel attention-based multiple instance learning model for regression was used to predict selected genes' expression from whole-slide images. Gene expression predictions were shown to be sufficiently replicated to identify supersusceptible mice using gradient-boosted trees trained on ground truth gene expression data.

FINDINGS

The model was accurate, showing high positive correlations with ground truth gene expression on both cross-validation (n = 77, 0.63 ≤ ρ ≤ 0.84) and external testing sets (n = 33, 0.65 ≤ ρ ≤ 0.84). The sensitivity and specificity for gene expression predictions to identify supersusceptible mice (n=77) were 0.88 and 0.95, respectively, and for an external set of mice (n=33) 0.88 and 0.93, respectively.

IMPLICATIONS

Our methodology maps histopathology to gene expression with sufficient accuracy to predict a clinical outcome. The proposed methodology exemplifies a computational template for gene expression panels, in which relatively inexpensive and widely available tissue histopathology may be mapped to specific genes' expression to serve as a diagnostic or prognostic tool.

FUNDING

National Institutes of Health and American Lung Association.

Identification of COVID-19 subtypes based on immunogenomic profiling

Although previous studies have shown that the host immune response is crucial in determining clinical outcomes in COVID-19 patients, the association between host immune signatures and COVID-19 patient outcomes remains unclear. Based on the enrichment levels of 11 immune signatures (eight immune-inciting and three immune-inhibiting signatures) in leukocytes of 100 COVID-19 patients, we identified three COVID-19 subtypes: Im-C1, Im-C2, and Im-C3, by clustering analysis. Im-C1 had the lowest immune-inciting signatures and high immune-inhibiting signatures. Im-C2 had medium immune-inciting signatures and high immune-inhibiting signatures. Im-C3 had the highest immune-inciting signatures while the lowest immune-inhibiting signatures. Im-C3 and Im-C1 displayed the best and worst clinical outcomes, respectively, suggesting that antiviral immune responses alleviated the severity of COVID-19 patients. We further demonstrated that the adaptive immune response had a stronger impact on COVID-19 outcomes than the innate immune response. The patients in Im-C3 were younger than those in Im-C1, indicating that younger persons have stronger antiviral immune responses than older persons. Nevertheless, we did not observe a significant association between sex and immune responses in COVID-19 patients. In addition, we found that the type II IFN response signature was an adverse prognostic factor for COVID-19. Our identification of COVID-19 immune subtypes has potential clinical implications for the management of COVID-19 patients.