The Role of Transcriptomics in Redefining Critical Illness

Machine learning-driven identification of the gene-expression signature associated with a persistent multiple organ dysfunction trajectory in critical illness

BACKGROUND

Multiple organ dysfunction syndrome (MODS) disproportionately drives morbidity and mortality among critically ill patients. However, we lack a comprehensive understanding of its pathobiology. Identification of genes associated with a persistent MODS trajectory may shed light on underlying biology and allow for accurate prediction of those at-risk.

METHODS

Secondary analyses of publicly available gene-expression datasets. Supervised machine learning (ML) was used to identify a parsimonious set of genes associated with a persistent MODS trajectory in a training set of pediatric septic shock. We optimized model parameters and tested risk-prediction capabilities in independent validation and test datasets, respectively. We compared model performance relative to an established gene-set predictive of sepsis mortality.

FINDINGS

Patients with a persistent MODS trajectory had 568 differentially expressed genes and characterized by a dysregulated innate immune response. Supervised ML identified 111 genes associated with the outcome of interest on repeated cross-validation, with an AUROC of 0.87 (95% CI: 0.85-0.88) in the training set. The optimized model, limited to 20 genes, achieved AUROCs ranging from 0.74 to 0.79 in the validation and test sets to predict those with persistent MODS, regardless of host age and cause of organ dysfunction. Our classifier demonstrated reproducibility in identifying those with persistent MODS in comparison with a published gene-set predictive of sepsis mortality.

INTERPRETATION

We demonstrate the utility of supervised ML driven identification of the genes associated with persistent MODS. Pending validation in enriched cohorts with a high burden of organ dysfunction, such an approach may inform targeted delivery of interventions among at-risk patients.

FUNDING

H.R.W.'s NIHR35GM126943 award supported the work detailed in this manuscript. Upon his death, the award was transferred to M.N.A. M.R.A., N.S.P, and R.K were supported by NIHR21GM151703. R.K. was supported by R01GM139967.

A MACHINE LEARNING MODEL DERIVED FROM ANALYSIS OF TIME-COURSE GENE-EXPRESSION DATASETS REVEALS TEMPORALLY STABLE GENE MARKERS PREDICTIVE OF SEPSIS MORTALITY

ABSTRACT

Sepsis is associated with significant mortality and morbidity among critically ill patients admitted to intensive care units and represents a major health challenge globally. Given the significant clinical and biological heterogeneity among patients and the dynamic nature of the host immune response, identifying those at high risk of poor outcomes remains a critical challenge. Here, we performed secondary analysis of publicly available time-series gene-expression datasets from peripheral blood of patients admitted to the intensive care unit to elucidate temporally stable gene-expression markers between sepsis survivors and nonsurvivors. Using a limited set of genes that were determined to be temporally stable, we derived a dynamical model using a Support Vector Machine classifier to accurately predict the mortality of sepsis patients. Our model had robust performance in a test dataset, where patients' transcriptome was sampled at alternate time points, with an area under the curve of 0.89 (95% CI, 0.82-0.96) upon 5-fold cross-validation. We also identified 7 potential biomarkers of sepsis mortality (STAT5A, CX3CR1, LCP1, SNRPG, RPS27L, LSM5, SHCBP1) that require future validation. Pending prospective testing, our model may be used to identify sepsis patients with high risk of mortality accounting for the dynamic nature of the disease and with potential therapeutic implications.

Biomarkers to guide immunomodulatory treatment: where do we stand?

INTRODUCTION

This review summarizes current progress in the development of biomarkers to guide immunotherapy in oncology, rheumatology, and critical illness.

AREAS COVERED

An extensive literature search was performed about biomarkers classifying patients' immune responses to guide immunotherapy in oncology, rheumatology, and critical illness. Surface markers, such as programmed death-ligand 1 (PD-L1), genetic biomarkers, such as tumor mutation load, and circulating tumor DNA are biomarkers associated with the effectiveness of immunotherapy in oncology. Genomics, metabolomics, and proteomics play a crucial role in selecting the most suitable therapeutic options for rheumatologic patients. Phenotypes and endotypes are a promising approach to detect critically ill patients with hyper- or hypo-inflammation. Sepsis trials using biomarkers such as ferritin, lymphopenia, HLA-DR expression on monocytes and PD-L1 to guide immunotherapy have been already conducted or are currently ongoing. Immunotherapy in COVID-19 pneumonia, guided by C-reactive protein and soluble urokinase plasminogen activator receptor (suPAR) has improved patient outcomes globally. More research is needed into immunotherapy in other critical conditions.

EXPERT OPINION

Targeted immunotherapy has improved outcomes in oncology and rheumatology, paving the way for precision medicine in the critically ill. Transcriptomics will play a crucial role in detecting the most suitable candidates for immunomodulation.

Multi-Omics Endotypes in ICU Sepsis-Induced Immunosuppression

It is evident that the admission of some patients with sepsis and septic shock to hospitals is occurring late in their illness, which has contributed to the increase in poor outcomes and high fatalities worldwide across age groups. The current diagnostic and monitoring procedure relies on an inaccurate and often delayed identification by the clinician, who then decides the treatment upon interaction with the patient. Initiation of sepsis is accompanied by immune system paralysis following "cytokine storm". The unique immunological response of each patient is important to define in terms of subtyping for therapy. The immune system becomes activated in sepsis to produce interleukins, and endothelial cells express higher levels of adhesion molecules. The proportions of circulating immune cells change, reducing regulatory cells and increasing memory cells and killer cells, having long-term effects on the phenotype of CD8 T cells, HLA-DR, and dysregulation of microRNA. The current narrative review seeks to highlight the potential application of multi-omics data integration and immunological profiling at the single-cell level to define endotypes in sepsis and septic shock. The review will consider the parallels and immunoregulatory axis between cancer and immunosuppression, sepsis-induced cardiomyopathy, and endothelial damage. Second, the added value of transcriptomic-driven endotypes will be assessed through inferring regulatory interactions in recent clinical trials and studies reporting gene modular features that inform continuous metrics measuring clinical response in ICU, which can support the use of immunomodulating agents.