Comprehensive characterization of cytokines in patients under extracorporeal membrane oxygenation: Evidence from integrated bulk and single-cell RNA sequencing data using multiple machine learning approaches.

Abstract

Background: ECMO (extracorporeal membrane oxygenation) is an effective technique for providing short-term mechanical support to the heart, lungs, or both. During ECMO treatment, the inflammatory response, particularly involving cytokines, plays a crucial role in pathophysiology. However, the potential effects of cytokines on patients receiving ECMO are not comprehensively understood.

Methods: We acquired three ECMO support datasets, namely two bulk and one single-cell RNA sequencing (RNA-seq), from the GEO (Gene Expression Omnibus) combined with hospital cohorts to investigate the expression pattern and potential biological processes of cytokine-related genes (CRGs) in patients under ECMO. Subsequently, machine learning approaches, including support vector machine (SVM), random forest (RF), modified Lasso penalized regression, extreme gradient boosting (XGBoost), and artificial neural network (ANN), were applied to identify hub CRGs, thus developing a prediction model called CRG classifier. The predictive and prognostic performance of the model was comprehensively evaluated in GEO and hospital cohorts. Finally, we mechanistically analyzed the relationship between hub cytokines, immune cells, and pivotal molecular pathways.

Results: Analyzing bulk and single-cell RNA-seq data revealed that most CRGs were significantly differentially expressed, the enrichment scores of cytokine and cytokine cytokine receptor (CCR) interaction were significantly higher during ECMO. Based on multiple machine learning algorithms, nine key CRGs (CCL2, CCL4, IFNG, IL1R2, IL20RB, IL31RA, IL4, IL7, and IL7R) were used to develop the CRG classifier. The CRG classifier exhibited excellent prognostic values (AUC > 0.85), serving as an independent risk factor. It performed better in predicting mortality and yielded a larger net benefit than other clinical features in GEO and hospital cohorts. Additionally, IL1R2, CCL4, and IL7R were predominantly expressed in monocytes, NK cells, and T cells, respectively. Their expression was significantly positively correlated with the relative abundance of corresponding immune cells. Gene set variation analysis (GSVA) revealed that parainflammation, complement and coagulation cascades, and IL6/JAK/STAT3 signaling were significantly enriched in the subgroup that died after receiving ECMO. Spearman correlation analyses and Mantel tests revealed that the expression of hub cytokines (IL1R2, CCL4, and IL7R) and pivotal molecular pathways scores (complement and coagulation cascades, IL6/JAK/STAT3 signaling, and parainflammation) were closely related.

Conclusion: A predictive model (CRG classifier) comprising nine CRGs based on multiple machine learning algorithms was constructed, potentially assisting clinicians in guiding individualized ECMO treatment. Additionally, elucidating the underlying mechanistic pathways of cytokines during ECMO will provide new insights into its treatment.