Machine learning predicts acute respiratory failure in pancreatitis patients: A retrospective study.

PURPOSE: The purpose of the research is to design an algorithm to predict the occurrence of acute respiratory failure (ARF) in patients with acute pancreatitis (AP). METHODS: We collected data on patients with AP in the Medical Information Mart for Intensive Care IV database. The enrolled observations were randomly divided into a 70 % training cohort and a 30 % validation cohort, and the observations in the training cohort were divided into ARF and non-ARF groups. Feature engineering was conducted using random forest (RF) and least absolute shrinkage and selection operator (LASSO) methods in the training cohort. The model building included logistic regression (LR), decision tree (DT), k-nearest neighbours (KNN), naive bayes (NB) and extreme gradient boosting (XGBoost). Parameters for model evaluation include receiver operating characteristic (ROC) curve, precision-recall curve (PRC), calibration curves, positive predictive value (PPV), negative predictive value (NPV), true positive rate (TPR), true negative rate (TNR), accuracy (ACC) and F1 score. RESULTS: Among 4527 patients, 445 patients (9.8 %) experienced ARF. Ca, ALB, GLR, WBC, AG and BUN have been included in the prediction model as features for predicting ARF. The AUC of XGBoost were 0.86 (95 %CI 0.84-0.88) and 0.87 (95 %CI 0.84-0.90) in the training and validation cohorts. In the training cohort, XGBoost demonstrates a true positive rate (TPR) of 0.662, a true negative rate (TNR) of 0.884, a positive predictive value (PPV) of 0.380, a negative predictive value (NPV) of 0.960, an accuracy (ACC) of 0.862, and an F1 score of 0.483. In the validation cohort, XGBoost shows a TPR of 0.620, a TNR of 0.895, a PPV of 0.399, an NPV of 0.955, an ACC of 0.867, and an F1 score of 0.486. CONCLUSION: The XGBOOST model demonstrates good discriminatory ability, which enables clinicians to ascertain the probability of developing ARF in AP patients.

Myeloid-derived suppressor cells-induced exhaustion of CD8 + T-cell participates in rejection after liver transplantation.

Liver transplantation (LT) rejection remains the most pervasive problem associated with this procedure, while the mechanism involved is still complicated and undefined. One promising solution may involve the use of myeloid-derived suppressor cells (MDSC). However, the immunological mechanisms underlying the effects of MDSC after LT remain unclear. This study is meant to clarify the role MDSCs play after liver transplantation. In this study, we collected liver tissue and peripheral blood mononuclear cells (PBMC) from LT patients showing varying degrees of rejection, as well as liver and spleen tissue samples from mice LT models. These samples were then analyzed using flow cytometry, immunohistochemistry and multiple immunofluorescence. M-MDSCs and CD8 + T-cells extracted from C57/BL6 mice were enriched and cocultured for in vitro experiments. Results, as obtained in both LT patients and LT mice model, revealed that the proportion and frequency of M-MDSC and PD-1 + T-cells increased significantly under conditions associated with a high degree of LT rejection. Within the LT rejection group, our immunofluorescence results showed that a close spatial contiguity was present between PD-1 + T-cells and M-MDSCs in these liver tissue samples and the proportion of CD84/PD-L1 double-positive M-MDSC was greater than that of G-MDSC. There was a positive correlation between the activity of CD84 and immunosuppressive function of M-MDSCs including PD-L1 expression and reactive oxygen species (ROS) production, as demonstrated in our in vitro model. M-MDSCs treated with CD84 protein were able to induce co-cultured CD8 + T-cells to express high levels of exhaustion markers. We found that CD84 regulated M-MDSC function via expression of PD-L1 through activation of the Akt/Stat3 pathway. These results suggest that the capacity for CD84 to regulate M-MDSC induction of CD8 + T-cell exhaustion may play a key role in LT rejection. Such findings provide important, new insights into the mechanisms of tolerance induction in LT.

FLT3+ DC inhibits immune rejection via interaction with Treg in liver transplantation.

Fms-like tyrosine kinase 3 (FLT3) is a receptor tyrosine kinase (RTK) primarily expressed in hematopoietic stem cells and dendritic cells (DCs). While FLT3 plays a critical role in the proliferation, development and maintenance of DCs, thus influencing immune responses under both normal and pathological conditions, there also exists some evidence that FLT3+DC may be involved with immune responses in liver transplantation (LT). In this study, results from single-cell sequencing data analysis revealed a clear relationship between FLT3+DCs and Regulatory T cells (Tregs) in liver tissue of LT recipients. In peripheral blood samples of LT patients, levels of FLT3+DCs were decreased post-LT-surgery, while Tregs were increased. In a LT mouse model, levels of FLT3+DCs in the liver and bone marrow exhibited an initial time-dependent decrease followed by an increase after LT surgery. Results as obtained with co-culture experiments using mature BMDCs and CD4+ T cells revealed fluctuations in Tregs in response to FLT3 inhibitors and the FLT3 ligand. These findings suggest that FLT3+DCs could emerge as a novel target for mitigating immune rejection in LT.

Characterization and Proteomic Analyses of Proinflammatory Cytokines in a Mouse Model of Liver Transplant Rejection.

Liver transplantation (LT) is an effective strategy for the treatment of end-stage liver disease, but immune rejection remains a significant detriment to the survival and prognosis of these LT patients. While immune rejection is closely related to cytokines, the cytokines investigated within previous studies have been limited and have not included a systematic analysis of proinflammatory cytokines. In the present study, we used a protein chip system and proteomics to detect and analyze serum proinflammatory cytokines and differentially expressed proteins in liver tissue in a mouse model of liver transplantation. In addition, bioinformatics analysis was employed to analyze the proinflammatory cytokines and differential changes in proteins in response to this procedure. With these analyses, we found that serum contents of GC-CSF, CXCL-1, MCP-5, and CXCL-2 were significantly increased after liver transplantation, while IL-5, IL-10, and IL-17 were significantly decreased. Results from Gene Ontology (GO) and KEGG pathway analyses revealed that the cytokine-cytokine receptor, Th1/Th2 cell differentiation, and JAK-STAT signaling pathway were enriched in a network associated with the activation of immune response. Results from our proteomic analysis of liver tissue samples revealed that 470 proteins are increased and 50 decreased, including Anxa1, Anxa2, Acsl4, Sirpa, S100a8, and S100a9. KEGG pathway analysis indicated that the neutrophil extracellular trap formation, NOD-like receptor signaling pathway, and leukocyte transendothelial migration were all associated with liver transplant rejection in these mice. Bioinformatics analysis results demonstrated that CXCL-1/CXCL-2 and S100a8/S100a9 were the genes most closely related to the functions of neutrophils and the mononuclear phagocyte system. These findings provide new insights into some of the critical factors associated with liver transplant rejection and thus offer new targets for the treatment and prevention of this condition.

ILC2s expanded by exogenous IL-33 regulate CD45+CD11b+F4/80high macrophage polarization to alleviate hepatic ischemia-reperfusion injury.

Hepatic ischemia-reperfusion injury (IRI) is an adverse consequence of hepatectomy or liver transplantation. Recently, immune mechanisms involved in hepatic IRI have attracted increased attention of investigators working in this area. In specific, group 2 innate lymphoid cells (ILC2s), have been strongly implicated in mediating type 2 inflammation. However, their immune mechanisms as involved with hepatic IRI remain unclear. Here, we reported that the population of ILC2s is increased with the development of hepatic IRI as shown in a mouse model in initial stage. Moreover, M2 type CD45+CD11b+F4/80high macrophages increased and reached maximal levels at 24 h followed by a significant elevation in IL-4 levels. We injected exogenous IL-33 into the tail vein of mice as a mean to stimulate ILC2s production. This stimulation of ILC2s resulted in a protective effect upon hepatic IRI along with an increase in M2 type CD45+CD11b+F4/80high macrophages. In contrast, depletion of ILC2s as achieved with use of an anti-CD90.2 antibody substantially abolished this protective effect of exogenous IL-33 and M2 type CD45+CD11b+F4/80high macrophage polarization in hepatic IRI. Therefore, this exogenous IL-33 induced potentiation of ILC2s appears to regulate the polarization of CD45+CD11b+F4/80high macrophages to alleviate IRI. Such findings provide the foundation for the development of new targets and strategies in the treatment of hepatic IRI.

Characteristics of changes in double positive CD4+CD8+ T cells in liver transplantation.

Although double positive CD4+CD8+ T (DPT) cells has been reported to be involved in some diseases, their trajectory and function as associated with liver transplantation (LT) remain unclear. In the present study, we found that the number of DPT cells was increased in the blood and liver tissue of LT patients. Meanwhile, we compared the distribution of DPT cells in peripheral blood samples and in penetrating liver tissue between liver rejection versus non-rejection patients, as well as the proportion of DPT cells as a function of the extent of liver rejection. The number of DPT cells in the rejection group was significantly increased. An analysis of the spatial distance and correlations between DPT and Treg cells, revealed that these cells showed a high degree of contiguity. In a mouse liver transplant model, the number of DPT cells were significantly increased in liver tissue, and the number of CD8+ T cells gradually increased, while CD4+ T cells decreased as a function of time post-transplantation. Expression level of PD-1 in DPT cells also increased in a temporally-dependent manner post liver transplantation and the changes of PD-1+ DPT cells were related to the degree of liver transplant rejection. In DPT cells interacting with Treg, there was an increased expression of PD-1, which enhanced cellular exhaustion. In conclusion, the capacity for DPT cells to induce immune tolerance may represent a new and important protocol for use in targeting treatments for the prevention of liver transplant rejection.