Search

Background: Pneumonia, a leading cause of morbidity and mortality worldwide, often necessitates Intensive Care Unit (ICU) admission. Accurate prediction of pneumonia mortality is crucial for tailored prevention and treatment plans. However, existing mortality prediction models face limited adoption in clinical practice due to their lack of interpretability. Objective: This study aimed to develop an interpretable model for predicting pneumonia mortality in ICUs. Leveraging the Shapley Additive Explanation (SHAP) method, we sought to elucidate the Extreme Gradient Boosting (XGBoost) model and identify prognostic factors for pneumonia. Methods: Conducted as a retrospective cohort study, we utilized electronic health records from the eICU-CRD (2014–2015) for all adult pneumonia patients. The first 24 h of each ICU admission records were considered, with 70% of the dataset allocated for model training and 30% for validation. The XGBoost model was employed, and performance was assessed using the area under the receiver operating characteristic curve (AUC). The SHAP method provided insights into the XGBoost model. Results: Among 10,962 pneumonia patients, in-hospital mortality was 16.33%. The XGBoost model demonstrated superior predictive performance (AUC: 0.778 ± 0.016)) compared to traditional scoring systems and other machine learning method, which achieved an improvement of 10% points. SHAP analysis identified Aspartate Aminotransferase (AST) as the most crucial predictor. Conclusions: Interpretable predictive models enhance mortality risk assessment for pneumonia patients in the ICU, fostering transparency. AST emerged as the foremost predictor, followed by patient age, albumin, BMI et al. These insights, rooted in strong correlations with mortality, facilitate improved clinical decision-making and resource allocation. [ABSTRACT FROM AUTHOR]

Acute pancreatitis (AP) is a common systemic inflammatory disease resulting from the activation of trypsinogen by various incentives in ICU. The annual incidence rate is approximately 30 out of 100,000. Some patients may progress to severe acute pancreatitis, with a mortality rate of up to 40%. Therefore, the goal of this article is to explore the key genes for effective diagnosis and treatment of AP. The analysis data for this study were merged from two GEO datasets. 1357 DEGs were used for functional enrichment and cMAP analysis, aiming to reveal the pathogenic genes and potential mechanisms of AP, as well as potential drugs for treating AP. Importantly, the study used LASSO and SVM-RFE machine learning to screen the most likely AP occurrence biomarker for Prdx4 among numerous candidate genes. A receiver operating characteristic of Prdx4 was used to estimate the incidence of AP. The ssGSEA algorithm was employed to investigate immune cell infiltration in AP. The biomarker Prdx4 gene exhibited significant associations with a majority of immune cells and was identified as being expressed in NKT cells, macrophages, granulocytes, and B cells based on single-cell transcriptome data. Finally, we found an increase in Prdx4 expression in the pancreatic tissue of AP mice through immunohistochemistry. After treatment with recombinant Prdx4, the pathological damage to the pancreatic tissue of AP mice was relieved. In conclusion, our study identified Prdx4 as a potential AP hub gene, providing a new target for treatment. [ABSTRACT FROM AUTHOR]

Background: Immunoscore from tumor tissues was initially established to evaluate the prognosis of solid tumor patients. However, the feasibility of circulating immune score (cIS) for the prognosis of advanced gastrointestinal cancers (AGC) has not been reported. Material and methods: Peripheral venous blood was collected from 64 untreated AGC patients. We utilized flow cytometry to determine several immune cell subpopulations, including CD8+ and CD4+ T cells, NK cells, and CD4 + CD25 + CD127low Tregs. The circulating immune score 1 (cIS1) was assessed according to the proportions of CD4+, CD8+ T cells, and NK cell, whereas circulating immune score 2 (cIS2) was derived from the proportions of CD4+, CD8+ T cell, and CD4 + CD25 + CD127low Tregs. The prognostic role of cIS for progression-free survival (PFS) and overall survival (OS) was analyzed using Kaplan–Meier curves and Cox multivariate models. Receiver operating characteristic (ROC) curves were depicted to compare the prognostic values of cIS1 and cIS2. Results: AGC patients with high cIS1(≥ 2) and cIS2(≥ 2) had significantly longer PFS (cIS1: median PFS, 11 vs. 6.7 months, P = 0.001; cIS2: 12 vs. 5.8 months, P < 0.0001) and OS (cIS1: median OS, 12 vs. 7.9 months, P = 0.0004; cIS2: 12.8 vs. 7.4 months, P < 0.0001) than those with low cIS1 and low cIS2. The areas under ROC curves (AUROCs) of cIS1 and cIS2 for OS were 0.526 (95% confidence interval; 95% CI 0.326–0.726) and 0.603 (95% CI 0.427–0.779, P = 0.332), whereas AUROC of cIS2 for PFS was larger than that of cIS1 0.735 (95% CI 0.609–0.837) vs 0.625 (95% CI 0.495–0.743) (P = 0.04)). Conclusion: The cIS can be applied to predict the prognosis of untreated AGC patients. Compared with cIS1, cIS2 displayed superior prognostic value for PFS prediction. [ABSTRACT FROM AUTHOR]

Background: The association between natural killer (NK) cells and survival in colorectal cancer (CRC) patients remains controversial. This study aimed to clarify the prognostic value of peripheral blood NK cells in CRC patients.Methods: A total of 447 CRC patients who underwent radical surgery and chemotherapy were retrospectively analyzed. Cox regression analyses were used to identify independent prognostic indicators. Correlation between NK cell percentage and other clinicopathological features (gender, age, histological grade, tumor stage, immune cells, and inflammatory indicators) was analyzed. The prognostic values of the combinations of NK cell percentage and other clinicopathological features were also determined.Results: Multivariate Cox regression analysis revealed that NK cell percentage in the peripheral blood was an independent prognostic indicator in CRC patients. A higher percentage of NK cells indicated a longer survival time than a lower percentage. NK cell percentage was positively correlated to the T and B lymphocyte counts and negatively correlated to the patients' age and albumin levels. With an area of 0.741 under a receiver operating characteristic curve, NK cells have a moderate predictive value for 3rd-year survival in CRC. This area increased to 0.851 by combining NK cell percentage with the B lymphocyte count. Elderly patients and those at an advanced clinical stage presented a lower percentage of NK cells than younger patients and those at an early clinical stage.Conclusions: This study demonstrated that NK cells in the blood were an independent predictor of survival in CRC patients, and the combined count of NK cells and B lymphocytes could increase the prognostic value. [ABSTRACT FROM AUTHOR]