Search

Sepsis-Associated Liver Injury (SALI) is an independent risk factor for death from sepsis. The aim of this study was to develop an interpretable machine learning model for early prediction of 28-day mortality in patients with SALI. Data from the Medical Information Mart for Intensive Care (MIMIC-IV, v2.2, MIMIC-III, v1.4) were used in this study. The study cohort from MIMIC-IV was randomized to the training set (0.7) and the internal validation set (0.3), with MIMIC-III (2001 to 2008) as external validation. The features with more than 20% missing values were deleted and the remaining features were multiple interpolated. Lasso-CV that lasso linear model with iterative fitting along a regularization path in which the best model is selected by cross-validation was used to select important features for model development. Eight machine learning models including Random Forest (RF), Logistic Regression, Decision Tree, Extreme Gradient Boost (XGBoost), K Nearest Neighbor, Support Vector Machine, Generalized Linear Models in which the best model is selected by cross-validation (CV_glmnet), and Linear Discriminant Analysis (LDA) were developed. Shapley additive interpretation (SHAP) was used to improve the interpretability of the optimal model. At last, a total of 1043 patients were included, of whom 710 were from MIMIC-IV and 333 from MIMIC-III. Twenty-four clinically relevant parameters were selected for model construction. For the prediction of 28-day mortality of SALI in the internal validation set, the area under the curve (AUC (95% CI)) of RF was 0.79 (95% CI: 0.73–0.86), and which performed the best. Compared with the traditional disease severity scores including Oxford Acute Severity of Illness Score (OASIS), Sequential Organ Failure Assessment (SOFA), Simplified Acute Physiology Score II (SAPS II), Logistic Organ Dysfunction Score (LODS), Systemic Inflammatory Response Syndrome (SIRS), and Acute Physiology Score III (APS III), RF also had the best performance. SHAP analysis found that Urine output, Charlson Comorbidity Index (CCI), minimal Glasgow Coma Scale (GCS_min), blood urea nitrogen (BUN) and admission_age were the five most important features affecting RF model. Therefore, RF has good predictive ability for 28-day mortality prediction in SALI. Urine output, CCI, GCS_min, BUN and age at admission(admission_age) within 24 h after intensive care unit(ICU) admission contribute significantly to model prediction. [ABSTRACT FROM AUTHOR]

Background: About a half of the world's population is infected with Helicobacter pylori (H. pylori), but only 1%–3% of them develop gastric cancer. As a primary risk factor for gastric cancer, the relationship between H. pylori infection and gastric microbiome has been a focus in recent years. Materials and methods: We reanalyze 11 human gastric microbiome datasets with or without H. pylori, covering the healthy control (HC) and four disease stages (chronic gastritis (CG), atrophic gastritis (AG), intestinal metaplasia (IM), and gastric cancer (GC)) of gastric cancer development to quantitatively compare the influences of the H. pylori infection and disease stages on the diversity, heterogeneity, and composition of gastric microbiome. Four medical ecology approaches including (i) diversity analysis with Hill numbers, (ii) heterogeneity analysis with Taylor's power law extensions (TPLE), (iii) diversity scaling analysis with diversity–area relationship (DAR) model, and (iv) shared species analysis were applied to fulfill the data reanalysis. Results: (i) The influences of H. pylori infection on the species diversity, spatial heterogeneity, and potential diversity of gastric microbiome seem to be more prevalent than the influences of disease stages during gastric cancer development. (ii) The influences of H. pyloriinfection on diversity, heterogeneity, and composition of gastric microbiomes in HC, CG, IM, and GC stages appear more prevalent than those in AG stage. Conclusion: Our study confirmed the impact of H. pylori infection on human gastric microbiomes: The influences of H. pylori infection on the diversity, heterogeneity, and composition of gastric microbiomes appear to be disease‐stage dependent. [ABSTRACT FROM AUTHOR]

Introduction: Despite observational studies suggest hypotheses indicating a potential link, the precise causal connection between sarcopenia and digestive system illnesses has not been clearly defined., Methods: We first use Linkage Disequilibrium Score Regression (LDSC) testing to determine the genetic correlation of traits associated with sarcopenia and 10 specific gastrointestinal diseases. Subsequently, we performed a set of bidirectional Mendelian Randomization (MR) analyses to gauge the genetic inclination towards sarcopenia-related traits in relation to each gastrointestinal condition, individually, across the FinnGen, UK Biobank, and other extensive collaborative consortia. The analytical outcomes were synthesized using a fixed-effects meta-analytic model. For outcomes indicating substantial causal impacts, mediation MR analyses were executed. Additionally, a battery of sensitivity analyses was conducted to evaluate the study's strength and dependability., Results: Our findings established a strong causal link between appendicular lean mass and gastroesophageal reflux disease (OR  =  0.8607; 95% CI: 0.8345-0.8877; p <  0.0001) and a noteworthy correlation with nonalcoholic fatty liver disease (OR  =  0.7981; 95% CI: 0.7281-0.8749; p < 0.0001), as per the meta-analysis data. We also evaluated the intermediary role of metabolic disorders in the association between appendicular lean mass and the aforementioned diseases. The intermediary effect towards gastroesophageal reflux disease is quantified as 0.0087 (95% CI, 8e-04, 0.0183), accounting for 5.9398% (95% CI, 0.5462, 12.4940%) of the overall effect. For non-alcoholic fatty liver, the intermediary impact is 0.0150 (95% CI, 0.0050, 0.0270), representing 19.7808% (95% CI, 6.5936, 35.6055%) of the total effect., Conclusion: The findings posit that augmenting muscle mass may serve as a preventative strategy against gastroesophageal reflux disease and non-alcoholic fatty liver, highlighting the critical role of metabolic disorder management in reducing the risks of these sarcopenia-related conditions., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2024 Yang, Liu, Xiu, Qing, Liu, Xiao and Lü.)