Admission Serum Bicarbonate Predicts Adverse Clinical Outcomes in Hospitalized Cirrhotic Patients

Factors predicting mortality in patients with alcoholic liver cirrhosis visiting the emergency department

Liver cirrhosis (LC) is a major cause of morbidity and mortality worldwide and is becoming a regional and healthcare burden. South Korea is one of the 10 countries with the highest age standardized prevalence of decompensated LC. Moreover, the proportion of patients with alcoholic LC is increasing and there has been no decrease in the incidence of decompensated alcoholic LC. Patients with decompensated LC frequently visit the emergency department (ED). Several studies focused on patients with LC who visited the ED, but the studies about alcoholic LC were limited. This study aimed to identify predicting factors for mortality in alcoholic LC patients visiting the ED. This was a retrospective study of alcoholic LC patients who visited an ED between November 2017 and June 2021. The baseline characteristics, complications of LC, model for end-stage liver disease (MELD) score, and laboratory values including lactate were assessed. The primary outcome was in-hospital mortality. In total, 433 patients with alcoholic LC were included for analysis and the in hospital mortality rate was 15.9% (n = 69). Univariate regression analyses identified that MELD score, lactate, platelet, international normalized ratio, bilirubin, creatinine, albumin, and C-reactive protein (CRP) predicted in-hospital mortality. Multivariate regression analysis showed that MELD score, lactate, albumin, and CRP were significantly associated with in-hospital mortality. MELD score, lactate, albumin, and CRP predicted the mortality in alcoholic LC patients visiting the ED.

Identification of key predictors of hospital mortality in critically ill patients with embolic stroke using machine learning

Embolic stroke (ES) is characterized by high morbidity and mortality. Its mortality predictors remain unclear. The present study aimed to use machine learning (ML) to identify the key predictors of mortality for ES patients in the intensive care unit (ICU). Data were extracted from two large ICU databases: Medical Information Mart for Intensive Care (MIMIC)-IV for training and internal validation, and eICU Collaborative Research Database (eICU-CRD) for external validation. We developed predictive models of ES mortality based on 15 ML algorithms. We relied on the synthetic minority oversampling technique (SMOTE) to address class imbalance. Our main performance metric was area under the receiver operating characteristic (AUROC). We adopted recursive feature elimination (RFE) for feature selection. We assessed model performance using three disease-severity scoring systems as benchmarks. Of the 1566 and 207 ES patients enrolled in the two databases, there were 173 (15.70%), 73 (15.57%), and 36 (17.39%) hospital mortality in the training, internal validation, and external validation cohort, respectively. The random forest (RF) model had the largest AUROC (0.806) in the internal validation phase and was chosen as the best model. The AUROC of the RF compact (RF-COM) model containing the top six features identified by RFE was 0.795. In the external validation phase, the AUROC of the RF model was 0.838, and the RF-COM model was 0.830, outperforming other models. Our findings suggest that the RF model was the best model and the top six predictors of ES hospital mortality were Glasgow Coma Scale, white blood cell, blood urea nitrogen, bicarbonate, age, and mechanical ventilation.