Establishment and evaluation of a model for predicting 3-month mortality in Chinese patients with hepatic encephalopathy

Using machine learning methods to predict 28-day mortality in patients with hepatic encephalopathy

BACKGROUND

Hepatic encephalopathy (HE) is associated with marked increases in morbidity and mortality for cirrhosis patients. This study aimed to develop and validate machine learning (ML) models to predict 28-day mortality for patients with HE.

METHODS

A retrospective cohort study was conducted in the Medical Information Mart for Intensive Care (MIMIC)-IV database. Patients from MIMIC-IV were randomized into training and validation cohorts in a ratio of 7:3. Training cohort was used for establishing the model while validation cohort was used for validation. The outcome was defined as 28-day mortality. Predictors were identified by recursive feature elimination (RFE) within 24 h of intensive care unit (ICU) admission. The area under the curve (AUC) and calibration curve were used to determine the predictive performance of different ML models.

RESULTS

In the MIMIC-IV database, 601 patients were eventually diagnosed with HE. Of these, 112 (18.64%) experienced death within 28 days. Acute physiology score III (APSIII), sepsis related organ failure assessment (SOFA), international normalized ratio (INR), total bilirubin (TBIL), albumin, blood urea nitrogen (BUN), acute kidney injury (AKI) and mechanical ventilation were identified as independent risk factors. Validation set indicated that the artificial neural network (NNET) model had the highest AUC of 0.837 (95% CI:0.774-0.901). Furthermore, in the calibration curve, the NNET model was also well-calibrated (P = 0.323), which means that it can better predict the 28-day mortality in HE patients. Additionally, the performance of the NNET is superior to existing scores, including Model for End-Stage Liver Disease (MELD) and Model for End-Stage Liver Disease-Sodium (MELD-Na).

CONCLUSIONS

In this study, the NNET model demonstrated better discrimination in predicting 28-day mortality as compared to other models. This developed model could potentially improve the early detection of HE with high mortality, subsequently improving clinical outcomes in these patients with HE, but further external prospective validation is still required.

Overview of oxidative stress findings in hepatic encephalopathy: From cellular and ammonium-based animal models to human data

Oxidative stress is a natural phenomenon in the body. Under physiological conditions intracellular reactive oxygen species (ROS) are normal components of signal transduction cascades, and their levels are maintained by a complex antioxidants systems participating in the in-vivo redox homeostasis. Increased oxidative stress is present in several chronic diseases and interferes with phagocytic and nervous cell functions, causing an up-regulation of cytokines and inflammation. Hepatic encephalopathy (HE) occurs in both acute liver failure (ALF) and chronic liver disease. Increased blood and brain ammonium has been considered as an important factor in pathogenesis of HE and has been associated with inflammation, neurotoxicity, and oxidative stress. The relationship between ROS and the pathophysiology of HE is still poorly understood. Therefore, sensing ROS production for a better understanding of the relationship between oxidative stress and functional outcome in HE pathophysiology is critical for determining the disease mechanisms, as well as to improve the management of patients. This review is emphasizing the important role of oxidative stress in HE development and documents the changes occurring as a consequence of oxidative stress augmentation based on cellular and ammonium-based animal models to human data.

Radiomics-based classification models for HBV-related cirrhotic patients with covert hepatic encephalopathy

INTRODUCTION

The significant abnormalities of precuneus (PC), which are associated with brain dysfunction, have been identified in cirrhotic patients with covert hepatic encephalopathy (CHE). The present study aimed to apply radiomics analysis to identify the significant radiomic features in PC and their subregions, combine with clinical risk factors, then build and evaluate the classification models for CHE diagnosis.

METHODS

106 HBV-related cirrhotic patients (54 had current CHE and 52 had non-CHE) underwent the three-dimensional T1-weighted imaging. For each participant, PC and their subregions were segmented and extracted a large number of radiomic features and then identified the features with significant discriminative power as the radiomics signature. The logistic regression analysis was employed to develop and evaluate the classification models, which are constructed using the radiomics signature and clinical risk factors.

RESULTS

The classification model (R-C model) achieved best diagnostic performance, which incorporated radiomics signature (4 radiomic features from right PC), venous blood ammonia, and the Child-Pugh stage. And the area under the receiver operating characteristic curve values (AUC), sensitivity, specificity, and accuracy values were 0.926, 1.000, 0.765, and 0.848, in the testing set. Application of the radiomics nomogram in the testing set still showed a good predictive accuracy.

CONCLUSIONS

This study presented the radiomic features of the right PC, as a potential image marker of CHE. The radiomics nomogram that incorporates the radiomics signature and clinical risk factors may facilitate the individualized prediction of CHE.

Association of serum albumin level with incidence and mortality of overt hepatic encephalopathy in cirrhosis during hospitalization

BACKGROUND

Hepatic encephalopathy (HE) is a serious complication of cirrhosis. Decreased serum albumin (ALB) level may facilitate the development of HE and accelerate the death of cirrhotic patients with HE. Recent evidence also suggests that human albumin infusion may reduce the incidence of HE and improve the outcomes of cirrhotic patients. This study aimed to explore the association of serum ALB level with the development of overt HE and HE-associated mortality during hospitalization.

METHODS

Cirrhotic patients admitted to our hospital between January 2010 and February 2019 were screened. Independent predictors for HE were identified by logistic regression analyses. Odds ratio (OR) with 95% confidence interval (95% CI) was calculated. Area under curve (AUC) was calculated by receiver operator characteristic curve analyses.

RESULTS

Of the 2376 included patients with cirrhosis but without HE at admission, 113 (4.8%) developed overt HE during hospitalizations. ALB level (OR = 0.878, 95% CI = 0.834-0.924) was an independent risk factor for development of overt HE. AUC of ALB level for predicting the development of overt HE was 0.770 (95% CI = 0.752-0.787, p < 0.0001), and the best cut-off value was ⩽31.6 g/l. Of the 183 included patients with cirrhosis and overt HE at admission, 20 (10.9%) died during hospitalizations. ALB level (OR = 0.864, 95% CI = 0.771-0.967) was an independent risk factor for death from overt HE. The AUC of ALB level for predicting death from overt HE was 0.737 (95% CI = 0.667-0.799, p = 0.0001), and the best cut-off value was ⩽22.8 g/l.

CONCLUSIONS

Decreased serum ALB level may be associated with higher risk of overt HE and HE-associated mortality during hospitalizations in cirrhosis.