Comparing CLIF-C ACLF, CLIF-C ACLFlactate, and CLIF-C ACLF-D Prognostic Scores in Acute-on-Chronic Liver Failure Patients by a Single-Center ICU Experience

Construction and validation of a machine learning-based prediction model for short-term mortality in critically ill patients with liver cirrhosis

OBJECTIVE

Critically ill patients with liver cirrhosis generally have a poor prognosis due to complications such as multiple organ failure. This study aims to develop a machine learning-based prediction model to forecast short-term mortality in critically ill cirrhotic patients in the intensive care unit (ICU), thereby assisting clinical decision-making for intervention and treatment.

METHODS

Machine learning models were developed using clinical data from critically ill cirrhotic patients in the MIMIC database, with multicenter validation performed using data from the eICU database and Qinghai University Affiliated Hospital(QUAH). Various machine learning models, including a Stacking ensemble model, were employed, with the SHAP method used to enhance model interpretability.

RESULTS

The Stacking ensemble model demonstrated superior predictive performance through internal and external validation, with AUC and AP values surpassing those of individual algorithms. The AUC values were 0.845 in the internal validation set, 0.819 in the eICU external validation, and 0.761 in the QUAH validation set. Additionally, the SHAP method highlighted key prognostic variables such as INR, bilirubin, and urine output. The model was ultimately deployed as a web-based calculator for bedside decision-making.

CONCLUSION

The machine learning model effectively predicts short-term mortality risk in critically ill cirrhotic patients in the ICU, showing strong predictive performance and generalizability. The model's robust interpretability and its deployment as a web-based calculator suggest its potential as a valuable tool for assessing the prognosis of cirrhotic patients.

Prognosis algorithms for acute decompensation of cirrhosis and ACLF

Accurate prediction of survival in patients with cirrhosis is crucial, as patients who are unlikely to survive in the short-term need to be oriented to liver transplantation and to novel therapeutic approaches. Patients with acute decompensation of cirrhosis without or with organ dysfunction/failure, the so-called acute-on-chronic liver failure (ACLF), have a particularly high short-term mortality. Recognizing the specificity of this clinical situation, dedicated classifications and scores have been developed over the last 15 years, including variables (e.g. organ failures and systemic inflammation) not part of the formerly available cirrhosis severity scores, namely Child-Pugh score or MELD. For patients with acute decompensation of cirrhosis, it led to the development of a dedicated score, the Clif-C-AD score, independently validated. For more severe patients, three different scoring systems have been proposed, by European, Asian and North American societies namely Clif-C-ACLF, AARC score and NASCELD-ACLF respectively. These scores have been validated, and are widely used across the world. The differences and similarities between these scores, as well as their validation and limitations are discussed here. Even if these scores and classifications have been a step forward in favouring homogeneity between studies, and in helping making decisions for individual patients, their predictive value for mortality can still be improved as their area under the ROC curve does not exceed .8. Novel scores including biomarkers reflecting the pathophysiology of acute decompensation of cirrhosis might help reach that goal.

A novel prognostic model to predict mortality in patients with acute-on-chronic liver failure in intensive care unit

Acute-on-chronic liver failure (ACLF) implies high short-term mortality rates and usually requires intensive care unit (ICU) admission. Proper prognosis for these patients is crucial for early referral for liver transplantation. The superiority of CLIF-C ACLF score in Asian patients with ACLF admitted to an ICU remains inconclusive when compared to other scoring systems. The purpose of the study is (i) to compare the predictive performance of original MELD, MELD-Lactate, CLIF-C ACLF, CLIF-C ACLF-Lactate, and APACHE-II scores for short-term mortality assessment. (ii) to build and validate a novel scoring system and to compare its predictive performance to that of the original five scores. Two hundred sixty-five consecutive cirrhotic patients with ACLF who were admitted to our ICU were enrolled. The prognostic values for mortality were assessed by ROC analysis. A novel model was developed and internally validated using fivefold cross-validation. Alcohol abuse was identified as the primary etiology of cirrhosis. The AUROC of the five prognostic scores were not significantly superior to each other in predicting 1-month and 3-month mortality. The newly developed prognostic model, incorporating age, alveolar-arterial gradient (A-a gradient), BUN, total bilirubin level, INR, and HE grades, exhibited significantly improved performance in predicting 1-month and 3-month mortality with AUROC of 0.863 and 0.829, respectively, as compared to the original five prognostic scores. The novel ACLF model seems to be superior to the original five scores in predicting short-term mortality in ACLF patients admitted to an ICU. Further rigorous validation is required.

Comparing Three Profoundly Influential Prognostic Scores in Cirrhotic Patients with Acute-on-Chronic-Liver Failure Admitted to the ICU: Prediction of One-Month Mortality-A Retrospective Cohort Study

BACKGROUND

Acute-on-chronic-liver failure (ACLF) demonstrates high short-term mortality rates and usually requires intensive care unit (ICU) admission. Accurate prognostication of these patients is pivotal for timely referral for liver transplantation. The superiority of CLIF-C ACLF, CLIF-C ACLF lactate, and NACSELD-ACLF scores in Asian patients with ACLF admitted to an ICU remains inconclusive.

AIMS

To compare the predictive performance of CLIF-C ACLF, CLIF-C ACLF lactate, and NACSELD-ACLF scores for one-month mortality.

METHODS

276 consecutive cirrhotic patients with ACLF admitted to ICU were enrolled. The prognostic values for one-month mortality were assessed by AUROC analysis.

RESULTS

The primary cause of cirrhosis in this cohort was alcohol abuse (56.5%). AUROC analysis (95% confidence intervals) demonstrated that CLIF-C ACLF lactate [0.802 (0.747-0.856)] outperformed both CLIF-C ACLF [0.791 (0.733-0.848)] and NACSELD-ACLF [0.673 (0.606-0.740)] in predicting one-month mortality. However, no statistically significant difference was observed between the predictive abilities of CLIF-C ACLF and CLIF-C ACLF lactate.

CONCLUSIONS

In critically ill cirrhotic patients with ACLF admitted to the hepatology ICU, CLIF ACLF-lactate outperformed CLIF-C ACLF and NACSELD-ACLF in predicting one-month mortality. Nevertheless, no statistically significant difference was observed between CLIF-C ACLF and CLIF-C ACLF lactate. Larger-scale multi-center prospective studies are warranted to validate these results.

CLIF-SOFA and CLIF-C scores for the prognostication of acute-on-chronic liver failure and acute decompensation of cirrhosis: A systematic review

BACKGROUND

Acute-on-chronic liver failure (ACLF) is a syndrome characterized by decompensation in individuals with chronic liver disease, generally secondary to one or more extra-hepatic organ failures, implying an elevated mortality rate. Acute decompensation (AD) is the term used for one or more significant consequences of liver disease in a short time and is the most common reason for hospital admission in cirrhotic patients. The European Association for the Study of Liver-Chronic-Liver Failure (EASL-CLIF) Group modified the intensive care Sequential Organ Failure Assessment score into CLIF-SOFA, which detects the presence of ACLF in patients with or without AD, classifying it into three grades.

AIM

To investigate the role of the EASL-CLIF definition for ACLF and the ability of CLIF-SOFA, CLIF-C ACLF, and CLIF-C AD scores for prognosticating ACLF or AD.

METHODS

This study is a literature review using a standardized search method, conducted using the steps following the guidelines for reporting systematic reviews set out by the PRISMA statement. For specific keywords, relevant articles were found by searching PubMed, ScienceDirect, and BioMed Central-BMC. The databases were searched using the search terms by one reviewer, and a list of potentially eligible studies was generated based on the titles and abstracts screened. The data were then extracted and assessed on the basis of the Reference Citation Analysis (https://www.referencecitationanalysis.com/).

RESULTS

Most of the included studies used the EASL-CLIF definition for ACLF to identify cirrhotic patients with a significant risk of short-term mortality. The primary outcome in all reviewed studies was mortality. Most of the study findings were based on an area under the receiver operating characteristic curve (AUROC) analysis, which revealed that CLIF-SOFA, CLIF-C ACLF, and CLIF-C AD scores were preferable to other models predicting 28-d mortality. Their AUROC scores were higher and able to predict all-cause mortality at 90, 180, and 365 d. A total of 50 articles were included in this study, which found that the CLIF-SOFA, CLIF-C ACLF and CLIF-C AD scores in more than half of the articles were able to predict short-term and long-term mortality in patients with either ACLF or AD.

CONCLUSION

CLIF-SOFA score surpasses other models in predicting mortality in ACLF patients, especially in the short-term. CLIF-SOFA, CLIF-C ACLF, and CLIF-C AD are accurate short-term and long-term mortality prognosticating scores.

Establishment of MELD-lactate clearance scoring system in predicting death risk of critically ill cirrhotic patients

Background

To develop a scoring system related to the lactate clearance (ΔLA) to predict the mortality risk (MELD-ΔLA) for critically ill cirrhotic patients.

Methods

In this retrospective cohort study, 881 critically ill cirrhotic patients from the Medical Information Mart for Intensive Care (MIMIC-III) database were included eventually. The outcomes of our study were defined as ICU death, 28-day, 90-day and 1-year mortality. Predictors were identified by multivariate Cox analysis to develop the predictive scoring system. The C-index and area under the curve (AUC) of receiver operator characteristic curve (ROC) were used to identify the predicting performance of the MELD-ΔLA, sequential organ failure assessment (SOFA), chronic liver failure-sequential organ failure assessment (CLIF-SOFA), the model for end-stage liver disease (MELD), Child–Pugh, chronic liver failure consortium acute-on-chronic liver failure (CLIF-C ACLF), chronic liver failure consortium-acute decompensation (CLIF-C AD) and MELD-Na scoring systems. Additionally, subgroup analysis was also performed based on whether critically ill cirrhotic patients underwent liver transplantation.

Results

Creatinine, bilirubin, international normalized ratio (INR), lactate first, ΔLA and vasopressors were closely associated with ICU death of liver critically ill cirrhotic patients. The C-index of the MELD-ΔLA in ICU death was 0.768 (95% CI 0.736–0.799) and the AUC for the MELD-ΔLA scoring system in predicting 28-day, 90-day, and 1-year mortality were 0.774 (95% CI 0.743–0.804), 0.765 (95% CI 0.735–0.796), and 0.757 (95% CI 0.726–0.788), suggested that MELD-ΔLA scoring system has a good predictive value than SOFA, CLIF-SOFA, MELD, Child–Pugh, CLIF-C ACLF, CLIF-C AD) and MELD-Na scoring systems. Additionally, the study also confirmed the good predictive value of MELD-ΔLA scoring system for critically ill cirrhotic patients regardless of undergoing liver transplantation.

Conclusion

The developed MELD-ΔLA score is a simple scoring system in predicting the risk of ICU death, 28-day, 90-day and 1-year mortality for critically ill cirrhotic patients, which may have a good predictive performance.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12876-022-02351-5.

Definition and classification of acute-on-chronic liver diseases

Patients with chronic liver diseases (CLDs) develop acute liver injury and/or acute decompensation under the attack of various precipitants and present with significantly elevated alanine aminotransferase and/or total bilirubin levels, liver failure, or acute decompensation of liver cirrhosis, which is called acute-on-CLD (AoCLD). AoCLD accounts for the majority of patients hospitalized in the Department of Hepatology or Infectious Diseases. AoCLD is complicated by various clinical types, the severity of the disease, and may pose a high risk of death. To date, the definition of AoCLD is still vague, and a consensus concept of the clinical classification is lacking. This review aimed to define the concept and clinical types of AoCLD based on related studies and the literature.