Prognostic factors of the short-term outcomes of patients with hepatitis B virus-associated acute-on-chronic liver failure

Acute on chronic liver failure: prognostic models and artificial intelligence applications

Critically ill patients presenting with acute on chronic liver failure (ACLF) represent a particularly vulnerable population due to various considerations surrounding the syndrome definition, lack of robust prospective evaluation of outcomes, and allocation of resources such as organs for transplantation. Ninety-day mortality related to ACLF is high and patients who do leave the hospital are frequently readmitted. Artificial intelligence (AI), which encompasses various classical and modern machine learning techniques, natural language processing, and other methods of predictive, prognostic, probabilistic, and simulation modeling, has emerged as an effective tool in various areas of healthcare. These methods are now being leveraged to potentially minimize physician and provider cognitive load and impact both short-term and long-term patient outcomes. However, the enthusiasm is tempered by ethical considerations and a current lack of proven benefits. In addition to prognostic applications, AI models can likely help improve the understanding of various mechanisms of morbidity and mortality in ACLF. Their overall impact on patient-centered outcomes and countless other aspects of patient care remains unclear. In this review, we discuss various AI approaches being utilized in healthcare and discuss the recent and expected future impact of AI on patients with ACLF through prognostic modeling and AI-based approaches.

Artificial neural network-based models used for predicting 28- and 90-day mortality of patients with hepatitis B-associated acute-on-chronic liver failure

Background

This study aimed to develop prognostic models for predicting 28- and 90-day mortality rates of hepatitis B virus (HBV)-associated acute-on-chronic liver failure (HBV-ACLF) through artificial neural network (ANN) systems.

Methods

Six hundred and eight-four cases of consecutive HBV-ACLF patients were retrospectively reviewed. Four hundred and twenty-three cases were used for training and constructing ANN models, and the remaining 261 cases were for validating the established models. Predictors associated with mortality were determined by univariate analysis and were then included in ANN models for predicting prognosis of mortality. The receiver operating characteristic curve analysis was used to evaluate the predictive performance of the ANN models in comparison with various current prognostic models.

Results

Variables with statistically significant difference or important clinical characteristics were input in the ANN training process, and eight independent risk factors, including age, hepatic encephalopathy, serum sodium, prothrombin activity, γ-glutamyltransferase, hepatitis B e antigen, alkaline phosphatase and total bilirubin, were eventually used to establish ANN models. For 28-day mortality in the training cohort, the model’s predictive accuracy (AUR 0.948, 95% CI 0.925–0.970) was significantly higher than that of the Model for End-stage Liver Disease (MELD), MELD-sodium (MELD-Na), Chronic Liver Failure-ACLF (CLIF-ACLF), and Child-Turcotte-Pugh (CTP) (all p < 0.001). In the validation cohorts the predictive accuracy of ANN model (AUR 0.748, 95% CI: 0.673–0.822) was significantly higher than that of MELD (p = 0.0099) and insignificantly higher than that of MELD-Na, CTP and CLIF-ACLF (p > 0.05). For 90-day mortality in the training cohort, the model’s predictive accuracy (AUR 0.913, 95% CI 0.887–0.938) was significantly higher than that of MELD, MELD-Na, CTP and CLIF-ACLF (all p < 0.001). In the validation cohorts, the prediction accuracy of the ANN model (AUR 0.754, 95% CI: 0.697–0.812 was significantly higher than that of MELD (p = 0.019) and insignificantly higher than MELD-Na, CTP and CLIF-ACLF (p > 0.05).

Conclusions

The established ANN models can more accurately predict short-term mortality risk in patients with HBV- ACLF.

The main content has been postered as an abstract at the AASLD Hepatology Conference (10.1002/hep.30257).

Risk factors and prognostic analysis of acute-on-chronic liver failure of chronic hepatitis B after cessation of nucleos(t)ide analogs

BACKGROUND

To explore the risk factors and prognostic factors related to the acute-on-chronic liver failure (ACLF) occurrence and adverse outcome after withdrawal of nucleos(t)ide analogs (NAs) in chronic hepatitis B (CHB) patients.

METHODS

Hospitalized CHB patients with relapse after NAs withdrawal at our medical center were retrospectively included in the present study from January 2011 to May 2018. Logistic regression, Cox regression analysis, Kaplan-Meier log-rank test, and area under the receiver operating characteristic curves (AUROC) were used.

RESULTS

A total of 389 CHB patients (including 46 ACLF patients) were included. Their median age was 48.0 years; 315 patients were male and 74 were female. The age ≥30 years and HBVDNA ≤1000 copies at admission in logistic regression were the independent risk factors for ACLF after NAs withdrawal in CHB patients. In patients who developed ACLF, only the model of end-stage liver disease combining serum natrium concentration (MELD-Na) score and relapse after Lamivudine (LAM) cessation in the Cox multivariate regression analysis were independent predictors for 12-week mortality. The artificial liver support system (ALSS) showed no improvement in the 12-week survival of ACLF patients. We further defined 22.35 as the optimal cutoff value of MELD-Na score to predict 12-week mortality for ACLF patients, with the AUROC of 0.817, a sensitivity of 76.5%, and a specificity of 75.9%.

CONCLUSION

The age ≥30 years and HBVDNA ≤1000 copies at admission strongly correlate with occurrence of ACLF, and higher MELD-Na score and relapse after LAM withdrawal are closely related with 12-week mortality among patients with ACLF after NAs withdrawal.

Incidence of infectious complications is associated with a high mortality in patients with hepatitis B virus-related acute-on-chronic liver failure

BACKGROUND

In China, hepatitis B virus-related acute-on-chronic liver failure (HBV-ACLF) is the most common liver failure characterized by serious clinical syndromes of liver decompensation with a very high mortality. Bacterial and/or fungal infections are the most common complications that are associated with high short-term mortality. Bacterial translocation from the intestine, impaired hepatic clearance, and immune paralysis of circulating immune cells are thought to contribute to infectious complications in liver failure. The control of bacterial and fungal infections is the key to improving HBV-ACLF outcomes. Active prevention, early diagnosis, and timely treatment of bacterial and fungal infections are essential for treating HBV-ACLF.

AIM

To investigate the frequency and role of bacterial and fungal infections in patients with HBV-ACLF.

METHODS

Patients with HBV-ACLF hospitalized at Taihe Hospital, Hubei University of Medicine from January 2014 to December 2017 were retrospectively enrolled. Patient-related information was retrieved from the hospital case database, including general information, blood biochemistry, complications, etc. According to the occurrence of secondary infection or not, the patients were divided into an infection group and a non-infection group. The sites, types, and incidences of bacterial and fungal infections and the influence of infections on the prognosis of HBV-ACLF were statistically analyzed. The risk factors for infections were assessed by unconditional logistic regression.

RESULTS

There were 174 cases of HBV-ACLF that met the enrollment criteria, of which 114 (65.52%) were diagnosed with infectious complications. Infections occurred in the abdominal cavity (87 cases), respiratory tract (51 cases), urinary tract (18 cases), and biliary tract (10 cases). Patients with infectious complications had a significantly higher 28-d mortality (70.18%, 80/114) than those without (40.00%, 24/60) (70.18% vs 40.00%, P < 0.05). And patients with infectious complications had a much higher incidence of non-infectious complications (54.39%, 62/114) (54.39% vs 15.00%, P < 0.05), leading to an extremely high 28-d mortality of 88.71% (55/62) (P < 0.05). The grade of liver failure, period of hospital stay ≥ 30 d, age ≥ 45 years, and percentage of neutrophils > 70% were identified as risk factors for infectious complications.

CONCLUSION

The high incidence of infectious complications in patients with HBV-ACLF is associated with severity and deterioration of the disease and may contribute to the extremely high mortality of these patients.