Liver transplantation in patients with non-alcoholic steatohepatitis and alcohol-related liver disease: the dust is yet to settle

Machine learning approaches to enhance diagnosis and staging of patients with MASLD using routinely available clinical information

AIMS

Metabolic dysfunction Associated Steatotic Liver Disease (MASLD) outcomes such as MASH (metabolic dysfunction associated steatohepatitis), fibrosis and cirrhosis are ordinarily determined by resource-intensive and invasive biopsies. We aim to show that routine clinical tests offer sufficient information to predict these endpoints.

METHODS

Using the LITMUS Metacohort derived from the European NAFLD Registry, the largest MASLD dataset in Europe, we create three combinations of features which vary in degree of procurement including a 19-variable feature set that are attained through a routine clinical appointment or blood test. This data was used to train predictive models using supervised machine learning (ML) algorithm XGBoost, alongside missing imputation technique MICE and class balancing algorithm SMOTE. Shapley Additive exPlanations (SHAP) were added to determine relative importance for each clinical variable.

RESULTS

Analysing nine biopsy-derived MASLD outcomes of cohort size ranging between 5385 and 6673 subjects, we were able to predict individuals at training set AUCs ranging from 0.719-0.994, including classifying individuals who are At-Risk MASH at an AUC = 0.899. Using two further feature combinations of 26-variables and 35-variables, which included composite scores known to be good indicators for MASLD endpoints and advanced specialist tests, we found predictive performance did not sufficiently improve. We are also able to present local and global explanations for each ML model, offering clinicians interpretability without the expense of worsening predictive performance.

CONCLUSIONS

This study developed a series of ML models of accuracy ranging from 71.9-99.4% using only easily extractable and readily available information in predicting MASLD outcomes which are usually determined through highly invasive means.

Antibody against apolipoprotein-A1, non-alcoholic fatty liver disease and cardiovascular risk: a translational study

BACKGROUND

Non-alcoholic fatty liver disease (NAFLD) is a common liver disease increasing cardiovascular disease (CVD) morbidity and mortality. Autoantibodies against apolipoprotein A-1 (AAA-1) are a possible novel CVD risk factor promoting inflammation and disrupting cellular lipid homeostasis, two prominent pathogenic features of NAFLD. We explored the role of AAA-1 in NAFLD and their association with CVD risk.

METHODS

HepaRG cells and liver sections from ApoE-/- mice exposed to AAA-1 were used for lipid quantification and conditional protein expression. Randomly selected sera from 312 subjects of the Prevention of Renal and Vascular End-stage Disease (PREVEND) general population cohort were used to measure AAA-1. A Fatty Liver Index (FLI) ≥ 60 and a 10-year Framingham Risk Score (FRS) ≥ 20% were used as proxy of NAFLD and high CVD risk, respectively.

RESULTS

In-vitro and mouse models showed that AAA-1 increased triglyceride synthesis leading to steatosis, and promoted inflammation and hepatocyte injury. In the 112 PREVEND participants with FLI ≥ 60, AAA-1 were associated with higher FRS, alkaline phosphatase levels, lower HDL cholesterol and tended to display higher FLI values. Univariate linear and logistic regression analyses (LRA) confirmed significant associations between AAA-1, FLI and FRS ≥ 20%, while in adjusted LRA, FLI was the sole independent predictor of FRS ≥ 20% (OR: 1.05, 95%CI 1.01-1.09, P = 0.003). AAA-1 was not an independent FLI predictor.

CONCLUSIONS

AAA-1 induce a NAFLD-compatible phenotype in vitro and in mice. Intricate associations exist between AAA-1, CVD risk and FLI in the general population. Further work is required to refine the role of AAA-1 in NAFLD and to determine if the AAA-1 association with CVD is affected by hepatic steatosis.

Collagen matrix scaffolds: Future perspectives for the management of chronic liver diseases

Approximately 1.5 billion chronic liver disease (CLD) cases have been estimated worldwide, encompassing a wide range of liver damage severities. Moreover, liver disease causes approximately 1.75 million deaths per year. CLD is typically characterized by the silent and progressive deterioration of liver parenchyma due to an incessant inflammatory process, cell death, over deposition of extracellular matrix proteins, and dysregulated regeneration. Overall, these processes impair the correct function of this vital organ. Cirrhosis and liver cancer are the main complications of CLD, which accounts for 3.5% of all deaths worldwide. Liver transplantation is the optimal therapeutic option for advanced liver damage. The liver is one of the most common organs transplanted; however, only 10% of liver transplants are successful. In this context, regenerative medicine has made significant progress in the design of biomaterials, such as collagen matrix scaffolds, to address the limitations of organ transplantation (e.g., low donation rates and biocompatibility). Thus, it remains crucial to continue with experimental and clinical studies to validate the use of collagen matrix scaffolds in liver disease.