Citations

INTRODUCTION: Cirrhosis is associated with cardiac dysfunction and distinct electrocardiogram (ECG) abnormalities. This study aimed to develop a proof-of-concept deep learning-based artificial intelligence (AI) model that could detect cirrhosis-related signals on ECG and generate an AI-Cirrhosis-ECG (ACE) score that would correlate with disease severity. METHODS: A review of Mayo Clinic's electronic health records identified 5,212 patients with advanced cirrhosis ≥18 years who underwent liver transplantation at the 3 Mayo Clinic transplant centers between 1988 and 2019. The patients were matched by age and sex in a 1:4 ratio to controls without liver disease and then divided into training, validation, and test sets using a 70%-10%-20% split. The primary outcome was the performance of the model in distinguishing patients with cirrhosis from controls using their ECGs. In addition, the association between the ACE score and the severity of patients' liver disease was assessed. RESULTS: The model's area under the curve in the test set was 0.908 with 84.9% sensitivity and 83.2% specificity, and this performance remained consistent after additional matching for medical comorbidities. Significant elevations in the ACE scores were seen with increasing model for end-stage liver disease-sodium score. Longitudinal trends in the ACE scores before and after liver transplantation mirrored the progression and resolution of liver disease. DISCUSSION: The ACE score, a deep learning model, can accurately discriminate ECGs from patients with and without cirrhosis. This novel relationship between AI-enabled ECG analysis and cirrhosis holds promise as the basis for future low-cost tools and applications in the care of patients with liver disease.

AbstractBackgroundThe prognosis of acute kidney disease (AKD), defined as a glomerular filtration rate of <60 ml/min/1.73 m2 or a rise in serum creatinine (sCr) of <50% for <3 months, is not clearly known.AimTo study the prevalence, predictive factors and clinical outcomes in hospitalized cirrhotic patients with AKD.MethodsThe North American Consortium for the Study of End‐Stage Liver Disease prospectively enrolled hospitalized decompensated cirrhotic patients. Patients were separated into those with normal renal function (controls or C), AKD or stage 1 AKI as their worst renal dysfunction per International Club of Ascites definition and compared. Parameters assessed included demographics, laboratory data, haemodynamics, renal and patient outcomes.Results1244 patients with cirrhosis and ascites (C: 704 or 57%; AKD: 176 or 14%; stage 1 AKI: 364 or 29%) with similar demographics were enrolled. AKD patients had similar baseline sCr but higher hospital admission in the previous 6 months, and higher peak sCr, compared to controls, with their peak sCr being lower than that in stage 1 AKI patients (all P < .0001). The in‐hospital and 30‐day survival for AKD patients were intermediary between that for controls and stage 1 AKI patients (96% vs 91% vs 86%, P < .0001). The strongest predictors for AKD development while in hospital were the presence of a second infection (OR: 2.44) and diabetes (OR: 1.53).ConclusionsPatients with AKD had intermediate outcomes between stage 1 AKI and controls. AKD patients, especially those with diabetes and a second infection, need careful monitoring and prompt treatment for AKD to prevent negative outcomes.

In patients with cirrhosis and chronic liver disease, acute-on-chronic liver failure is emerging as a major cause of mortality. These guidelines indicate the preferred approach to the management of patients with acute-on-chronic liver failure and represent the official practice recommendations of the American College of Gastroenterology. The scientific evidence for these guidelines was evaluated using the Grading of Recommendations, Assessment, Development, and Evaluation process. In instances where the evidence was not appropriate for Grading of Recommendations, Assessment, Development, and Evaluation, but there was consensus of significant clinical merit, key concept statements were developed using expert consensus. These guidelines are meant to be broadly applicable and should be viewed as the preferred, but not only, approach to clinical scenarios.

Patients with decompensated cirrhosis, particularly those with acute‐on‐chronic liver failure (ACLF), show profound alterations in plasma metabolomics. The aim of this study was to investigate the effect of treatment with simvastatin and rifaximin on plasma metabolites of patients with decompensated cirrhosis, specifically on compounds characteristic of the ACLF plasma metabolomic profile. Two cohorts of patients were investigated. The first was a descriptive cohort of patients with decompensated cirrhosis (n = 42), with and without ACLF. The second was an intervention cohort from the LIVERHOPE‐SAFETY randomized, double‐blind, placebo‐controlled trial treated with simvastatin 20 mg/day plus rifaximin 1,200 mg/day (n = 12) or matching placebo (n = 13) for 3 months. Plasma samples were analyzed using ultrahigh performance liquid chromatography–tandem mass spectroscopy for plasma metabolomics characterization. ACLF was characterized by intense proteolysis and lipid alterations, specifically in pathways associated with inflammation and mitochondrial dysfunction, such as the tryptophan–kynurenine and carnitine beta‐oxidation pathways. An ACLF‐specific signature was identified. Treatment with simvastatin and rifaximin was associated with changes in 161 of 985 metabolites in comparison to treatment with placebo. A remarkable reduction in levels of metabolites from the tryptophan–kynurenine and carnitine pathways was found. Notably, 18 of the 32 metabolites of the ACLF signature were affected by the treatment. Conclusion: Treatment with simvastatin and rifaximin modulates some of the pathways that appear to be key in ACLF development. This study unveils some of the mechanisms involved in the effects of treatment with simvastatin and rifaximin in decompensated cirrhosis and sets the stage for the use of metabolomics to investigate new targeted therapies in cirrhosis to prevent ACLF development.

INTRODUCTION: Several scoring systems predict mortality in alcohol-associated hepatitis (AH), including the Maddrey discriminant function (mDF) and model for end-stage liver disease (MELD) score developed in the United States, Glasgow alcoholic hepatitis score in the United Kingdom, and age, bilirubin, international normalized ratio, and creatinine score in Spain. To date, no global studies have examined the utility of these scores, nor has the MELD-sodium been evaluated for outcome prediction in AH. In this study, we assessed the accuracy of different scores to predict short-term mortality in AH and investigated additional factors to improve mortality prediction. METHODS: Patients admitted to hospital with a definite or probable AH were recruited by 85 tertiary centers in 11 countries and across 3 continents. Baseline demographic and laboratory variables were obtained. The primary outcome was all-cause mortality at 28 and 90 days. RESULTS: In total, 3,101 patients were eligible for inclusion. After exclusions (n = 520), 2,581 patients were enrolled (74.4% male, median age 48 years, interquartile range 40.9–55.0 years). The median MELD score was 23.5 (interquartile range 20.5–27.8). Mortality at 28 and 90 days was 20% and 30.9%, respectively. The area under the receiver operating characteristic curve for 28-day mortality ranged from 0.776 for MELD-sodium to 0.701 for mDF, and for 90-day mortality, it ranged from 0.773 for MELD to 0.709 for mDF. The area under the receiver operating characteristic curve for mDF to predict death was significantly lower than all other scores. Age added to MELD obtained only a small improvement of AUC. DISCUSSION: These results suggest that the mDF score should no longer be used to assess AH's prognosis. The MELD score has the best performance in predicting short-term mortality.

AbstractWhether tubular injury develops in patients with acute kidney injury owing to hepatorenal syndrome (AKI‐HRS) is controversial. We performed repeated measurements of biomarkers of tubular injury during a 14‐day period in 60 patients with cirrhosis and AKI (34 with AKI‐HRS meeting the classical definition of type 1 HRS and 26 with AKI owing to acute tubular necrosis, AKI‐ATN). Nineteen of 34 patients had resolution of AKI‐HRS, while the remainder had persistent AKI‐HRS. The persistence of AKI‐HRS was associated with remarkably high short‐term mortality. There were no significant differences in urinary NGAL or IL‐18 between patients with resolution vs those with persistent AKI‐HRS throughout the 14‐day period. By contrast, biomarker levels were significantly lower in AKI‐HRS, even if persistent, compared to AKI‐ATN. These findings are highly suggestive of lack of significant tubular injury in AKI‐HRS and could be of value in the clinical decision between combined liver–kidney or liver transplantation alone in patients with cirrhosis and AKI candidates to transplantation.