An artificial intelligence-generated model predicts 90-day survival in alcohol-associated hepatitis: A global cohort study.

BACKGROUND AIMS: Alcohol-associated hepatitis (AH) poses significant short-term mortality. Existing prognostic models lack precision for 90-day mortality. Utilizing artificial intelligence (AI) in a global cohort, we sought to derive and validate an enhanced prognostic model. APPROACH AND RESULTS: The Global AlcHep initiative, a retrospective study across 23 centers in 12 countries, enrolled AH patients per NIAAA criteria. Centers were partitioned into derivation (11 centers, 860 patients) and validation cohorts (12 centers, 859 patients). Focusing on 30 and 90-day post-admission mortality, three AI algorithms (Random Forest, Gradient Boosting Machines, and eXtreme Gradient Boosting) informed an ensemble model, subsequently refined via Bayesian updating, integrating the derivation cohort's average 90-day mortality with each center's approximate mortality rate to produce post-test probabilities. The ALCoholic Hepatitis Artificial INtelligence (ALCHAIN) Ensemble score integrated age, gender, cirrhosis, and 9 laboratory values, with center-specific mortality rates. Mortality was 18.7% (30-day) and 27.9% (90-day) in the derivation cohort, versus 21.7% and 32.5% in the validation cohort. Validation cohort 30 and 90-day AUCs were 0.811 (0.779 - 0.844) and 0.799 (0.769 - 0.830), significantly surpassing legacy models like Maddrey's Discriminant Function, MELD variations, ABIC, Glasgow, and modified Glasgow Scores (p<0.001). ALCHAIN Ensemble score also showcased superior calibration against MELD and its variants. Steroid use improved 30-day survival for those with an ALCHAIN Ensemble score>0.20 in both derivation and validation cohorts. CONCLUSIONS: Harnessing AI within a global consortium, we pioneered a scoring system excelling over traditional models for 30 and 90-day AH mortality predictions. Beneficial for clinical trials, steroid therapy, and transplant indications, it's accessible at: https://aihepatology.shinyapps.io/ALCHAIN/.

Review article: Current indications and selection criteria for early liver transplantation in severe alcohol-associated hepatitis.

BACKGROUND: Alcohol-associated hepatitis (AH) is a severe inflammatory form of alcohol-associated liver disease (ALD) that carries a high mortality rate. Early liver transplantation for severe AH is increasingly available. However, specific criteria for referral and selection remain a subject of debate. AIMS: To provide a narrative review of the natural history, diagnostic criteria and indications for referral for early liver transplantation for severe AH. METHODS: We searched PubMed for articles published through August 2023. Key search terms were 'alcoholic hepatitis,' 'alcohol-associated hepatitis,' 'abstinence,' 'alcohol relapse,' and 'liver transplantation.' RESULTS: Previously, a six-month period of alcohol abstinence was required before patients with ALD were considered for liver transplantation. However, studies in recent years have demonstrated that, among carefully selected patients, patients who received early transplants have much higher survival rates than patients with similarly severe disease who did not undergo transplants (77% vs. 23%). Despite these successes, early liver transplantation remains controversial, as these patients have typically not undergone treatment for alcohol use disorder, with the ensuing risk of returning to alcohol use. CONCLUSIONS: While early liver transplantation for AH has survival benefits, many patients would not have received treatment for alcohol use disorder. An integrated approach to evaluating candidacy for early liver transplantation is needed.

Association between public health policies on alcohol and worldwide cancer, liver disease and cardiovascular disease outcomes.

BACKGROUND & AIMS: The long-term impact of alcohol-related public health policies (PHPs) on disease burden is unclear. We aimed to assess the association between alcohol-related PHPs and alcohol-related health consequences. METHODS: We conducted an ecological multi-national study including 169 countries. We collected data on alcohol-related PHPs from the WHO Global Information System of Alcohol and Health 2010. Data on alcohol-related health consequences between 2010-2019 were obtained from the Global Burden of Disease database. We classified PHPs into five items, including criteria for low, moderate, and strong PHP establishment. We estimated an alcohol preparedness index (API) using multiple correspondence analysis (0 lowest and 100 highest establishment). We estimated an incidence rate ratio (IRR) for outcomes according to API using adjusted multilevel generalized linear models with a Poisson family distribution. RESULTS: The median API in the 169 countries was 54 [IQR 34.9-76.8]. The API was inversely associated with alcohol use disorder (AUD) prevalence (IRR 0.13; 95% CI 0.03-0.60; p = 0.010), alcohol-associated liver disease (ALD) mortality (IRR 0.14; 95% CI 0.03-0.79; p = 0.025), mortality due to neoplasms (IRR 0.09; 95% CI 0.02-0.40; p = 0.002), alcohol-attributable hepatocellular carcinoma (HCC) (IRR 0.13; 95% CI 0.02-0.65; p = 0.014), and cardiovascular diseases (IRR 0.09; 95% CI 0.02-0.41; p = 0.002). The highest associations were observed in the Americas, Africa, and Europe. These associations became stronger over time, and AUD prevalence was significantly lower after 2 years, while ALD mortality and alcohol-attributable HCC incidence decreased after 4 and 8 years from baseline API assessment, respectively (p <0.05). CONCLUSIONS: The API is a valuable instrument to quantify the robustness of alcohol-related PHP establishment. Lower AUD prevalence and lower mortality related to ALD, neoplasms, alcohol-attributable HCC, and cardiovascular diseases were observed in countries with a higher API. Our results encourage the development and strengthening of alcohol-related policies worldwide. IMPACT AND IMPLICATIONS: We first developed an alcohol preparedness index, an instrument to assess the existence of alcohol-related public policies for each country. We then evaluated the long-term association of the country's alcohol preparedness index in 2010 with the burden of chronic liver disease, hepatocellular carcinoma, other neoplasms, and cardiovascular disease. The strengthening of alcohol-related public health policies could impact long-term mortality rates from cardiovascular disease, neoplasms, and liver disease. These conditions are the main contributors to the global burden of disease related to alcohol use. Over time, this association has not only persisted but also grown stronger. Our results expand the preliminary evidence regarding the importance of public health policies in controlling alcohol-related health consequences.