Tijera, Fatima Higuera‐de la

Background and Aims: Alcohol-associated hepatitis (AH) poses significant short-term mortality. Existing prognostic models lack precision for 90-day mortality. Utilizing artificial intelligence 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 patients with AH per National Institute for Alcohol Abuse and Alcoholism criteria. Centers were partitioned into derivation (11 centers, 860 patients) and validation cohorts (12 centers, 859 patients). Focusing on 30 and 90-day postadmission mortality, 3 artificial intelligence algorithms (Random Forest, Gradient Boosting Machines, and eXtreme Gradient Boosting) informed an ensemble model, subsequently refined through Bayesian updating, integrating the derivation cohort’s average 90-day mortality with each center’s approximate mortality rate to produce posttest probabilities. The ALCoholic Hepatitis Artificial INtelligence Ensemble score integrated age, gender, cirrhosis, and 9 laboratory values, with center-specific mortality rates. Mortality was 18.7% (30 d) and 27.9% (90 d) 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, Model for End-Stage Liver Disease variations, age-serum bilirubin-international normalized ratio-serum Creatinine score, Glasgow, and modified Glasgow Scores (p < 0.001). ALCoholic Hepatitis Artificial INtelligence Ensemble score also showcased superior calibration against MELD and its variants. Steroid use improved 30-day survival for those with an ALCoholic Hepatitis Artificial INtelligence Ensemble score > 0.20 in both derivation and validation cohorts. Conclusions: Harnessing artificial intelligence 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/.

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.