An artificial intelligence-generated model predicts 90-day survival in alcohol-associated hepatitis: A global cohort study
Winston Dunn, Yanming Li, Ashwani K. Singal, Douglas A. Simonetto, Luis Antonio Díaz, Francisco Idalsoaga, Gustavo Ayares, Jorge Arnold, María Ayala-Valverde, Diego Pérez, Jaime Gomez, Rodrigo Escarate, Eduardo Fuentes–López, Carolina Ramírez, Dalia Morales‐Arráez, Wei Zhang, Steve Qian, Joseph Ahn, Seth Buryska, Heer Mehta, Nicholas Dunn, Muhammad Waleed, Horia Ştefănescu, Andreea Bumbu, Adelina Horhat, Bashar Attar, Rohit Agrawal, Joaquín Cabezas, Victor Echavaría, Berta Cuyàs, María Poca, Germán Soriano, Shiv Kumar Sarin, Rakhi Maiwall, Prasun K. Jalal, Fatima Higuera‐de la Tijera, Anand V. Kulkarni, Padaki Nagaraja Rao, Patricia Guerra-Salazar, Ľubomír Skladaný, Natália Kubánek, Verónica Prado, Ana Clemente, Diego Rincón, Tehseen Haider, Kristina R. Chacko, Gustavo Romero, Florencia Pollarsky, Juan Carlos Restrepo, Luis Toro, Pamela Yaquich, Manuel Mendizábal, María Laura Garrido, Sebastián Marciano, Melisa Dirchwolf, Vı́ctor Vargas, César Jiménez, David Hudson, Guadalupe García–Tsao, Guillermo Ortiz, Juan G. Abraldeṣ, Patrick S. Kamath, Marco Arrese, Vijay H. Shah, Ramón Bataller, Juan Pablo Arab
Abstract
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/ .