TY - JOUR
T1 - An artificial intelligence-generated model predicts 90-day survival in alcohol-associated hepatitis
T2 - A global cohort study
AU - Dunn, Winston
AU - Li, Yanming
AU - Singal, Ashwani K.
AU - Simonetto, Douglas A.
AU - Díaz, Luis A.
AU - Idalsoaga, Francisco
AU - Ayares, Gustavo
AU - Arnold, Jorge
AU - Ayala-Valverde, María
AU - Perez, Diego
AU - Gomez, Jaime
AU - Escarate, Rodrigo
AU - Fuentes-López, Eduardo
AU - Ramirez-Cadiz, Carolina
AU - Morales-Arraez, Dalia
AU - Zhang, Wei
AU - Qian, Steve
AU - Ahn, Joseph C.
AU - Buryska, Seth
AU - Mehta, Heer
AU - Dunn, Nicholas
AU - Waleed, Muhammad
AU - Stefanescu, Horia
AU - Bumbu, Andreea
AU - Horhat, Adelina
AU - Attar, Bashar
AU - Agrawal, Rohit
AU - Cabezas, Joaquín
AU - Echavaría, Victor
AU - Cuyàs, Berta
AU - Poca, Maria
AU - Soriano, German
AU - Sarin, Shiv K.
AU - Maiwall, Rakhi
AU - Jalal, Prasun K.
AU - Higuera-De-La-Tijera, Fátima
AU - Kulkarni, Anand V.
AU - Rao, P. Nagaraja
AU - Guerra-Salazar, Patricia
AU - Skladaný, Lubomir
AU - Kubánek, Natália
AU - Prado, Veronica
AU - Clemente-Sanchez, Ana
AU - Rincon, Diego
AU - Haider, Tehseen
AU - Chacko, Kristina R.
AU - Romero, Gustavo A.
AU - Pollarsky, Florencia D.
AU - Restrepo, Juan C.
AU - Toro, Luis G.
AU - Yaquich, Pamela
AU - Mendizabal, Manuel
AU - Garrido, Maria L.
AU - Marciano, Sebastián
AU - Dirchwolf, Melisa
AU - Vargas, Victor
AU - Jiménez, César
AU - Hudson, David
AU - García-Tsao, Guadalupe
AU - Ortiz, Guillermo
AU - Abraldes, Juan G.
AU - Kamath, Patrick S.
AU - Arrese, Marco
AU - Shah, Vijay H.
AU - Bataller, Ramon
AU - Arab, Juan Pablo
N1 - Publisher Copyright:
Copyright © 2024 American Association for the Study of Liver Diseases.
PY - 2024/11
Y1 - 2024/11
N2 - 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/.
AB - 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/.
UR - http://www.scopus.com/inward/record.url?scp=85198655953&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85198655953&partnerID=8YFLogxK
U2 - 10.1097/HEP.0000000000000883
DO - 10.1097/HEP.0000000000000883
M3 - Article
C2 - 38607809
AN - SCOPUS:85198655953
SN - 0270-9139
VL - 80
SP - 1196
EP - 1211
JO - Hepatology
JF - Hepatology
IS - 5
ER -