RESUMO
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/ .
RESUMO
INTRODUCTION: Crohn's disease and ulcerative colitis are characterized by chronic inflammation of the gastrointestinal tract. Mucosal healing (MH) is a therapeutic goal in patients with inflammatory bowel disease (IBD). Current data suggest that Black patients may experience worse clinical outcomes than White patients with IBD. This study assessed MH between Black and White patients with IBD. METHODS: Retrospective analysis was performed on Black and White adults with IBD who were hospitalized for an active flare. The presence of MH was assessed at 6-18 months after hospitalization. IBD treatments received before and during hospitalization, within 6 months, and 6-18 months after discharge were recorded. C-reactive protein (CRP) levels were collected at hospitalization and 6-18 months after discharge; the difference was reported as delta CRP. RESULTS: One hundred nine patients were followed up after hospitalization. Of those 88 (80.7%) were White patients, and 21 (19.3%) were Black patients. White and Black patients received similar proportions of IBD treatment before ( P = 0.2) and during ( P = 0.6) hospitalization, within 6 months ( P = 0.1), and 6-18 months ( P = 0.1) after discharge. Black patients achieved numerically higher rates of MH (15/21 = 71.4% vs 53/88 = 60.2%, P = 0.3) and delta CRP ( P = 0.2) than White patients, however, not statistically significant. DISCUSSION: In patients admitted to the hospital with an IBD flare with similar treatment and care, there was a trend toward higher rates of MH in Black patients compared with White patients. These data suggest that MH is likely not the only factor that is associated with Black patients experiencing worse clinical outcomes when compared with White patients.
RESUMO
BACKGROUND AND AIMS: Patients with alcohol use disorder (AUD) can develop alcohol-associated fatty liver disease (AFLD). However, the impact of AFLD on outcomes remains unclear. We studied the impact of AFLD on readmission, 30-day mortality, and overall mortality in patients admitted with AUD. METHODS: Hospitalized patients with AUD between 2011 and 2019 at a tertiary medical center were retrospectively evaluated. Our population included patients with AUD with AFLD: AST and ALT elevation and serum bilirubin <3â mg/dl. Patients with AUD without evidence of liver disease served as control and were labeled as no ALD. Patients with alcohol-associated cirrhosis (AC) and alcohol-associated hepatitis (AH) were included for comparison. Kaplan-Meier survival analysis and multivariable regression for predictors of mortality and survival were performed. RESULTS: There were 7522 patients of which 32.44% were female with mean age of 51.86â ±â 14.41 years. Patient distribution included no ALD (nâ =â 3775), AFLD (nâ =â 2192), AC (nâ =â 1017) and AH (nâ =â 538) groups. Compared to no ALD group, AFLD group was associated with significantly higher 30-day mortality [4.43% vs. 1.56%, hazard ratio (HR): 2.84; P â <â 0.001], overall mortality [15.97% vs. 12.69%, HR 1.40, P â <â 0.001], and 30-day readmission [21.85% vs. 18.49%, odds ratio: 1.21; P â <â 0.01]. CONCLUSION: We demonstrated that AFLD is not a benign entity and poses significant mortality risk. Our results suggest that AFLD may be under-recognized and highlight the need for focused management and close follow-up after discharge.