METHODS: We recruited ACLF patients between 2009 and 2020 from APASL-ACLF Research Consortium (AARC). Their clinical data, investigations and organ involvement were serially noted for 90-days and utilized for AI modelling. Data were split randomly into train and validation sets. Multiple AI models, MELD and AARC-Model, were created/optimized on train set. Outcome prediction abilities were evaluated on validation sets through area under the curve (AUC), accuracy, sensitivity, specificity and class precision.

RESULTS: Among 2481 ACLF patients, 1501 in train set and 980 in validation set, the extreme gradient boost-cross-validated model (XGB-CV) demonstrated the highest AUC in train (0.999), validation (0.907) and overall sets (0.976) for predicting 30-day outcomes. The AUC and accuracy of the XGB-CV model (%Δ) were 7.0% and 6.9% higher than the standard day-7 AARC model (p AARC-AI model was developed and validated twice with optimal performance for 30-day predictions.

METHODS: ACLF patients recruited from the APASL-ACLF Research Consortium (AARC) were followed up till 30 days, death or transplantation, whichever earlier. Clinical details, including dynamic grades of HE and laboratory data, including ammonia levels, were serially noted.

RESULTS: Of the 3009 ACLF patients, 1315 (43.7%) had HE at presentation; grades I-II in 981 (74.6%) and grades III-IV in 334 (25.4%) patients. The independent predictors of HE at baseline were higher age, systemic inflammatory response, elevated ammonia levels, serum protein, sepsis and MELD score (p AARC score (≥ 9) and ammonia levels (≥ 85 μmol/L) (p ACLF patients.

METHODS: Patients with AIH-ACLF without baseline infection/hepatic encephalopathy were identified from APASL ACLF research consortium (AARC) database. Diagnosis of AIH-ACLF was based mainly on histology. Those treated with steroids were assessed for non-response (defined as death or liver transplant at 90 days for present study). Laboratory parameters, AARC, and model for end-stage liver disease (MELD) scores were assessed at baseline and day 3 to identify early non-response. Utility of dynamic SURFASA score [- 6.80 + 1.92*(D0-INR) + 1.94*(∆%3-INR) + 1.64*(∆%3-bilirubin)] was also evaluated. The performance of early predictors was compared with changes in MELD score at 2 weeks.

METHODS: Altogether 1021 patients were analyzed for the severity and organ failure at admission to determine transplant eligibility and 28 day survival with or without transplant.

METHODS: Patients with MAFLD-ACLF were recruited from the AARC registry. The diagnosis of MAFLD-ACLF was made when the treating unit had identified the etiology of chronic liver disease (CLD) as MAFLD (or previous nomenclature such as NAFLD, NASH, or NASH-cirrhosis). Patients with coexisting other etiologies of CLD (such as alcohol, HBV, HCV, etc.) were excluded. Data was randomly split into derivation (n=258) and validation (n=111) cohorts at a 70:30 ratio. The primary outcome was 90-day mortality. Only the baseline clinical, laboratory features and severity scores were considered.

RESULTS: The derivation group had 258 patients; 60% were male, with a mean age of 53. Diabetes was noted in 27%, and hypertension in 29%. The dominant precipitants included viral hepatitis (HAV and HEV, 32%), drug-induced injury (DILI, 29%) and sepsis (23%). MELD-Na and AARC scores upon admission averaged 32±6 and 10.4±1.9. At 90 days, 51% survived. Non-viral precipitant, diabetes, bilirubin, INR, and encephalopathy were independent factors influencing mortality. Adding diabetes and precipitant to MELD-Na and AARC scores, the novel MAFLD-MELD-Na score (+12 for diabetes, +12 for non-viral precipitant) and MAFLD-AARC score (+5 for each) were formed. These outperformed the standard scores in both cohorts.