RESUMEN
BACKGROUND: The prevalence of Metabolic dysfunction associated fatty liver disease (MAFLD) and its complication, MAFLD-related acute on chronic liver failure (MAFLD-ACLF), is rising. Yet, factors determining patient outcomes in MAFLD-ACLF remain understudied. 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. CONCLUSION: Almost half of MAFLD-ACLF patients die within 90 days. Diabetes and non-viral precipitants such as DILI and sepsis lead to adverse outcomes. The new MAFLD-MELD-Na and MAFLD-AARC scores provide reliable 90-day mortality predictions for MAFLD-ACLF patients.
RESUMEN
BACKGROUND AND AIMS: We hypothesized that artificial intelligence (AI) models are more precise than standard models for predicting outcomes in acute-on-chronic liver failure (ACLF). 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 < .001) and 12.8% and 10.6% higher than the day 7 MELD for 30-day predictions in validation set (p < .001). The XGB model had the highest AUC for 7- and 90-day predictions as well (p < .001). Day-7 creatinine, international normalized ratio (INR), circulatory failure, leucocyte count and day-4 sepsis were top features determining the 30-day outcomes. A simple decision tree incorporating creatinine, INR and circulatory failure was able to classify patients into high (~90%), intermediate (~60%) and low risk (~20%) of mortality. A web-based AARC-AI model was developed and validated twice with optimal performance for 30-day predictions. CONCLUSIONS: The performance of the AARC-AI model exceeds the standard models for outcome predictions in ACLF. An AI-based decision tree can reliably undertake severity-based stratification of patients for timely interventions.
Asunto(s)
Insuficiencia Hepática Crónica Agudizada , Humanos , Insuficiencia Hepática Crónica Agudizada/diagnóstico , Inteligencia Artificial , Creatinina , Pronóstico , Factores de TiempoRESUMEN
BACKGROUND AND AIMS: Limited data exist regarding outcomes of acute variceal bleeding (AVB) in patients with acute-on-chronic liver failure (ACLF), especially in those with hepatic failure. We evaluated the outcomes of AVB in patients with ACLF in a multinational cohort of APASL ACLF Research Consortium (AARC). METHODS: Prospectively maintained data from AARC database on patients with ACLF who developed AVB (ACLF-AVB) was analysed. This data included demographic profile, severity of liver disease, and rebleeding and mortality in 6 weeks. These outcomes were compared with a propensity score matched (PSM) cohort of ACLF matched for severity of liver disease (MELD, AARC score) without AVB (ACLF without AVB). RESULTS: Of the 4434 ACLF patients, the outcomes in ACLF-AVB (n = 72) [mean age-46 ± 10.4 years, 93% males, 66% with alcoholic liver disease, 65% with alcoholic hepatitis, AARC score: 10.1 ± 2.2, MELD score: 34 (IQR: 27-40)] were compared with a PSM cohort selected in a ratio of 1:2 (n = 143) [mean age-44.9 ± 12.5 years, 82.5% males, 48% alcoholic liver disease, 55.7% alcoholic hepatitis, AARC score: 9.4 ± 1.5, MELD score: 32 (IQR: 24-40)] of ACLF-without AVB. Despite PSM, ACLF patients with AVB had a higher baseline HVPG than without AVB (25.00 [IQR: 23.00-28.00] vs. 17.00 [15.00-21.75] mmHg; p = 0.045). The 6-week mortality in ACLF patients with or without AVB was 70.8% and 53.8%, respectively (p = 0.025). The 6-week rebleeding rate was 23% in ACLF-AVB. Presence of ascites [hazard ratio (HR) 2.2 (95% CI 1.03-9.8), p = 0.026], AVB [HR 1.9 (95% CI 1.2-2.5, p = 0.03)], and MELD score [HR 1.7 (95% CI 1.1-2.1), p = 0.001] independently predicted mortality in the overall ACLF cohort. CONCLUSION: Development of AVB confers poor outcomes in patients with ACLF with a high 6-week mortality. Elevated HVPG at baseline represents a potential risk factor for future AVB in ACLF.