Background and Aims: We sought to characterise the impact of GLP‐1RA on adverse liver outcomes (ALO) among patients with alcohol‐associated liver disease (ALD) and Type 2 diabetes mellitus (T2DM). Methods: Patients with T2DM newly diagnosed with ALD between 2013 and 2020 were identified using IBM MarketScan database and were categorised by GLP‐1RA exposure. Overlap propensity score weighting (OPSW) followed by Poisson regression models was used to analyse adjusted risk of ALO, a composite endpoint defined by first occurrence of hepatic decompensation (HD), portal hypertension (PH), hepatocellular carcinoma (HCC) or liver transplantation (LT) relative to GLP‐1RA. Results: Among 14 730 patients, most individuals were male ( n = 9752, 66.2%) with median age of 57 (IQR 52–61) years; 2.2% ( n = 317) of patients had GLP‐1RA exposure. Overall, 32.0% ( n = 4717) of patients experienced HD, 15.9% ( n = 2345) had PH, 3.8% ( n = 563) developed HCC, while 2.5% ( n = 374) underwent transplantation. Non‐GLP‐1RA patients had higher incidence of HD (32.2% vs. 22.4%) and HCC (3.9% vs. 0.3%) versus patients taking GLP‐1RA (both p < 0.001); in contrast, there was no difference in incidence of PH (14.5% vs. 16.0%) and LT (1.3% vs. 2.6%) (both p > 0.05). After OPSW, overall incidence of ALO was lower in GLP‐1RA cohort (GLP‐1RA: 12.0%, 95%CI 9.0–16.0 vs. non‐GLP‐1RA: 21.0%, 95%CI 20.0–22.0) with an absolute incidence risk reduction of 9.0% (95%CI 3.0%–15.0%) associated with GLP‐1RA. GLP‐1RA was most strongly associated with lower likelihood of HD with reduced adjusted incidence rate of 0.56 (95%CI 0.36–0.86) relative to non‐GLP‐1RA individuals. Conclusions: GLP‐1RA may have a hepatoprotective impact among patients with ALD and T2DM.

Gallbladder cancer is often associated with poor prognosis, especially when patients experience early recurrence after surgery. Machine learning may improve prediction accuracy by analysing complex non-linear relationships. The aim of this study was to develop and evaluate a machine learning model to predict early recurrence risk after resection of gallbladder cancer. In this cross-sectional study, patients who underwent resection of gallbladder cancer with curative intent between 2001 and 2022 were identified using an international database. Patients were assigned randomly to a development and an evaluation cohort. Four machine learning models were trained to predict early recurrence (within 12 months) and compared using the area under the receiver operating curve (AUC). Among 374 patients, 56 (15.0%) experienced early recurrence; most patients had T1 (51, 13.6%) or T2 (180, 48.1%) disease, and a subset had lymph node metastasis (120, 32.1%). In multivariable Cox analysis, resection margins (HR 2.34, 95% c.i. 1.55 to 3.80; P < 0.001), and greater AJCC T (HR 2.14, 1.41 to 3.25; P < 0.001) and N (HR 1.59, 1.05 to 2.42; P = 0.029) categories were independent predictors of early recurrence. The random forest model demonstrated the highest discrimination in the evaluation cohort (AUC 76.4, 95% c.i. 66.3 to 86.5), compared with XGBoost (AUC 74.4, 53.4 to 85.3), support vector machine (AUC 67.2, 54.4 to 80.0), and logistic regression (AUC 73.1, 60.6 to 85.7), as well as good accuracy after bootstrapping validation (AUC 75.3, 75.0 to 75.6). Patients classified as being at high versus low risk of early recurrence had much worse overall survival (36.1 versus 63.8% respectively; P < 0.001). An easy-to-use calculator was made available (https://catalano-giovanni.shinyapps.io/GallbladderER). Machine learning-based prediction of early recurrence after resection of gallbladder cancer may help stratify patients, as well as help inform postoperative adjuvant therapy and surveillance strategies.

Metabolic Dysfunction-Associated Steatotic Liver Disease (MASLD) has been introduced as a superior term to describe steatosis on a background of metabolic dysregulation and is slated to become the leading cause of HCC worldwide, as the incidence of metabolic comorbidities is increasing. As such, MASLD has evolved into an important public health issue, potentially leading to higher rates of liver mortality and end-stage liver disease. To this end, understanding the association between MASLD and HCC may allow for the identification of better interventions and novel therapeutic strategies. The authors provide a review of current knowledge on HCC development among patients with MASLD, with insights into molecular pathways and current and future therapeutic strategies. MASLD has a strong association with the risk of HCC development, as metabolic comorbidities induce dysregulation in molecular pathways, leading to insulin-resistance, oxidative stress, and chronic inflammation, thus causing progression to cirrhosis and eventually to HCC. Therapeutic strategies focused on reducing diabetes-associated complications, as well as the prevalence of obesity and smoking can improve patient outcomes and reduce HCC incidence. Future studies on the molecular background of metabolic alterations may help devise new therapeutic approaches aiming to improve the current management of MASLD-HCC.

Intrahepatic cholangiocarcinoma (ICC) is a heterogeneous disease characterized by a dismal prognosis. Various attempts have been made to classify ICC subtypes with varying prognoses, but a consensus has yet to be reached. This systematic review aims to gather relevant data on the multi-omics-based ICC classification. The PubMed, Embase, and Cochrane databases were searched for terms related to ICC and multi-omics analysis. Studies that identified multi-omics-derived ICC subtypes and investigated clinicopathological predictors of long-term outcomes were included. Nine studies, which included 910 patients, were considered eligible. Mean 3- and 5-year overall survival were 25.7% and 19.6%, respectively, for the multi-omics subtypes related to poor prognosis, while they were 70.2% and 63.3%, respectively, for the subtypes linked to a better prognosis. Several negative prognostic factors were identified, such as genes’ expression profile promoting inflammation, mutations in the KRAS gene, advanced tumor stage, and elevated levels of oncological markers. The subtype with worse clinicopathological characteristics was associated with worse survival (Ref.: good prognosis subtype; pooled hazard ratio 2.06, 95%CI 1.67–2.53). Several attempts have been made to classify molecular ICC subtypes, but they have yielded heterogeneous results and need a clear clinical definition. More efforts are required to build a comprehensive classification system that includes both molecular and clinical characteristics before implementation in clinical practice to facilitate decision-making and select patients who may benefit the most from comprehensive molecular profiling in the disease’s earlier stages.