The integration of artificial intelligence (AI) into hepatology is revolutionizing the diagnosis and management of liver diseases amidst a rising global burden of conditions like metabolic-associated steatotic liver disease (MASLD). AI harnesses vast datasets and complex algorithms to enhance clinical decision making and patient outcomes. AI’s applications in hepatology span a variety of conditions, including autoimmune hepatitis, primary biliary cholangitis, primary sclerosing cholangitis, MASLD, hepatitis B, and hepatocellular carcinoma. It enables early detection, predicts disease progression, and supports more precise treatment strategies. Despite its transformative potential, challenges remain, including data integration, algorithm transparency, and computational demands. This review examines the current state of AI in hepatology, exploring its applications, limitations, and the opportunities it presents to enhance liver health and care delivery.

Background/Aims: Self-expanding metallic stents (SEMS) are an alternative to emergency surgery (ES) for malignant colorectal obstruction. This study aimed to compare surgical outcomes between SEMS as a bridge to surgery (BTS) and ES in patients with malignant colorectal obstruction.Methods: A comprehensive database search was conducted until October 2023 to compare outcomes between SEMS as a BTS and ES. A subgroup analysis of results by malignancy site was performed.Results: We analyzed 57 studies, including 7,223 patients over a mean duration of 35.4 months. SEMS as a BTS showed clinical and technical success rates of 88.0% (95% confidence interval [CI], 86.1%–90.1%; I2=68%) and 91.6% (95% CI, 89.7%–93.7%; I2=66%), respectively. SEMS as a BTS revealed reduced postoperative adverse events (odds ratio [OR], 0.51; 95% CI, 0.41–0.63; I2=70%; p<0.001) and 30-day mortality (OR, 0.52; 95% CI, 0.37–0.72; I2=10%; p<0.001) compared to ES. Subgroup analysis showed postoperative mortality of 5% and 1.5% for left- and right-sided malignancies, respectively. Adverse events were 15% and 33% for the right and left colon, respectively.Conclusions: SEMS as a BTS demonstrated a higher success rate, fewer postoperative adverse events, and a reduced 30-day mortality rate than ES, supporting its use as the preferred initial intervention for right- and left-sided obstructions and indicating broader clinical adoption.

Background/Aims: Cold snare polypectomy (CSP) is routinely performed for small colorectal polyps (≤10 mm). However, challenges include insufficient resection depth and immediate bleeding, hindering precise pathological evaluation. We aimed to compare the outcomes of cold endoscopic mucosal resection (CEMR) with that of CSP for colorectal polyps ≤10 mm, using data from randomized controlled trials (RCTs).Methods: Multiple databases were searched in December 2023 for RCTs reporting outcomes of CSP versus CEMR for colorectal polyps ≤10 mm in size. Our primary outcomes were rates of complete and en-bloc resections, while our secondary outcomes were total resection time (seconds) and adverse events, including immediate bleeding, delayed bleeding, and perforation.Results: The complete resection rates did not significantly differ (CSP, 91.8% vs. CEMR 94.6%), nor did the rates of en-bloc resection (CSP, 98.9% vs. CEMR, 98.3%) or incomplete resection (CSP, 6.7% vs. CEMR, 4.8%). Adverse event rates were similarly insignificant in variance. However, CEMR had a notably longer mean resection time (133.51 vs. 91.30 seconds).Conclusions: Our meta-analysis of seven RCTs showed that while both CSP and CEMR are equally safe and effective for resecting small (≤10 mm) colorectal polyps, the latter is associated with a longer resection time.

INTRODUCTION: Despite research efforts, predicting Clostridioides difficile incidence and its outcomes remains challenging. The aim of this systematic review was to evaluate the performance of machine learning (ML) models in predicting C. difficile infection (CDI) incidence and complications using clinical data from electronic health records. METHODS: We conducted a comprehensive search of databases (OVID, Embase, MEDLINE ALL, Web of Science, and Scopus) from inception up to September 2023. Studies employing ML techniques for predicting CDI or its complications were included. The primary outcome was the type and performance of ML models assessed using the area under the receiver operating characteristic curve. RESULTS: Twelve retrospective studies that evaluated CDI incidence and/or outcomes were included. The most commonly used ML models were random forest and gradient boosting. The area under the receiver operating characteristic curve ranged from 0.60 to 0.81 for predicting CDI incidence, 0.59 to 0.80 for recurrence, and 0.64 to 0.88 for predicting complications. Advanced ML models demonstrated similar performance to traditional logistic regression. However, there was notable heterogeneity in defining CDI and the different outcomes, including incidence, recurrence, and complications, and a lack of external validation in most studies. DISCUSSION: ML models show promise in predicting CDI incidence and outcomes. However, the observed heterogeneity in CDI definitions and the lack of real-world validation highlight challenges in clinical implementation. Future research should focus on external validation and the use of standardized definitions across studies.

Hepatocellular carcinoma (HCC), the most common primary liver cancer, remains a leading cause of cancer-related mortality worldwide. Its often-silent progression results in late-stage diagnosis, limiting curative options and necessitating systemic therapy for many patients. The presence of underlying cirrhosis in most cases further complicates treatment decisions. While the approval of sorafenib in 2007 marked a major milestone in systemic therapy for HCC, the treatment landscape has since evolved significantly, particularly with the advent of immune checkpoint inhibitors and anti-angiogenic agents. Combination regimens, such as atezolizumab plus bevacizumab, have demonstrated superior outcomes and are now considered standard first-line options. Despite these advances, efforts to translate insights from HCC’s molecular pathogenesis into personalized treatments have been limited. This narrative review explores the current systemic therapy options for HCC, from first-line to subsequent-line treatments, and highlights emerging strategies, including novel immunotherapies and targeted agents. We emphasize the need for individualized treatment approaches that consider tumor biology, liver function, and performance status, and we outline future directions for research aimed at improving outcomes in this complex and evolving field.