Systematic review of machine learning models in predicting the risk of bleed/grade of esophageal varices in patients with liver cirrhosis: A comprehensive methodological analysis.

Esophageal varices (EV) in liver cirrhosis carry high mortality risks. Traditional endoscopy, which is costly and subjective, prompts a shift towards machine learning (ML). This review critically evaluates ML applications in predicting bleeding risks and grading EV in patients with liver cirrhosis. Following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, we conducted a systematic review of studies using ML to predict the risk of variceal bleeding and/or grade EV in liver disease patients. Data extraction and bias assessment followed the CHARMS (CHecklist for critical Appraisal and data extraction for systematic Reviews of prediction Modeling Studies) checklist and PROBAST (Prediction model Risk Of Bias Assessment Tool) tool, respectively. Due to the heterogeneity of the study, a meta-analysis was not feasible; instead, descriptive statistics summarized the findings. Twelve studies were included, highlighting the use of various ML models such as extreme gradient boosting, artificial neural networks, and convolutional neural networks. These studies demonstrated high predictive accuracy, with some models achieving area under the curve values above 99%. However, significant heterogeneity was noted in input variables, methodologies, and outcome measures. Moreover, a substantial portion of the studies exhibited unclear or high risk of bias, mainly due to insufficient participant numbers, unclear handling of missing data, and a lack of detailed reporting on endoscopic procedures. ML models show significant promise in predicting the risk of variceal bleeding and grading EV in patients with cirrhosis, potentially reducing the need for invasive procedures. Nonetheless, the current literature reveals considerable heterogeneity and methodological limitations, including high or unclear risks of bias. Future research should focus on larger, prospective trials and the standardization of ML assessment criteria to confirm these models' practical utility in clinical settings.

The Efficacy of Albumin Dialysis in the Treatment of Severe Cholestatic Drug-Induced Liver Injury.

Drug-induced liver injury (DILI) is a significant cause of acute liver injury and can present as cholestatic injury with or without associated hepatitis. Although most patients with DILI recover with supportive care, some can develop severe refractory cholestasis that impairs recovery of hepatic function, with subsequent progression to acute or chronic liver failure. Current pharmacotherapy and extracorporeal therapies such as hemodialysis have limited benefit. Albumin dialysis is an emerging strategy in the extracorporeal treatment of intoxications caused by protein bound drugs and can be used for the removal of albumin bound bilirubin and bile acids. CASES SERIES: We describe the efficacy of albumin dialysis with the molecular adsorbent recirculating system (MARS) in the successful treatment of five patients with severe cholestatic DILI that was refractory to standard medical therapy. All patients had a sustained improvement in serum bilirubin levels after completing MARS therapy, with a complete resolution of their liver injury. DISCUSSION: Our case series demonstrates that albumin dialysis could provide an important treatment strategy in the setting of severe refractory cholestatic DILI and be considered as a novel therapeutic option in specific cases of drug hepatotoxicity in which the causative agent has high protein binding characteristics.

Use of the Molecular Adsorbent Recirculating System in Acute Liver Failure: Results of a Multicenter Propensity Score-Matched Study.

OBJECTIVES: The molecular adsorbent recirculating system removes water-soluble and albumin-bound toxins and may be beneficial for acute liver failure patients. We compared the rates of 21-day transplant-free survival in acute liver failure patients receiving molecular adsorbent recirculating system therapy and patients receiving standard medical therapy. DESIGN: Propensity score-matched retrospective cohort analysis. SETTING: Tertiary North American liver transplant centers. PATIENTS: Acute liver failure patients receiving molecular adsorbent recirculating system at three transplantation centers (n = 104; January 2009-2019) and controls from the U.S. Acute Liver Failure Study Group registry. INTERVENTIONS: Molecular adsorbent recirculating system treatment versus standard medical therapy (control). MEASUREMENTS AND MAIN RESULTS: One-hundred four molecular adsorbent recirculating system patients were propensity score-matched (4:1) to 416 controls. Using multivariable conditional logistic regression adjusting for acute liver failure etiology (acetaminophen: n = 248; vs nonacetaminophen: n = 272), age, vasopressor support, international normalized ratio, King's College Criteria, and propensity score (main model), molecular adsorbent recirculating system was significantly associated with increased 21-day transplant-free survival (odds ratio, 1.90; 95% CI, 1.07-3.39; p = 0.030). This association remained significant in several sensitivity analyses, including adjustment for acute liver failure etiology and propensity score alone ("model 2"; molecular adsorbent recirculating system odds ratio, 1.86; 95% CI, 1.05-3.31; p = 0.033), and further adjustment of the "main model" for mechanical ventilation, and grade 3/4 hepatic encephalopathy ("model 3"; molecular adsorbent recirculating system odds ratio, 1.91; 95% CI, 1.07-3.41; p = 0.029). In acetaminophen-acute liver failure (n = 51), molecular adsorbent recirculating system was associated with significant improvements (post vs pre) in mean arterial pressure (92.0 vs 78.0 mm Hg), creatinine (77.0 vs 128.2 µmol/L), lactate (2.3 vs 4.3 mmol/L), and ammonia (98.0 vs 136.0 µmol/L; p ≤ 0.002 for all). In nonacetaminophen acute liver failure (n = 53), molecular adsorbent recirculating system was associated with significant improvements in bilirubin (205.2 vs 251.4 µmol/L), creatinine (83.1 vs 133.5 µmol/L), and ammonia (111.5 vs 140.0 µmol/L; p ≤ 0.022 for all). CONCLUSIONS: Treatment with molecular adsorbent recirculating system is associated with increased 21-day transplant-free survival in acute liver failure and improves biochemical variables and hemodynamics, particularly in acetaminophen-acute liver failure.

Colonoscopy procedural volume increases adenoma and polyp detection rates in gastroenterologytrainees.

AIM: To investigate changes in polyp detection throughout fellowship training, and estimate colonoscopy volume required to achieve the adenoma detection rate (ADRs) and polyp detection rate (PDRs) of attending gastroenterologists. METHODS: We reviewed colonoscopies from July 1, 2009 to June 30, 2014. Fellows' procedural logs were used to retrieve colonoscopy procedural volumes, and these were treated as the time variable. Findings from screening colonoscopies were used to calculate colonoscopy outcomes for each fellow for the prior 50 colonoscopies at each time point. ADR and PDR were plotted against colonoscopy procedural volumes to produce individual longitudinal graphs. Repeated measures linear mixed effects models were used to study the change of ADR and PDR with increasing procedural volume. RESULTS: During the study period, 12 fellows completed full three years of training and were included in the analysis. The average ADR and PDR were, respectively, 31.5% and 41.9% for all fellows, and 28.9% and 38.2% for attendings alone. There was a statistically significant increase in ADR with increasing procedural volume (1.8%/100 colonoscopies, P = 0.002). Similarly, PDR increased 2.8%/100 colonoscopies (P = 0.0001), while there was no significant change in advanced ADR (0.04%/100 colonoscopies, P = 0.92). The ADR increase was limited to the right side of the colon, while the PDR increased in both the right and left colon. The adenoma per colon and polyp per colon also increased throughout training. Fellows reached the attendings' ADR and PDR after 265 and 292 colonoscopies, respectively. CONCLUSION: We found that the ADR and PDR increase with increasing colonoscopy volume throughout fellowship. Our findings support recent recommendations of ≥ 275 colonoscopies for colonoscopy credentialing.

Mesenteric Ischemia.

Acute mesenteric ischemia (AMI) is a rare disease that most commonly affects the elderly. The vague symptoms often lead to delayed diagnosis and consequent high mortality. Physical exam and laboratory findings lack the sensitivity and specificity to exclude AMI, but computed tomography angiography can rapidly and accurately confirm the diagnosis. Survival improves with prompt restoration of perfusion and resection of nonviable bowel. Advances in imaging, operative techniques, and critical care have led to a steady decline in overall mortality; however, long-term survival is limited because of the comorbidities in this patient group.