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.

Outcomes following renal transplantation in patients with chronic hepatitis C based on severity of fibrosis on pre-transplant liver biopsy.

Data regarding long-term outcomes following renal transplantation in patients with hepatitis C virus (HCV) infection have been controversial. Our aim was to determine whether there is a difference in outcomes between patients with HCV and more advanced fibrosis on pretransplant biopsy and those with minimal or no fibrosis. Patients were divided according to the severity of fibrosis and their outcomes (including acute rejection, chronic rejection, re-initiation of dialysis, progression of liver disease and mortality) were compared. Thirty-one patients with minimal or no fibrosis (Scheuer stages 0 and 1: Group-A) and 10 patients with more advanced fibrosis (Scheuer stages 2 and 3: Group-B) were included in the final data analysis. Acute rejection occurred in 29% (9/31) of the patients with minimal and 30% (3/10) of the patients with advanced fibrosis (P = 0.95), while chronic allograft nephropathy occurred in 6.5% (2/31) of the patients without and 50% (5/10) of the patients with fibrosis (P = 0.006). None of the patients without fibrosis required re-initiation of dialysis compared with 50% (5/10) of the patients with fibrosis (P <0.05). Median graft survival was 46 months and 18 months for patients with minimal and advanced fibrosis, respectively. There were four deaths among patients with advanced and three deaths among patients with minimal fibrosis (P = 0.04). Our data suggests that patients with chronic HCV and more advanced fibrosis on liver biopsy who undergo a renal transplant have a higher incidence of chronic rejection, graft failure and mortality following renal transplant compared with those with minimal fibrosis.

Impact of pretransplant antinuclear antibody and antismooth muscle antibody titers on disease recurrence and graft survival following liver transplantation in autoimmune hepatitis patients.

BACKGROUND AND AIMS: Disease recurrence following transplantation occurs in 20-45% of patients with autoimmune hepatitis (AIH). Factors associated with an increased risk of recurrence include human leukocyte antigen (HLA) DR3 and HLA DR4 positivity, inadequate immunosuppression, and severity of inflammation in the native liver. Titers of several autoantibodies can be elevated in patients with AIH, including antinuclear antibody (ANA) and antismooth muscle antibody (SMA); however, it is unclear whether or not the degree of elevation influences the risk of disease recurrence following transplantation. METHODS: We conducted a retrospective study to evaluate the potential impact of pretransplant titers on post-transplant outcomes for patients with AIH. Sixty-three patients with AIH who underwent 72 liver transplants between 1 January 1989 and 1 January 2009 were included, with a median follow up of 10 months. Patients were divided into group A (ANA or SMA ≥ 1:160) and group B (titers ≤ 1:160). RESULTS: There was no significant difference in the recurrence rates or death between patients in groups A and B, respectively. Only race appeared to impact outcomes, with African American patients having a higher incidence of death and recurrent disease post-transplant compared to other ethnicities. CONCLUSIONS: Based on our findings, pretransplant ANA and SMA levels do not appear to impact recurrence rates or outcomes following liver transplantation for AIH.

Assessment of the PHQ-9 as a screening tool for depression in patients with chronic hepatitis C.

BACKGROUND AND OBJECTIVES: We examined the test characteristics of the PHQ-9, a new screening tool that has been validated in the general population but not amongst patients with hepatitis C virus (HCV). METHODS: The PHQ-9, CES-D and BDI-II questionnaires were administered to 129 consecutive patients with chronic HCV attending a specialty clinic between August 2005 and April 2006. RESULTS: Approximately 52% of participants reported symptoms suggesting depression. Prevalence of depression was 62% using the BDI-II, 75% per the PHQ-9 and 72% per the CES-D. We observed a strong correlation between the BDI-II, CES-D and PHQ-9 in patients on and off interferon. Scores on the three questionnaires were only moderately associated with symptoms reported by the patients. There was moderate agreement between the CES-D and BDI-II and slight agreement between both these questionnaires and the PHQ-9. Scores on the PHQ-9 correlated strongly with scores on the CES-D and BDI-II and moderately with patients' symptoms.

Hepatic encephalopathy: a review of its pathophysiology and treatment.

Hepatic encephalopathy (HE) is a broad spectrum of neuropsychiatric manifestations usually affecting individuals with end-stage liver disease. The presence of HE is a poor prognostic sign, with 1-year mortality rates of almost 60%. There is much debate about the underlying mechanisms that result in this syndrome; however, elevated plasma and central nervous system ammonia levels are considered key factors in its pathogenesis. Initial evaluation of the patient presenting with overt HE should include a careful search for predisposing factors, including underlying infection, gastrointestinal (GI) bleeding, electrolyte disturbances, hepatocellular carcinoma, dehydration, hypotension, and excessive use of benzodiazepines, psychoactive drugs, or alcohol. The mainstay of treatment for many years has been nonabsorbable disaccharides, particularly lactulose. Alternative treatments, which usually are second line in patients who do not respond to lactulose, include zinc, antibiotics (neomycin, metronidazole, and rifaximin), ornithine aspartate, sodium benzoate, probiotics, and surgical intervention. Accepted treatments for HE are associated with significant unpleasant side effects, including diarrhea, renal failure, neuropathy, and other GI disturbance. Newer therapies are still in development, and most are awaiting human trials in order to confirm their benefit. These include manganese chelators, L-carnitine, N-methyl-d-aspartate receptor antagonists, blood purification dialysis system, and an intravenous combination of sodium benzoate and phenylacetate.