Search

BACKGROUND Nonalcoholic steatohepatitis (NASH), advanced fibrosis, and subsequent cirrhosis and hepatocellular carcinoma are becoming the most common etiology for liver failure and liver transplantation; however, they can only be diagnosed at these potentially reversible stages with a liver biopsy, which is associated with various complications and high expenses. Knowing the difference between the more benign isolated steatosis and the more severe NASH and cirrhosis informs the physician regarding the need for more aggressive management. OBJECTIVE We intend to explore the feasibility of using machine learning methods for noninvasive diagnosis of NASH and advanced liver fibrosis and compare machine learning methods with existing quantitative risk scores. METHODS We conducted a retrospective analysis of clinical data from a cohort of 492 patients with biopsy-proven nonalcoholic fatty liver disease (NAFLD), NASH, or advanced fibrosis. We systematically compared 5 widely used machine learning algorithms for the prediction of NAFLD, NASH, and fibrosis using 2 variable encoding strategies. Then, we compared the machine learning methods with 3 existing quantitative scores and identified the important features for prediction using the SHapley Additive exPlanations method. RESULTS The best machine learning method, gradient boosting (GB), achieved the best area under the curve scores of 0.9043, 0.8166, and 0.8360 for NAFLD, NASH, and advanced fibrosis, respectively. GB also outperformed 3 existing risk scores for fibrosis. Among the variables, alanine aminotransferase (ALT), triglyceride (TG), and BMI were the important risk factors for the prediction of NAFLD, whereas aspartate transaminase (AST), ALT, and TG were the important variables for the prediction of NASH, and AST, hyperglycemia (A1c), and high-density lipoprotein were the important variables for predicting advanced fibrosis. CONCLUSIONS It is feasible to use machine learning methods for predicting NAFLD, NASH, and advanced fibrosis using routine clinical data, which potentially can be used to better identify patients who still need liver biopsy. Additionally, understanding the relative importance and differences in predictors could lead to improved understanding of the disease process as well as support for identifying novel treatment options.

Patients with primary biliary cholangitis (PBC) often suffer with pruritus. We describe the impact of pruritus on quality of life and how it is managed in a real-world cohort.TARGET-PBC is a longitudinal observational cohort of patients with PBC across the USA. Data include information from medical records for three years prior to the date of consent up to 5 years of follow-up. Enrolled patients were asked to complete patient-reported outcome surveys: PBC-40, 5-D itch, and the PROMIS fatigue survey. Kruskal-Wallis tests were used to compare differences in symptoms between groups.A total of 211 patients with completed PRO surveys were included in the current study. PRO respondents were compared with non-respondents in the TARGET-PBC population and were broadly similar. Pruritus was reported in 170 patients (81%), with those reporting clinically significant pruritus (30%) scoring worse across each domain of the PBC-40 and 5-D itch, more frequently having cirrhosis, and having significantly greater levels of fatigue. Patients reporting clinically significant pruritus were more likely to receive treatment, but 33% had never received treatment (no itch = 43.9%, mild itch = 38.3%).The prevalence of pruritus was high in this population, and those reporting clinically significant pruritus had a higher likelihood of having advanced disease and worse quality of life. However, this study found that pruritus in PBC is under-treated. This may be due in part to ineffectiveness of current treatments, poor tolerance, or the lack of FDA-approved medications for pruritus.