Clinic-radiomics model using liver magnetic resonance imaging helps predict chronicity of drug-induced liver injury.

BACKGROUND AND AIMS: Some drug-induced liver injury (DILI) cases may become chronic, even after drug withdrawal. Radiomics can predict liver disease progression. We established and validated a predictive model incorporating the clinical characteristics and radiomics features for predicting chronic DILI. METHODS: One hundred sixty-eight DILI patients who underwent liver gadolinium-diethylenetriamine pentaacetate-enhanced magnetic resonance imaging were recruited. The patients were clinically diagnosed using the Roussel Uclaf causality assessment method. Patients who progressed to chronicity or recovery were randomly divided into the training (70%) and validation (30%) cohorts, respectively. Hepatic T1-weighted images were segmented to extract 1672 radiomics features. Least absolute shrinkage and selection operator regression was used for feature selection, and Rad-score was constructed using support vector machines. Multivariable logistic regression analysis was performed to build a clinic-radiomics model incorporating clinical characteristics and Rad-scores. The clinic-radiomics model was evaluated for its discrimination, calibration, and clinical usefulness in the independent validation set. RESULTS: Of 1672 radiomics features, 28 were selected to develop the Rad-score. Cholestatic/mixed patterns and Rad-score were independent risk factors of chronic DILI. The clinic-radiomics model, including the Rad-score and injury patterns, distinguished chronic from recovered DILI patients in the training (area under the receiver operating characteristic curve [AUROC]: 0.89, 95% confidence interval [95% CI]: 0.87-0.92) and validation (AUROC: 0.88, 95% CI: 0.83-0.91) cohorts with good calibration and great clinical utility. CONCLUSION: The clinic-radiomics model yielded sufficient accuracy for predicting chronic DILI, providing a practical and non-invasive tool for managing DILI patients.

qHBsAg for the Identification of Liver Histological Abnormalities in HBeAg-Negative Chronic Hepatitis B Patients with Normal and Mildly Elevated ALT Levels.

Backgrounds: Noninvasive detection of histological abnormalities remains challenging in patients with HBeAg-negative chronic HBV infection with normal or mildly elevated levels of alanine aminotransferase (ALT). This study aimed to assess the utility of serum quantitative hepatitis B surface antigen (qHBsAg) in identifying significant histological lesions in this population. Methods: This is a single-center study with retrospective analysis of 392 treatment-naive patients of HBeAg-negative chronic HBV infection with normal or mildly elevated levels of ALT. Results: In this cohort, significant necroinflammation and fibrosis were found in 69.4% and 61.5% of patients, respectively. Patients with qHBsAg >1000 IU/mL (N = 236) had more hepatic inflammation of ≥G2 (75.4% vs. 60.9%, P < 0.01) or fibrosis ≥ S2 (66.1% vs. 54.5%, P < 0.05) compared to those without (N = 156). Serum HBsAg (cutoff point = 1000 IU/mL), aspartate aminotransferase (AST) level (cutoff point = 25 IU/L), age (cutoff point = 40 years), and HBV family history were identified as independent predictors of significant histological abnormalities in multivariate logistic analysis. Conclusions: A significantly higher proportion of patients with histological abnormalities were found in patients with qHBsAg >1000 IU/mL than those without. The qHBsAg level together with age, AST, and family history of HBV infection could be used as an algorithm to help noninvasive patient selection for antiviral therapy.

Alteration of Bile Acids and Omega-6 PUFAs Are Correlated With the Progression and Prognosis of Drug-Induced Liver Injury.

Background & Aims: Drug-induced liver injury (DILI) is one of the leading causes of liver failure with some of the patients progressed to chronic DILI. The mechanisms underlying the severity and chronicity of DILI are poorly elucidated and the biomarkers are limited. Metabolites and gut microbiota played a crucial role in the development of various liver diseases. Herein, a systematic analysis of serum metabolites and gut microbiota was performed in DILI patients, aiming to identify metabolites correlated with the progression and clinical prognosis of DILI. Methods: Various serum metabolites were quantitated using a metabolite array technology in this prospective study. Gut microbiome compositions and the expression profiles of liver genes were determined in patients with DILI and healthy controls. Results: Metabolomic analysis revealed that bile acids (BAs) and polyunsaturated fatty acids (PUFAs) were closely related to DILI severity and chronicity respectively. The ratios of serum primary/secondary BAs and omega-6/omega-3 PUFAs were elevated in DILI patients. A model established by adrenic acid (AdA) and aspartic acid (Asp) exerts good performance for predicting the chronicity of DLIL. Hepatic transcriptome revealed enhanced expression of PUFA peroxidation and supressed expression of BA synthesis related genes in DILI patients. In addition, Lactic acid bacteria and BA converting bacteria were increased in gut of DILI patients. Besides, elevated serum malondialdehyde (MDA) and fibroblast growth factor 19 (FGF19) was observed in DILI patients. Conclusion: BAs and PUFAs could be potent markers for the severity and chronicity of DILI respectively. The panel of AdA and Asp could be ideal predictive model for the risk of chronicity at the acute stage of DILI. Gut microbiota might act as a negative feedback mechanism to maintain the homeostasis of BAs and PUFAs via FGF19 signalling and PUFA saturation, respectively. Our study revealed novel biomarkers for severe and chronic DILI and provided new therapeutic targets for DILI.