Search

BackgroundDysregulated bile acid (BA) metabolism has been linked to steatosis, inflammation, and fibrosis in nonalcoholic fatty liver disease (NAFLD).AimTo determine whether circulating BA levels accurately stage liver fibrosis in NAFLD.MethodsWe recruited 550 Chinese adults with biopsy-proven NAFLD and varying levels of fibrosis. Ultra-performance liquid chromatography coupled with tandem mass spectrometry was performed to quantify 38 serum BAs.ResultsCompared to those without fibrosis, patients with mild fibrosis (stage F1) had significantly higher levels of secondary BAs, and increased diastolic blood pressure (DBP), alanine aminotransferase (ALT), body mass index, and waist circumstance (WC). The combination of serum BAs with WC, DBP, ALT, or Homeostatic Model Assessment for Insulin Resistance performed well in identifying mild fibrosis, in men and women, and in those with/without obesity, with AUROCs 0.80, 0.88, 0.75 and 0.78 in the training set (n = 385), and 0.69, 0.80, 0.61 and 0.69 in the testing set (n = 165), respectively. In comparison, the combination of BAs and clinical/biochemical biomarkers performed less well in identifying significant fibrosis (F2-4). In women and in non-obese subjects, AUROCs were 0.75 and 0.71 in the training set, 0.65 and 0.66 in the validation set, respectively. However, these AUROCs were higher than those observed for the fibrosis-4 index, NAFLD fibrosis score, and Hepamet fibrosis score.ConclusionsSecondary BA levels were significantly increased in NAFLD, especially in those with mild fibrosis. The combination of serum BAs and clinical/biochemical biomarkers for identifying mild fibrosis merits further assessment.

Summary: Background: Liver fibrosis is the strongest histological risk factor for liver‐related complications and mortality in metabolic dysfunction‐associated fatty liver disease (MAFLD). Second harmonic generation/two‐photon excitation fluorescence (SHG/TPEF) is a powerful tool for label‐free two‐dimensional and three‐dimensional tissue visualisation that shows promise in liver fibrosis assessment. Aim: To investigate combining multi‐photon microscopy (MPM) and deep learning techniques to develop and validate a new automated quantitative histological classification tool, named AutoFibroNet (Automated Liver Fibrosis Grading Network), for accurately staging liver fibrosis in MAFLD. Methods: AutoFibroNet was developed in a training cohort that consisted of 203 Chinese adults with biopsy‐confirmed MAFLD. Three deep learning models (VGG16, ResNet34, and MobileNet V3) were used to train pre‐processed images and test data sets. Multi‐layer perceptrons were used to fuse data (deep learning features, clinical features, and manual features) to build a joint model. This model was then validated in two further independent cohorts. Results: AutoFibroNet showed good discrimination in the training set. For F0, F1, F2 and F3‐4 fibrosis stages, the area under the receiver operating characteristic curves (AUROC) of AutoFibroNet were 1.00, 0.99, 0.98 and 0.98. The AUROCs of F0, F1, F2 and F3‐4 fibrosis stages for AutoFibroNet in the two validation cohorts were 0.99, 0.83, 0.80 and 0.90 and 1.00, 0.83, 0.80 and 0.94, respectively, showing a good discriminatory ability in different cohorts. Conclusion: AutoFibroNet is an automated quantitative tool that accurately identifies histological stages of liver fibrosis in Chinese individuals with MAFLD. [ABSTRACT FROM AUTHOR]

LINKED CONTENT: This article is linked to Harrison et al paper. To view this article, visit https://doi.org/10.1111/apt.17734 [ABSTRACT FROM AUTHOR]