Machine learning algorithms reveal gut microbiota signatures associated with chronic hepatitis B-related hepatic fibrosisOriginal paper
Karen Pendergrass is a microbiome researcher specializing in microbiome-targeted interventions (MBTIs). She systematically analyzes scientific literature to identify microbial patterns, develop hypotheses, and validate interventions. As the founder of the Microbiome Signatures Database, she bridges microbiome research with clinical practice. In 2012, based on her own investigative research, she became the first documented case of FMT for Celiac Disease, four years before the first published case study.
Read MoreWhat was studied?
Researchers examined gut microbiota in patients with chronic hepatitis B (CHB), comparing those with hepatic fibrosis (HF) to those without. The HF group was further split into four severity stages, F1 through F4, based on liver stiffness measurements.
How was it studied?
Stool samples underwent 16S rRNA sequencing, with diversity and LEfSe analysis across groups. Random forest and XGBoost machine learning algorithms, evaluated with Shapley additive explanations, identified key differential taxa alongside clinical indicator correlations.
What did they find?
The genus Dorea emerged as the core differential feature separating HF from non-HF patients, varying significantly across fibrosis stages (P < 0.05). Dorea abundance declined significantly as fibrosis severity increased (P = 0.041). Microbiota composition also correlated with liver function markers including gamma-glutamyl transferase, alkaline phosphatase, total bilirubin, and the AST/ALT ratio.
Why it matters
These findings position Dorea as a potential microbial marker for detecting hepatic fibrosis onset and tracking its progression in CHB patients. The results support a role for gut microbiota in the pathophysiology of liver fibrosis.