The abstract is read at the publisher; the summary is JClub's.
A multi-kingdom, functional gut microbiota panel distinguishes cholangiocarcinoma from hepatocellular carcinoma with an AUC of 99.74% and a 11.11% false positive rate.
- Why it matters: Gut microbiota links to cholangiocarcinoma are known, but prior work largely focused on bacterial components, leaving non-bacterial members and functional signals unclear.
- What they did: Metagenomic sequencing of 700 fecal samples from China (289 CCA, 312 healthy controls, 99 HCC) quantified multi-kingdom composition and functions, then used machine learning to screen 117 diagnostic schemes and validate across three cohorts.
- The result: The optimal 21-marker model achieved an average AUC of 91% across validation cohorts, pooled sensitivity/specificity of 96.2%/78.5%, and detected 97.6% of CA19-9-negative CCA cases.
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.