Truace
Subscribe

Machine learning-based discrimination of metabolic dysfunction-associated steatotic liver disease: implications of tryptophan metabolites as potential biomarkers

Objectives Early screening of individuals at high risk of metabolic dysfunction-associated steatotic liver disease (MASLD) facilitates timely intervention and may reduce the risk of progression to cirrhosis. This study aimed to develop a reliable and clinically practical model for MASLD discrimination. Methods A total of 179 individuals were recruited, including 80 healthy controls and 99 MASLD patients. Non-targeted and targeted metabolomics were performed to identify and validate candidate biomarkers associate…

By the Truvace desk1 min read1 sourcePeer-reviewedTRV-2026-1223· cite & verify
Machine learning-based discrimination of metabolic dysfunction-associated steatotic liver disease: implications of tryptophan metabolites as potential biomarkers
"Cat health check, blood sample tubes" is licensed under CC BY 4.0. To view a copy of this license, visit https://creativecommons.org/licenses/by/4.0/.

In brief

In a 179-person study of 80 healthy controls and 99 MASLD patients published September 2026, investigators used non-targeted and targeted metabolomics to identify dysregulated tryptophan metabolites and trained seven machine learning classifiers for MASLD discrimination, selecting a Random Forest model that combines kynurenine, neopterin and five routine labs.

The approach matters because early identification of high-risk MASLD could enable timely intervention to reduce progression to cirrhosis, but the reported excellent performance is from a small internal cohort and the authors frame the tool as promising and requiring further validation and mechanistic work.

Main points

  1. Study recruited 179 individuals including 80 healthy controls and 99 MASLD patients.
  2. Non-targeted metabolomics identified tryptophan metabolism as the most significantly enriched pathway in MASLD.
  3. Targeted metabolomics verified serum tryptophan metabolites were significantly dysregulated between groups.
  4. Final model used kynurenine, neopterin, triglyceride, high-density lipoprotein cholesterol, uric acid, alanine aminotransferase, and glucose.

The gain

A Random Forest model combining two tryptophan metabolites (kynurenine and neopterin) with five routine clinical tests discriminated MASLD from healthy controls with high diagnostic performance.

The rundown

Researchers performed non-targeted metabolomics to find enriched pathways, then targeted metabolomics to validate tryptophan metabolites, and built seven machine learning algorithms assessed by accuracy, sensitivity, specificity and AUC with Shapley Additive Explanations for interpretation.

The selected Random Forest model integrated kynurenine and neopterin with triglyceride, HDL cholesterol, uric acid, ALT and glucose, achieving AUC 0.926-0.972 across evaluations in the 179-person cohort.

Sources

  1. Peer-reviewedClinica Chimica Acta2026-09-27

The debate