AI Science Tracker
EN

Machine learning identifies metabolic signatures associated with ER-positive breast-cancer disparities

Division of Nutritional Sciences, University of Illinois Urbana-Champaign, Urbana, IL, USA · 26 Jul 2023 · medicine

Discovery

Machine learning identifies metabolic signatures associated with ER-positive breast-cancer disparities

Source check: Source checked. Not independent scientific confirmation.

Finding: Untargeted plasma metabolomics and feature-selection/classification analyses identified group-associated metabolic signatures in ER-positive breast-cancer cases; selected pathway associations were examined in TCGA data. These observational associations do not establish causal drivers of racial disparities.

Technology: Boruta and recursive feature selection with random-forest classification identified group-associated metabolite signatures for downstream pathway analysis.

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
Feature selection and random-forest classification identified group-associated plasma-metabolite signatures and prioritized pathway analyses.
Test and result
Pretreatment metabolomics from 102 ER-positive breast-cancer cases and 148 controls supported group-associated signatures; selected associations were examined in TCGA cases.
Limitation / still unknown
The retrospective observational analyses do not establish causal mechanisms or explain individual outcomes.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC10372029/

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: linked separately.

Review date: 22 Nov 2026. Review scope: Primary full-text review as recorded in case evidence; record-level claim and attribution review..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open in the full catalog for filters, charts and related discoveries. Browse medicine discoveries.