AI Science Tracker
EN

The Gut Resistome Atlas in Preterm Infants Enables Prediction of Necrotizing Enterocolitis Onset.

West China Second University Hospital, Sichuan University; Guangzhou Women and Children’s Medical Center; Zhujiang Hospital, Southern Medical University · 30 Sep 2025 · medicine

Discovery

The Gut Resistome Atlas in Preterm Infants Enables Prediction of Necrotizing Enterocolitis Onset.

Source check: Source checked. Not independent scientific confirmation.

Finding: Machine-learning analysis of preterm-infant gut resistomes identified convergence before necrotizing enterocolitis (NEC) onset. A random-forest model achieved external-cohort AUROC 0.823 versus 0.727 for bacterial-species features; the external evaluation included only nine NEC cases and 16 controls, so this is an early predictive association, not clinical readiness or causation.

Technology: A 500-tree random forest uses gut-resistome features to predict impending NEC.

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

AI contribution
A random-forest model links infant gut resistome profiles to the reported NEC early-warning result.
Test and result
The study reports resistome convergence before NEC onset and external-validation AUROC 0.823, compared with 0.727 for bacterial-species features.
Limitation / still unknown
The external cohort contains 9 NEC cases and 16 controls; the study does not establish causation or clinical readiness.
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/PMC12677589/

Source checked · editorial details

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

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary source full-text Methods and Results; version date and reported validation scope checked..

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.