AI Science Tracker
EN

Machine learning identifies a candidate NEC expression signature with experimental checks

Soochow University · 28 May 2026 · medicine

Discovery

Machine learning identifies a candidate NEC expression signature with experimental checks

Source check: Source checked. Not independent scientific confirmation.

Finding: RF+XGBoost screening identified SLC26A3, CCL20 and CXCL5 as a candidate expression signature for neonatal necrotizing enterocolitis, with retrospective expression validation and new mouse and cell-model expression checks. The study used 46 training and 24 test samples; the reported 0.979 AUC is training performance, with 0.917 and 0.957 in two small test cohorts. Geneformer and virtual-knockout analyses generated regulatory hypotheses; causality, protein-level diagnostic performance and clinical benefit remain unestablished.

Technology: Random forest; XGBoost; Geneformer

Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.

AI contribution
RF+XGBoost screening links expression data to three NEC candidate genes; 46 training and24 independent retrospective test samples.
Test and result
Mouse and cell-model expression checks corroborated candidate-gene directions; diagnostic evaluation used retrospective human datasets.
Limitation / still unknown
Clinical diagnostic utility, causal regulatory interactions and treatment efficacy remain unestablished.
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/PMC13240151/

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: 21 Nov 2026. Review scope: Primary full paper Methods, Results and limitations plus Europe PMC bibliographic metadata;reviewed 2026-11-21..

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 2/5 · Validation 3/5 · Novelty 2/5. 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.