AI Science Tracker
EN

University of Salento

1 discovery from 2024

Discoveries

An infant cohort model ranks perinatal features for gastrointestinal outcomes

Source check: Source checked. Not independent scientific confirmation.

Finding: A random-forest analysis of 6,060 infants ranked birth weight, cord-blood pH and maternal age as important features for recorded first-year gastrointestinal-disorder labels. The result describes model importance in one hospital cohort, not causal risk factors or a validated preventive-care tool.

Technology: Random forest

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

AI contribution
A fitted random forest ranks variables by impurity reduction when classifying clinician-assessed colic, regurgitation and constipation outcomes. The learned ranking, not conventional regression alone, enables the represented feature pattern.
Test and result
Outcomes were assessed by a trained pediatrician using RomeIV criteria during first-year follow-up. The source reports a 70:30 split, model comparisons and weighted-average F1 of0.74, without a complete condition-specific independent-validation account.
Limitation / still unknown
Prospective enrollment is distinct from model locking before new outcomes. Preprocessing/feature-selection containment and class resampling details are incomplete. Impurity importance can favor continuous variables and does not establish effect direction or causation. The source alternates between the random-forest classification model and a logistic-regression web tool; no deployed-tool accuracy, prevention benefit or independent cohort confirmation is represented.
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/PMC11743318/ · https://www.ncbi.nlm.nih.gov/research/bionlp/RESTful/pmcoa.cgi/BioC_json/PMC11743318/unicode

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: Official primary BioC original article sections: Participants/outcome reference;ML/preprocessing/feature selection;random-forest ranking Results and model limitations; no laboratory-method validation.

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 1/5 · Validation 2/5 · Novelty 1/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open the interactive profile for the timeline, or browse all organizations and model families.