AI Science Tracker
EN

The First Clinical Medical College

1 discovery from 2026

Discoveries

An interpretable machine learning model for predicting NICU admission in preterm infants: a single-center retrospective cohort study.

Source check: Source checked. Not independent scientific confirmation.

Finding: A machine-learning model using perinatal clinical indicators predicted NICU admission among preterm infants in a retrospective single-center cohort, with internal validation reported.

Technology: Interpretable prenatal machine-learning model

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

AI contribution
Uses prenatal indicators to predict NICU admission; SHAP summarizes model predictor contributions.
Test and result
The retrospective single-center cohort used internal validation. The article reports different AUC values in its conclusion text and later summary (0.861 and 0.904); the catalog claim therefore does not select one inconsistent value.
Limitation / still unknown
The retrospective single-center study does not establish prospective impact or performance at other hospitals.
Evidence sources and annotation context

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

Evidence sources: https://doi.org/10.21037/tp-2026-1-0121 · https://europepmc.org/article/MED/42158711 · https://europepmc.org/articles/PMC13181635 · https://www.ncbi.nlm.nih.gov/research/bionlp/RESTful/pmcoa.cgi/BioC_json/PMC13181635/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: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

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