AI Science Tracker
EN

Structural MRI shows weak psychiatric prediction in 6,916 children

Ludwig Maximilian University of Munich · 28 Jun 2023 · medicine

Discovery

Structural MRI shows weak psychiatric prediction in 6,916 children

Source check: Source checked. Not independent scientific confirmation.

Finding: Gradient-boosted classifier chains tested structural-MRI patterns for ten psychiatric outcomes in 6,916 children from ABCD. After accounting for sociodemographic confounding and diagnostic interdependence, ADHD and bipolar outcomes were predicted above chance, with AUROCs of 0.567 and 0.551. These small effects did not support clinical use. The observational study does not establish causal neuroanatomy or reliable individual diagnosis.

Technology: Gradient-boosted classifier chains

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

AI contribution
Gradient-boosted ensembles and classifier chains combine brain measures and disorder interdependencies after confound adjustment.
Test and result
Cross-validated classification and permutation tests in an existing multicentre child cohort.
Limitation / still unknown
Clinical diagnostic utility, causal mechanisms and transportability beyond the evaluated population 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/PMC10694548/

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 relevant model Methods, study Results and limitations; exact primary front-matter identity and Europe PMC metadata 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 2/5 · Validation 2/5 · 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.