AI Science Tracker
EN

Learned MRI markers associate with subtle cognitive decline

University of Geneva; Geneva University Hospitals; Technical University of Munich; Jena University Hospital; University of Freiburg · 29 Apr 2022 · medicine

Discovery

Learned MRI markers associate with subtle cognitive decline

Source check: Source checked. Not independent scientific confirmation.

Finding: Previously trained support-vector and relevance-vector models generated Alzheimer-like atrophy and brain-age scores in 80 cognitively intact older adults followed for 4.5 years. Scores were associated with decline in specific visuospatial or executive tests, rather than global cognition. No participant developed mild cognitive impairment; the small selected cohort does not establish dementia prediction or clinical utility.

Technology: Support-vector machine; relevance-vector regression; AD-RAI; BrainAGE

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

AI contribution
Models trained on separate MRI cohorts quantify Alzheimer-like atrophy and age-related structural patterns, enabling associations with subsequently recorded domain-specific cognitive change.
Test and result
Independent pretrained MRI scores related to longitudinal neuropsychological changes, with observational regression comparisons in 80 participants.
Limitation / still unknown
Dementia conversion, independent prognostic replication and clinical utility remain unestablished; multiple domain tests and the healthy, educated cohort limit interpretation.
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/PMC9668758/

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 relevant model Methods, Results and limitations; exact primary identity and current primary PubMed correction/retraction relationships 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.