AI Science Tracker
EN

Structural MRI learning identifies Alzheimer-like patterns associated with cognition

Shanghai Jiao Tong University; Massachusetts General Hospital · 28 Sep 2021 · medicine

Discovery

Structural MRI learning identifies Alzheimer-like patterns associated with cognition

Source check: Source checked. Not independent scientific confirmation.

Finding: A support-vector classifier learned Alzheimer-like structural patterns after age adjustment and identified 8.8% of an additional Human Connectome Project Aging sample as structurally Alzheimer-like. Those patterns were associated with cognitive differences, with additional biomarker analyses in mild cognitive impairment. These are cross-sectional exploratory associations; they do not establish future Alzheimer conversion, a clinical diagnosis in asymptomatic people or screening benefit.

Technology: Support vector machine; radial-basis kernel

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

AI contribution
An RBF support-vector machine learns weighted, age-adjusted cortical/subcortical patterns and assigns Alzheimer-like structural scores.
Test and result
Age-detrended structural MRI classification, additional-cohort cognitive associations and MCI biomarker comparisons.
Limitation / still unknown
Longitudinal disease conversion, independent clinical screening performance and patient benefit remain unestablished; development-stage feature weighting can inflate internal classification.
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/PMC8559490/

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 Methods/results/limitations, exact primary front identity and current primary PubMed notice metadata; version dates distinguished..

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.