Supplementary file 1_Gray matter volume alterations in adolescents with ADHD are associate

27 adolescents with ADHD and 34 typically developing controls were analyzed using structural MRI and voxel-based morphometry. The spatial pattern of gray matter volume changes was correlated with whole-brain gene expression profiles from the Allen Human Brain Atlas. The dataset includes results from three machine learning models, with Random Forest achieving an AUC of 0.871 for diagnostic classification.

Use Cases

• Train diagnostic classifiers for ADHD based on neuroimaging-derived gray matter volume patterns.
• Investigate cell-type-specific gene expression signatures associated with brain structural changes.
• Validate neuroimaging findings by correlating spatial patterns with transcriptomic data from a reference atlas.
• Benchmark machine learning models like Support Vector Machine, Random Forest, and Decision Tree on a clinical neuroimaging task.

Strengths

• Includes results from three distinct machine learning models, with Random Forest achieving an AUC of 0.871.
• Integrates two data modalities: structural MRI from a clinical cohort and transcriptomic data from the Allen Human Brain Atlas.
• Provides cell-type enrichment analysis, linking findings to microglia and neuronal populations.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is 2.8 MB, indicating a relatively small scale of processed results.

Provenance

Source

figshare, author Meng Chen.

Collection Method

Voxel-based morphometry on structural MRI data, integrated with gene expression profiles via partial least squares regression.

Freshness

Last updated 2026-05-29 07:02:04; freshness should be verified.