BSWiMS Models: Predicting Alzheimer's Progression from MCI with Multi-Source Data

Data from 564 participants in the ADNI study who transitioned from mild cognitive impairment to Alzheimer's disease. The dataset includes 330 features from quantitative MRI, cognitive assessments, CSF biomarkers, and APOE 4 status, analyzed using Cox survival models. It was authored by Diana Sofia Rosales-Gurmendi and last updated on April 30, 2026.

Use Cases

• Training survival analysis models based on 330 multi-source features to predict time-to-conversion from MCI to AD.
• Evaluating feature importance for clinical prediction based on cognitive scores, CSF, and qMRI biomarkers mentioned in the description.
• Developing interpretable Cox models for early risk identification based on the integration of cognitive, genetic, and imaging data.

Strengths

• Includes data from 564 participants in the ADNI study.
• Contains 330 features from four distinct data sources (qMRI, cognitive, CSF, APOE 4).
• The associated model achieved a reported specificity of 0.87, 95% CI [0.83, 0.90].

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 very small at 5.5 KB, indicating limited scope.

Provenance

Source

ADNI (Alzheimer's Disease Neuroimaging Initiative) study.

Collection Method

Clinical study data analyzed with machine learning methods.

Freshness

Last updated 2026-04-30 17:37:19; freshness should be verified.