Comparison with Earlier Efforts: EEG-Based Alzheimer's and MCI Diagnosis

Ashik Mostafa Alvi's dataset, last updated April 20, 2026, compares a proposed diagnostic framework against earlier methods. The research uses electroencephalography (EEG) data to classify subjects as healthy, having mild cognitive impairment (MCI), or Alzheimer's disease (AD). The dataset is small at 9.5 KB and is stored in an XLS file format.

Use Cases

• Benchmarking new diagnostic models against earlier machine learning classifiers based on EEG data.
• Training multiclass classifiers for Alzheimer's disease, MCI, and healthy subjects based on EEG-derived features.
• Analyzing the performance of the Cognitive Decline Recognition Network (CDR-Net) architecture mentioned in the description.
• Investigating cross-validation strategies (10-fold, leave-one-out) for EEG-based medical data.

Strengths

• The proposed CDR-Net model achieved reported multiclass accuracy, sensitivity, and specificity of 99.25%, 99.13%, and 99.32%, respectively.
• Dataset is openly licensed under CC-BY-4.0.
• The description details a complete framework from EEG acquisition to performance assessment.

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 9.5 KB, indicating limited scope.

Provenance

Source

Ashik Mostafa Alvi via figshare

Collection Method

Likely contains results from EEG data preprocessing, feature extraction, and classification using the proposed CDR-Net architecture.

Time Range

null

Freshness

Last updated 2026-04-20 17:58:14; freshness should be verified.

Geography

null