Synthetic EEG Data For Disorder Diagnosis With 39 Features

E2M's Disorders and Diagnosis EEG Dataset V5 contains synthetic EEG data generated by the 'bai' model based on real data. The dataset includes 39 features per record, such as demographic attributes, cognitive scores, and EEG electrode readings. It is designed for analyzing patterns related to disorders like Obsessive Compulsive Disorder and Bipolar Disorder.

Use Cases

• Train a classifier to predict the Disorder/Diagnosis label using EEG_Electrode signals and demographic features like Age and Sex.
• Analyze correlations between cognitive metrics (IQ, EQ) and EEG_Electrode patterns across different Education levels.
• Build a generative model to create synthetic EEG_Electrode time series conditioned on specific Disorder/Diagnosis categories.

Strengths

• Includes 39 features per record, combining demographic, cognitive, and 32-channel EEG_Electrode data.
• Synthetic data generation via the 'bai' model may facilitate research without privacy constraints of real patient data.

Limitations

• Data is synthetic, which may not fully capture the complexity and noise of real-world clinical EEG recordings.
• Key metadata such as the number of rows, temporal coverage, and geographic origin are unknown, limiting reproducibility.

Provenance

Source

E2M on Hugging Face.

Collection Method

Synthetic data generated by the 'bai' model based on real data.

Freshness

Last updated on March 24, 2026.