Published March 2026 | Version v2
Dataset Open

Complexity of Resting Cortical Activity Predicts Neurophysiological Responses to Theta- Burst Stimulation but Fails to Generalize: A Rigorous Machine-Learning Approach

Authors/Creators

  • 1. ROR icon Beth Israel Deaconess Medical Center
  • 2. ROR icon Hebrew SeniorLife
  • 3. ROR icon Massachusetts General Hospital

Description

Preprocessed files (resting-state EEG, motor-evoked potentials and TMS-EEG evoked potentials) for the manuscript of the same title: "Complexity of Resting Cortical Activity Predicts Neurophysiological Responses to Theta- Burst Stimulation but Fails to Generalize: A Rigorous Machine-Learning Approach," to be published on PLOS Computational Biology Journal (doi, coming soon). Uploaded as a single compressed file, which in turn, contains 574 files spanning two independent test-retest cohorts. De-identified in accordance with HIPAA/IRB. For feature store and labels, please refer to version 0.0.1 of this data repository.

Files

Files (33.4 GB)

Name Size Download all
md5:cd4ecd4f5eeed97abed17de71262fb83
33.4 GB Download

Additional details

Software

Repository URL
https://github.com/NoPenguinsLand/TMS-EEG-Machine-Learning-PLOS-CompBio
Programming language
Python
Development Status
Active