Motor evoked potentials for multiple sclerosis: A multiyear follow-up dataset.

Jan Yperman 76dca8459e Various tweaks to the notebook text hace 3 años
LICENSE fc835d36a9 Initial commit hace 3 años
README.md 1f10ee5086 Added information on the time series. hace 3 años
apen_cache.p 813f4c2f30 Added cache for the ApEn computation hace 3 años
create_df_from_portable_dataset.py 76f90a1058 Added sample use case notebook; Added code to convert to pandas dataframes. hace 3 años
mep_dataset.zip 8de7561f3a Added the MEP dataset hace 3 años
sample_use_case.ipynb 76dca8459e Various tweaks to the notebook text hace 3 años

README.md

Motor evoked potentials for multiple sclerosis: A multiyear follow-up dataset.

Introduction

This dataset contains Motor Evoked Potential measurements, performed on Multiple Sclerosis patients. The dataset descriptor can be found at: [TODO]().

Usage

Structure

The dataset itself is stored in mep_dataset.zip. The general structures is as follows:

  • patient.csv: Contains the records for the various patients.
  • visit.csv: Contains the records for the various visits.
  • test.csv: Contains the records for the various tests.
  • measurement.csv: Contains the records for the various measurements.
  • edss.csv: Contains the records for the various edss measurements.

Besides these files the dataset also contains textfiles for each of the actual time series. The filenames of these files contain a unique identifier which can be used to link back to the column "timeseries" in the measurement.csv file. Some code to automate this linking (in Python) is included in create_df_from_portable_dataset.py.

More details about specifics fields can be found in the dataset descriptor.

Getting started

It is highly recommended to have a look at the included jupyter notebook to familiarize oneself with the dataset. It includes a sample use case and goes over how to work with the dataset.

To run the jupyter notebook a few Python packages are required:

  • Pandas
  • Numpy
  • Matplotlib
  • Scipy
  • Scikit-learn
  • Tqdm
  • Jupyter

For example in anaconda this could be achieved using:

conda create --name mep python=3 pandas numpy matplotlib scipy scikit-learn tqdm jupyter

which creates an environment called "mep" that contains the required packages.