MSP-Tracker

(Multiple Sclerosis Progression-tracker)

---

Setting up the environment

To create and activate the environment.

conda env create -f environment.yml
conda activate websmsreg

To export the conda environment to Jupyter Notebook.

python -m ipykernel install --user --name=websmsreg

---

Data preprocessing and creating data splits

The data can be collected from Swedish MS REGistry (SMSREG). The data shall be kept in a designated folder. The path to the data can be provided in the notebook (data_cleaning_and_splitting.ipynb) under the input section.

Training

Code for training and evaluation of both the model and conformal prediction is given in notebook (random_forest_cp.ipynb)

MSP-Tracker - Take me to the website

The model and scripts used for the website model are available in the folder gradio.
To run the website locally, activate the conda environment and run

python3 gradio/app.py

Citation

Please cite:

Sreenivasan, A.P., Vaivade, A., Noui, Y. et al. Conformal prediction enables disease course prediction and
allows individualized diagnostic uncertainty in multiple sclerosis. npj Digit. Med. 8, 224 (2025).
https://doi.org/10.1038/s41746-025-01616-z