Machine learning-assisted clinical decision support prototype for the diagnostic evaluation of telomere biology disorders (TBDs).
MLxTBD is a Streamlit-based application designed to support clinicians during the diagnostic work-up of telomeropathies by integrating clinical and laboratory variables into a supervised machine learning framework.
Massaccesi E, Arcuri L, Cavalca G, et al. Application of machine learning in the diagnostic work-up of telomere biology disorders. Hemasphere. 2026;10(1):e70272. doi:10.1002/hem3.70272
- Interactive Streamlit web interface
- Machine learning-based diagnostic support
- Random Forest classifier backend
- Clinical variable integration
- Probability-based output visualization
- Lightweight deployment
Once all fields have been filled in:
Clone the repository:
git clone https://github.com/Jackcava/MLxTBD.git
cd MLxTBD(recommended) Create a virtual envirnoment:
python -m venv .venv
source .venv/bin/activateInstall dependencies:
pip install -r requirements.txtstreamlit run app/main.pyThe current implementation uses a Random Forest classifier trained on a curated clinical dataset of patients with telomere biology disorders.
The training dataset is not publicly available due to privacy and ethical restrictions.
This repository currently provides the application framework and inference workflow only.
This software is intended for:
- research purposes
- educational purposes
- prototype evaluation
It is not intended for clinical decision-making or medical deployment.
If you use this repository in academic work, please cite:
@article{massaccesi2026mlxtbd,
title={Application of machine learning in the diagnostic work-up of telomere biology disorders},
author={Massaccesi, E and Arcuri, L and Cavalca, G and others},
journal={Hemasphere},
year={2026},
volume={10},
number={1},
pages={e70272},
doi={10.1002/hem3.70272}
}