Interpretable machine learning for thyroid cancer recurrence predicton: Leveraging XGBoost and SHAP analysis
Our XGBoost model, supported by SHAP analysis empowers clinicians with interpretable insights and defined risk thresholds and could facilitate informed decision-making and patient-centric care.
Authors
- Thomas Wendler (ORCID: https://orcid.org/0000-0002-0915-0510)
- Ralph A. Bundschuh (ORCID: https://orcid.org/0000-0001-7291-9372)
- Johannes Tran‐Gia (ORCID: https://orcid.org/0000-0001-9552-7750)
- Elisabeth Pfaehler (ORCID: https://orcid.org/0000-0002-6160-3011)
- Christina Berr (ORCID: https://orcid.org/0000-0003-2307-1728)
- Andreas Schindele (ORCID: https://orcid.org/0009-0003-8738-7622)
- Olivia Kertels (ORCID: https://orcid.org/0000-0001-7144-1901)
- Anne Krebold
- Katharina Nimptsch (ORCID: https://orcid.org/0000-0001-7877-205X)
- Constantin Lapa (ORCID: https://orcid.org/0000-0001-7536-2207)
- Christian H. Pfob (ORCID: https://orcid.org/0000-0003-2989-5883)
- Ursula Heiß
Institutions
- Technische Hochschule Augsburg (DE)
- University of Augsburg (DE)
- University Hospital Augsburg (DE)
- TUM Klinikum (DE)
- Universitätsklinikum Würzburg (DE)
- Technical University of Munich (DE)
Publication Details
- Journal
- European Journal of Radiology
- Published
- 2025-03-14
- DOI
- https://doi.org/10.1016/j.ejrad.2025.112049
- Citations
- 30
- Primary Topic
- Biomedical Text Mining and Ontologies
- Type
- article
- Field-Weighted Citation Impact
- 24.18