TumorTwin: a Python framework for patient-specific digital twins in oncology
7 affiliations
- 1Oden Institute for Computational Engineering and Sciences, The University of Texas at Austin, Austin, TX, USA. [email protected]
- 2Oden Institute for Computational Engineering and Sciences, The University of Texas at Austin, Austin, TX, USA
- 3Texas Advanced Computing Center, The University of Texas at Austin, Austin, TX, USA
- 4Department of Biomedical Engineering, The University of Texas at Austin, Austin, TX, USA
- 5Department of Diagnostic Medicine, The University of Texas at Austin, Austin, TX, USA
- 6Department of Imaging Physics, MD Anderson Cancer Center, Houston, TX, USA
- 7UT Austin Cancer Research Center, The University of Texas at Austin, Austin, TX, USA
Abstract
BACKGROUND: Advances in the theory and methods of computational oncology have enabled accurate characterization and prediction of tumor growth and treatment response on a patient-specific basis. This capability can be integrated into a digital twin framework in which bi-directional data-flow between the physical tumor and the digital tumor facilitate dynamic model re-calibration, uncertainty quantification, and clinical decision-support via recommendation of optimal therapeutic interventions. However, many digital twin frameworks rely on bespoke implementations tailored to each disease site, modeling choice, and algorithmic implementation. FINDINGS: We present TumorTwin, a modular software framework for initializing, updating, and leveraging patient-specific cancer tumor digital twins. TumorTwin is publicly available as a Python package, with associated documentation, datasets, and tutorials. Novel contributions include the development of a patient-data structure adaptable to different disease sites, a modular architecture to enable the composition of different data, model, solver, and optimization objects, and CPU- or GPU-parallelized implementations of forward model solves and gradient computations. We demonstrate the functionality of TumorTwin via an in silico dataset of high-grade glioma growth and response to radiation therapy. CONCLUSIONS: The TumorTwin framework enables rapid prototyping and testing of image-guided oncology digital twins. This allows researchers to systematically investigate different models, algorithms, disease sites, or treatment decisions while leveraging robust numerical and computational infrastructure.
Related
- Healthy Participant Versus Patient Selection for Clinical Pharmacology Studies in Small-Molecule Oncology Drug Development.
- Evidence-to-Decision (E2D): Structuring Action-Specific Evidence for Early-Phase Oncology Development
- Development and preliminary validation of a patient-report experience measure of acute oncology: The PREMAC study
- KESurv: A Kernel Ensemble Method for Patient-Specific Survival Prediction
- Comparison of the Cox Proportional Hazards Model and Random Survival Forest Algorithm for Predicting Patient‐Specific Survival Probabilities in Clinical Trial Data
BibTeX
@article{kapteyn2026tumortwin,
title = {{TumorTwin: a Python framework for patient-specific digital twins in oncology}},
author = {Michael G. Kapteyn and Anirban Chaudhuri and Ernesto A. B. F. Lima and Graham Pash and Rafael Bravo and Karen E. Willcox and Thomas E. Yankeelov and David A. Hormuth},
journal = {BMC Medical Informatics and Decision Making},
year = {2026},
month = may,
doi = {10.1186/s12911-026-03520-2},
url = {https://doi.org/10.1186/s12911-026-03520-2},
note = {CC BY},
}
RIS
TY - JOUR
TI - TumorTwin: a Python framework for patient-specific digital twins in oncology
AU - Michael G. Kapteyn
AU - Anirban Chaudhuri
AU - Ernesto A. B. F. Lima
AU - Graham Pash
AU - Rafael Bravo
AU - Karen E. Willcox
AU - Thomas E. Yankeelov
AU - David A. Hormuth
PY - 2026
DA - 2026/05/11
JO - BMC Medical Informatics and Decision Making
DO - 10.1186/s12911-026-03520-2
UR - https://doi.org/10.1186/s12911-026-03520-2
AB - BACKGROUND: Advances in the theory and methods of computational oncology have enabled accurate characterization and prediction of tumor growth and treatment response on a patient-specific basis. This capability can be integrated into a digital twin framework in which bi-directional data-flow between the physical tumor and the digital tumor facilitate dynamic model re-calibration, uncertainty quantification, and clinical decision-support via recommendation of optimal therapeutic interventions. However, many digital twin frameworks rely on bespoke implementations tailored to each disease site, modeling choice, and algorithmic implementation. FINDINGS: We present TumorTwin, a modular software framework for initializing, updating, and leveraging patient-specific cancer tumor digital twins. TumorTwin is publicly available as a Python package, with associated documentation, datasets, and tutorials. Novel contributions include the development of a patient-data structure adaptable to different disease sites, a modular architecture to enable the composition of different data, model, solver, and optimization objects, and CPU- or GPU-parallelized implementations of forward model solves and gradient computations. We demonstrate the functionality of TumorTwin via an in silico dataset of high-grade glioma growth and response to radiation therapy. CONCLUSIONS: The TumorTwin framework enables rapid prototyping and testing of image-guided oncology digital twins. This allows researchers to systematically investigate different models, algorithms, disease sites, or treatment decisions while leveraging robust numerical and computational infrastructure.
SN - 1472-6947
ER -