Skip to main content

CAFCW 113 Digital Twins for Predictive Cancer Care: an HPC-Enabled Community Initiative

By Emily Greenspan1, Carolyn Lauzon2, Amy Gryshuk3, Jonathan Ozik4, Nicholson Collier5, Tanveer Syeda-Mahmood6, Ilya Shmulevich7, Tina Hernandez-Boussard8, Paul Macklin9

1. National Cancer Institute 2. US Department of Energy 3. Lawrence Livermore National Laboratory 4. University of Chicago 5. Argonne National Laboratory 6. IBM Research 7. Institute for Systems Biology 8. Stanford University 9. Indiana University

Download (PDF)

Licensed under

Published on

Abstract

Cancer is a complex multiscale dynamical systems problem with interactions between the tumor and host at the molecular, cellular, tissue, and organism levels. Moreover, treatment occurs within a larger dynamical system that couples clinical care teams, hospital systems, industry, and government policies. For individuals, effective patient-tailored therapeutic guidance and planning will require bridging spatiotemporal scales with modeling from atomistic to organismal levels. At the societal level, improving the patient population’s overall health and quality of life requires understanding how actions by patients, clinicians, researchers, and government agencies impact one another.

Predictive oncology aims to predict and steer each patient’s future disease dynamics, but it cannot be fully realized by any single technology, laboratory, or discipline. It will require a coordinated multidisciplinary, multi-institutional effort with access to sufficient data and computational resources. The past decade has seen tremendous advances in data-rich medical measurements; biological theories of cancer progression, therapeutic response and resistance; artificial intelligence (AI) and deep learning techniques; next-generation high-performance computing; multiscale modeling and simulation; and secure high-speed data infrastructures. The time is ripe to leverage these advances to create digital twins for predictive cancer care: patient-tailored models that can evaluate thousands of potential therapeutic plans, help clinicians understand and choose the plan that best meets the patient’s objectives, benchmark clinical performance, and continuously integrate new data and knowledge to refine treatment plans. This talk will discuss a community-driven initiative to design HPC-enabled digital twins for predictive cancer care, available technologies, barriers that must be overcome, and ongoing opportunities to help translate digital twins to clinical practice.

In 2016, the National Cancer Institute (NCI) and the Department of Energy (DOE) partnered to create Joint Design of Advanced Computing Solutions for Cancer (JDACS4C): a collaboration of multidisciplinary experts in the biological, computational, data, and physical sciences at the NCI, the Frederick National Laboratory for Cancer Research, and four DOE national laboratories. JDACS4C aims to develop, demonstrate, and disseminate advanced computational capabilities that help answer driving scientific questions across molecular, cellular and population scales. These efforts frame forward-looking approaches for integrating and analyzing large, heterogeneous data collections with advanced computational modeling that will accelerate predictive oncology.

In March 2019, the agencies built on JDACS4C’s team science approach to launch the Envisioning Computational Innovations for Cancer Challenges (ECICC) community. A series of ECICC events identified the digital twin initiative as a key opportunity to push the limits of computational approaches to cancer care, compel the development of innovative computational technologies, and bring about new paradigms for care.

Digital twins have great potential to help patients reach their treatment goals. Aggregated data from populations of digital twins could help improve national strategies for cancer screening, prevention, research investment, and structuring healthcare systems. The ECICC community has initiated work to create this national resource, but it can only succeed with expanded contributions by the experimental, computational, and clinical communities. After outlining next steps, we will present opportunities to contribute to and drive the effort.

Cite this work

Researchers should cite this work as follows:

  • Emily Greenspan; Carolyn Lauzon; Amy Gryshuk; Jonathan Ozik; Nicholson Collier; Tanveer Syeda-Mahmood; Ilya Shmulevich; Tina Hernandez-Boussard; Paul Macklin (2019), "CAFCW 113 Digital Twins for Predictive Cancer Care: an HPC-Enabled Community Initiative," https://ncihub.org/resources/2296.

    BibTex | EndNote

Tags