A cancer patient’s “digital twin” would be the ideal resource for personalized treatment, and creating the technology stands as a grand challenge for the convergence of advanced computing technologies and oncology.
A digital twin is a computer replica of the systems and processes needed to run simulations without disrupting or harming the real-world object.
On July 6, 30 scientists participated in a five-day virtual Ideas Lab, Toward Building a Cancer Patient “Digital Twin.” The event, held by the NCI-DOE Collaboration, brought together a diverse group of researchers to form new collaborations and create innovative research projects that would advance the development of a cancer patient digital twin.
Over 130 scientists from all career stages applied, representing academic institutions including medical schools, national laboratories, non-profit research institutes, cancer centers and clinical care centers.
“The scientists selected to participate in the Ideas Lab were enthusiastic, motivated, and open to new interactions and feedback,” said Emily Greenspan, PhD, Program Director at the National Cancer Institute, Center for Biomedical Informatics and Information Technology. “They displayed a lot of creativity and outside-the-box thinking for tackling a risky but exciting new area of predictive oncology research.”
What is an ideas lab?
Ideas Labs have been described as “opportunities to build collaborations that would normally take a year or more, in a single week.” Over the course of the week, a small group of scientists with a range of experience and expertise work to deepen their shared understanding of a complex challenge, redefine the problems within the challenge, and generate innovative ideas for research proposals.
Why a digital twin for cancer and why now?
In healthcare, a digital twin would be a real-life replica of the human body able to show outcomes in the present and future. In the future, a cancer patient’s digital twin (aka, avatar or virtual patient) could be used as a holistic computer-based model to enable personalized medicine, support cancer research, pre-clinical development, clinical trials, aid diagnosis and support running treatment simulations.
“Seeing the research community so willingly embrace the path toward creating a cancer patient digital twin is a tremendous step forward,” noted Eric Stahlberg, PhD, director of the Frederick National Laboratory’s Biomedical Informatics and Data Science and a program co-manager of the NCI-DOE collaboration. “The Ideas Lab allowed scientists to bridge across the disciplines of cancer, biology and computing, and envision how a human ‘digital twin’ could provide transformative insights and predictions about multiple, complex interactions that clinicians need to improve treatment for patients.”
Digital twins of the future
Healthcare digital twins of the future will be patient-tailored models that can provide critical information about real patients and in silico clinical trials for biomedical research. Thus, a human cancer patient digital twin will be a tool for doctors and patients to enable determination of specific outcomes, including response to individual treatments.
Aspirational challenges and innovative approaches
During the week-long Ideas Lab, participants formed collaborations based on their interests to determine aspirational cancer challenge research areas and develop novel research projects involving cutting-edge computing. With guidance from six multidisciplinary mentors, project teams explored, probed, challenged and refined their ideas.
On the final day, project teams each presented a short paper describing their multidisciplinary research concept, and mentors provided suggestions for improvement.
Since then, the project teams developed research proposals with a short- and long-term vision and roadmap for the future. Each project focuses on a digital twin component that, within the next two to three years, seeks to advance the development of a model of an individual cancer patient. These projects have the potential to lead to disease- and intervention-specific models and simulations, using mathematical, active learning and ensemble model approaches.
Project participants are now applying for seed funding made possible by the U.S. Department of Energy and NCI, through the Frederick National Laboratory. Awards are expected in January 2021. For more information, visit the Envisioning Computational Innovations for Cancer Challenges Hub Site.