Home > About >
> The Potential of Digital Twin Technology - From Individualized Healthcare to Aerospace Design
Computational model of human heart. Credit: Greg Foss (TACC)
The Potential of Digital Twin Technology - From Individualized Healthcare to Aerospace Design
Members of the Oden Institute for Computational Engineering and Sciences at UT Austin have collaborated with researchers from King’s College of London, The Alan Turing Institute, and the University of Cambridge to discuss the potential for digital twin technology as a powerful simulation technology tool.
Digital twins are a virtual version of real-life objects that can be used to predict how that object will perform. The authors discuss how digital twin technology can benefit two contrasting applications: the aerospace industry and simulations of the heart. In the aerospace industry, for example, it is used for monitoring and adaptation of drones in changing conditions without human interaction. When applied to the heart, a digital twin could predict how the state of a patient’s diseased heart will develop and how diverse patients are likely to respond to different therapies.
Although the possibilities are promising, current digital twins are largely the result of bespoke technical solutions that are difficult to scale. The paper’s authors say that these use cases place new demands on the speeds, robustness, validation, verification, and uncertainty quantification in digital twin creation workflows.
Lead author Professor Steven Niederer from the School of Biomedical Engineering & Imaging Sciences, King’s College London said in medicine, the digital twin will allow testing of a large number of therapies on a patient to identify the best option for that individual with their unique disease. “There is a need to invest in the underlying theory for how to make models, how to run these models at speed and how to combine multiple models together to ensure that they run as expected,” he said.
Further investment is needed to develop the mathematics of creating digital twins from patient data, measuring uncertainty in patient data, and accounting for uncertainty in the model in predictions.
One challenge in the health care realm is determining “how we get better at predicting how the heart will operate under extreme conditions,” says Niederer. “We often want to predict when the heart will fail, however, we only have information that is obtained from them under normal operating procedures.”
“The Digital Twin represents a new paradigm in the modeling and simulation of the heart for both basic and clinical translational goals,” said Michael Sacks.
“Unlike traditional modeling wherein we develop a ‘static’ version of the state of the heart, a cardiac digital twin is continuously updated with patient and population data. It can then be used in near real-time simulations to detect and predict functional anomalies for improved patient diagnosis and treatment. The ongoing challenges that remain include large-scale human data integration, including dealing with regulatory and privacy issues, and major advancements in the development of near real time cardiac simulations.”