Scientists at Austria’s University of Graz have used mathematical image processing to create a digital twin of a human heart


Scientists at Austria’s University of Graz have developed a computer model which can pre-simulate the optimal therapy for cardiovascular disease, dramatically improving treatment.

The researchers at the university’s BioTechMed-Graz Research Cooperation used diagnostic data from MRI, ECG and other heart examinations of the patient. Using this data, imaging algorithms created a digital image of the patient’s heart. This customized model  provides a wealth of information that helps to understand the individual clinical picture and to run through various therapeutic scenarios.

Thomas Pock, researcher at the Institute of Biophysics at the Medical University of Graz, explained: “To simulate such a heartbeat in a computer, you have to calculate millions of variables. This requires complex mathematical procedures, special algorithms and special hardware that can perform billions of computing actions per second.”

The developed method is so sophisticated and automated that anatomically correct digital twins of patient hearts can already be routinely produced in a clinical setting. In the next step, the researchers want to further improve the technology and enable fully automatic adjustment of all functional aspects of the heartbeat. “This requires further efforts in basic research, especially in those areas of machine learning and artificial intelligence that allow a high degree of personalization,” said Pock.

Further development is based on the latest AI methods for optimal control and focuses on the wave propagation in the heart, which is controlled by the alignment of the heart muscle fibers. The research team wants to implement this approach in cooperation with the Cardiocentro Ticinio (center for computer-assisted cardiology, Lugano, Switzerland) in a new research project and try to incorporate the control elements into the model using machine learning techniques in such a way that the simulated heartbeat comes as close as possible to the real heartbeat.

The first clinical validation studies are in preparation for 2021 in cooperation with Daniel Scherr from the Division of Cardiology at the Medical University of Graz.

The research team predict that clinically usable prototypes of a fully automated digital twin heart can be tested as early as 2022. The simulation technology on which the method is based is already being distributed by the Graz-based start-up NumeriCor and is used by leading medical technology companies in the R&D sector.