Medical Digital Twin
Now more than ever digital twin has become a buzz word. At CMIV there has been a research platform named Medical Digital Twin since early 2019. In the movement towards precision medicine, it has become more and more important to create a digital copy of the patient, a digital simulation of a patient’s health. That digital replica learns through simulation and gives the possibility to test interventions at a minimal risk but with greater benefit.
MeDigiT as flagship project
In 2021, Medical Digital Twin (MeDigiT) was elected flagship project by CMIV scientific council.
A prerequisite for being able to maintain cost-effectiveness and high qualitative healthcare is to make the treatment of patients more individualized. Advanced data driven techniques offer the possibility to measure and quantify the course of disease. However, it is difficult to make a diagnosis based on measurements as local ailments often affect the whole body. In addition, patients seldom have only one ailment but several at the same time. To be able to understand and use all these data, a tool is needed that can evaluate and visualize the entire patient's complex anatomy and physiology. A common solution for this in the industry is to create a digital twin, a replica in a computer. In the same way this is applied to medicine.
Thus, in a clinical environment it is possible to simulate different treatment scenarios by using a digital twin of a patient. This digital model can be used to optimize treatment but also to gain insight on how different treatments for different diseases affect each other. In the development of medical digital twins, health care and MedTech companies need to work together. That cooperation is a prerequisite for moving forward.
Tino Ebbers, professor in physiological measurements, with special research interest in cardiovascular imaging with focus on assessment of blood flow dynamics and tissue characterization, is leading the MeDigiT platform. The goal is to enable the use of individual-specific digital models in healthcare to facilitate diagnoses, more individualized treatment of different illness and improved training of healthcare staff.
The platform consists of five demonstrator projects, Tino explains. One of the projects is a collaboration with Sectra and Region Östergötland and focuses on the use of time-resolved digital twins of the body’s joints in teaching.
Another demonstrator is focusing on CMIV’s cutting edge research on imaging of the cardiovascular system. By simulating the heart flow based on examinations in the computed tomography (CT) scanner, individualized digital twins are tested for diagnosis and treatment evaluation in heart disease. The goal is to improve valve surgery and risk assessment of blood clot formation in atrial fibrillation.
The third demonstrator is a collaboration with Scandinavian Real Heart. This demonstrator strives to improve the design of medical implants as for example the artificial heart by using magnetic resonance imaging (MRI), conventional CT as well as the new photon counting detector CT (PCD-CT). The entire measuring equipment is huge for two reasons (see image).
Medical equipment with an artificial heart in the MR scanner. One is that it is a heart with a motor in it and that motor cannot be in the MR scanner. The second is that to test a heart, you need to have the whole system around in order to simulate the vascular system. It must work with a certain pressure, Tino explains.
In the Whole-body demonstrator a SheDigiT and a HeDigiT are created. It also develops a platform to enable the creation of digital twins of patients with public diseases.
Last there is a new demonstrator of the whole-body composition digital twin, which is focusing on body composition measurements in cooperation with AMRA Medical.
The main objective with MeDigiT is to create and promote a network for the exchange of knowledge and experience between Linköping University, Region Östergötland and companies in medical visualization.
-The most important thing about the platform is that we create a network where we can learn from each other, Tino concludes.