Simulating stroke treatments using a digital twin

Amsterdam UMC has received a Horizon grant of €10m from the European Commission to lead 19 partners in developing digital twin simulators to assess the best treatment for stroke patients.


Researchers at Amsterdam UMC explained that the ‘digital twins’ they aim to develop are not animations, but ‘real calculations.’

In a statement, Alfons Hoekstra, professor of Computational Science at the University of Amsterdam, said: “We enter the blood pressure, heart rhythm, information from the brain scan and other medical data of the stroke patient. Then a 'digital twin' is generated, on which we can simulate treatments.”

Researchers cited the example of removing a blood clot in the event of a cerebral infarction. By running simulations, researchers said that doctors could be able to see whether a specific treatment will leave the patient's blood clot intact or disintegrates it.

“We are now finding out what is good for the individual patient. The more measurements we can put into the digital twin, the more precisely we can predict what the best treatment will be," said Hoekstra.

This way of entering data into a computer model is called ‘knowledge-based artificial intelligence’, which uses in-depth biological and medical knowledge of strokes. Researchers said that this tool differs from data-driven artificial intelligence, which purely looks at large amounts of data, and uses the data from many previous patients to make predictions.

In addition to the EU's €10m grant, two partners from Switzerland and a partner from Taiwan are contributing a total of €3m.

Researchers said that over the next four years they will be working together to develop the digital twin technology. Once the technology is in place, they expect to need another two years to transfer it into a computer simulation that doctors can use.

The hope is that doctors can increasingly work with computer scientists to combine their physical and biological knowledge with computer data specific to each patient, to ensure efficient and optimal diagnoses and treatment.

“Strangely enough, computer simulations in [medical] work are far from the norm, despite having the potential to be an incredibly valuable tool. With this project, we want to first test the treatment for individual stroke patients on a digital twin. The doctors can see in the simulation which treatment works and which doesn't,” said Henk Marquering, professor of Translational Artificial Intelligence at Amsterdam UMC.

“A treatment that has first been virtually tested on your digital twin? That's tailor-made care."