Digital Twins — virtual replicas of things from the real world – are already commonplace in manufacturing, industry and aerospace. There are very complex digital models of cities, ports and power plants, but what about people?
The idea of digital lookalikes has long been confined to the realm of science fiction. But one a new book presented at London’s Science Museum last week suggests the concept could come to life.
In Virtual youPeter Coveney, professor of chemistry and computer science at University College London, and Roger Highfield, scientific director of London’s Science Museum, show how far researchers have come in their quest for accurate digital simulations of humans.
At the book launch, the authors were joined by leading experts on digital twins in healthcare from the University of Oxford, UCL, and the Barcelona Supercomputing Center (BSC). The panel discussed the opportunities and challenges of creating a digital twin of the human body, and its implications for medicine.
The BSC has already created virtual models of living cells and whole organs. The most notable example is Alya Reda digital twin of a heart consisting of approximately 100 million virtual cells.
The heart beats not in a human being, but within MareNostrum, one of the most powerful supercomputers in Europe. In collaboration with medical technology company Medtronic, the Alya Red simulations can help position a pacemaker, fine-tune the electrical stimulus and model its effects.
MareNostrum is located in the chapel Torre Girona, Barcelona. Credit: Karolina Moon Photography.Perhaps one of the most notable examples is Yoon-sun, a 26-year-old Korean woman whose entire circulation – a 95,000 km long network of ships – has been virtually mapped through an international collaboration using several supercomputers. Researchers use the model to study blood pressure and the movement of clots through the vascular system.
These digital twins are not just limited to the lab. Several are already in use and in some cases approved by the US Food and Drug Administration (FDA).
Until now, these models have mainly been used for in silicon trials – when a drug or disease is tested virtually rather than on actual human or animal tissue.
These trials allow companies to test their drug in ‘virtual patients’ before testing it on humans. This can help companies detect a “failure in the making” early in the drug development cycle. say François-Henri Boissel, CEO of Frans simulation platform for clinical trials Nova Discovery. This can involve significant time and expense savings for companies conducting clinical trials.
In silico studies also eliminate the ethical issues associated with animal testing, explained Blanca Rodriguez, a professor of computational medicine at the University of Oxford, at the panel conversation last Wednesday.
Rodriguez’s team has created a digital twin of a heart that is used to simulate the effects of various drugs and diseases on heart function. In one virtual process, her team tested the effects of 66 different drugs on more than a thousand different heart cell simulations and were able to predict the risk of abnormal heart rhythms with an accuracy of 89%. Comparable research in animals was 75% accurate.
These trials could also help combat the next public health emergency. During the COVID-19 pandemic, supercomputers were used to simulate almost everything from possible treatments to predicting how the virus might spread, as highlighted in the video below.
And as simulations of human tissues, organs and cells become more sophisticated, they could open new frontiers for vaccine testing, personalized treatment of symptoms and help physicians explore the effects of an infection on the whole body.
Digital twins could also speed up the search for vaccine candidates for the large families of animal viruses at risk of spillover to the human population, Highfield said.
Coveney and Highfield believe this advancement lays the foundation for digital twins of the entire human body.
Computer models of patients would not only look like their human counterparts, but also behave like them.
Creating a virtual you requires collecting and analyzing enough personal data to provide a realistic representation. This can come from any number of scans of your body and its organs, as well as genomic, biochemical analysis, and portable devices.
“This digital twin can indicate what action a surgeon takes, what drug you’re prescribed, or even what kind of life you choose to live,” Coveney said.
Your doctor can run a number of scenarios through your digital twin — how you might react to a particular drug or illness, for example — without ever touching you (if you hate doctor visits, take note).
“Virtual patients can potentially save and extend your life.
Your digital twin can accurately predict your risk of disease and recommend changes in medications, diet, and lifestyle, potentially saving and extending your life.
According to the European Commission, about 200,000 people die every year in Europe of medicines prescribed to them, in part because these therapies are generic and not specifically designed for the patient.
The same goes for the treatment of diseases: doctors are forced to make decisions based on similar but non-identical patients in similar but non-identical circumstances in the past.
“Modern medicine is like driving a car looking in the rearview mirror — it’s always looking back trying to figure out what’s happening now,” Highfield said. “The hope is that digital twins will enable healthcare to become forward-looking, truly personal and predictive, taking much of the guesswork out.”
Perhaps less reassuring is the idea that your twins might be used to it to predict when you will die, with a fairly high degree of accuracy.
When will I get a virtual me?
Before you get too excited (or petrified) – let’s do a quick inventory.
Denis Noble, a professor at the University of Oxford, developed the first model of a beating heart cell in 1959. supercomputers, began to take shape. Now programs like Alya Red enable simulations of almost every part of the human body.
That is where we are now. To date, a digital twin of a whole human has never been created.
There are still “huge technical hurdles” to overcome, Conveney said.
Simulations of this complexity require access to incredibly powerful computers, such as Frontier, the world’s first and fastest exascale super computer. These computers are still rare and require large quantities energy run.
Another “huge challenge,” he says, is stitching together all the codes for every part of the virtual body. Each part of the digital human, such as a cell or a heart, is technically a separate simulation. There are also multiple scales for the simulations: one model for a cell and another for the whole organ require different codes and run at different speeds. Loading all these codes at once and at the same speed is no easy feat.
There are also ethical considerations. The ability to predict almost everything about your health is a powerful tool for healthcare professionals, but potential dangerous in the wrong hands.
Within the confines of current technology, creating your own virtual twin is currently only within the reach of billionaires, says Conveney.
Even the most powerful computers imaginable in the distant future will not have the capacity to analyze you in molecular detail. You, my friend, are too complicated even for the smartest computer.
But Coveney and Highfield make a compelling case that incomplete digital representations will still be an extremely useful tool for advancing medical science and the health of individuals. As the late British statistician George Box opined: “All models are wrong. Some are useful.”
The authors are also hopeful that these twins’ computing requirements could be reduced using, you guessed it, artificial intelligence.
“AI and machine learning can replicate part of the code and allow the entire digital twin to load at the speeds necessary for effective medical decision-making,” said Highfield. AI could make it possible to run virtual humans on much smaller machines.
While there are many hurdles to overcome, and certainly some ethical issues to resolve, fully functioning virtual patients, providing healthcare professionals with insights they can actually act upon, are not as far off as you might think.
Conveney, one of the leading global experts in the field, believes that virtual patients could be available for practical medical use in about five years.