Digital twins — virtual replicas of real-world objects – 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 the Science Museum in London last week suggests the concept could come to life.
In you virtualPeter Coveney, professor of chemistry and computer science at University College London, and Roger Highfield, scientific director of the Science Museum in London, show how far researchers have already gone in their quest for accurate digital simulations of people.
At the book launch, the authors were joined by leading healthcare digital twin experts from the University of Oxford, UCL, and the Barcelona Supercomputing Center (BSC). THE sign discussed the opportunities and challenges of creating a digital twin version 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 core comprising about 100 million virtual cells.
The heart does not beat inside a person but inside Mare Nostrum, one of the most powerful supercomputers in Europe. In collaboration with medical technology company Medtronic, Alya Red simulations can help position a pacemaker, fine-tune its electrical stimulus and model its effects. All without touching a real person.
Perhaps one of the most striking examples is Yoon-sun, a 26-year-old Korean woman whose entire circulation – a network of ships 95,000 km long – has been mapped virtually through an international collaboration using multiple supercomputers. Researchers use the model to study blood pressure and the movement of clots throughout the vascular system.
These digital twins aren’t just confined to the lab. Several are already in use and, in some cases, approved by the United States Food and Drug Administration (FDA).
So far, these models have been deployed primarily for silicone trials – when a drug or disease is tested virtually rather than on real human or animal tissue.
These trials allow companies to test their drug on “virtual patients” before testing them on humans. This can help companies detect “failure in manufacturing” early in the drug development cycle, said François-Henri Boissel, CEO of French Novadiscovery clinical trial simulation platform. This can lead to significant delays and costs savings for companies carrying out clinical trials.
In silico trials also eliminate the ethical issues associated with animal testing, explained Blanca Rodriguez, professor of computational medicine at the University of Oxford, during the sign debate last Wednesday.
Rodriguez’s team has created a digital twin of a heart that is used to simulate the effects of different drugs and diseases on heart function. In a virtual trial, his 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 89% accuracy. Comparable research on animals was 75% accurate.
These trials can also help tackle the next public health emergency. During the COVID-19 pandemic, supercomputers have been used to simulate almost everything from potential treatments to predicting the spread of the virus, as highlighted in the below video produced by the BSC.
And as simulations of human tissues, organs and cells become increasingly sophisticated, they could open up new frontiers for testing vaccines, personalized treatment of symptoms and helping doctors explore the effects of an infection all over the body.
Digital twins could also speed up the search for candidate vaccines for large families of animal viruses that are at risk of spreading to the human population, Highfield said.
Coveney and Highfield believe these advances are laying the foundation for whole-body digital twins.
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 analyzes of your body and its organs, as well as genomic, biochemical and portable devices.
“These digital twins can inform about what steps a surgeon is taking, what medication you’re being prescribed, or even what kind of life you’re choosing to live,” Coveney said.
Your doctor could run a number of scenarios through your digital twin – how you might react to a certain medication or illness, for example – without ever touching you (if you hate doctor visits, take note) .
“Your twin could be used to predict when you die.
Your digital twin could accurately predict your disease risk and recommend medication, diet and lifestyle changes, potentially extending your life.
According the European Commission, around 200,000 people die every year in Europe from the drugs they have been prescribed, in part because these therapies are generic and not designed specifically for the patient.
The same applies to the treatment of diseases: doctors are obliged to make decisions based on similar but not identical patients in similar but not identical circumstances in the past.
“Modern medicine is like driving a car while looking in the rear view mirror – it’s always looking back to try to figure out what’s going on now,” Highfield said. “The hope is that digital twins will enable healthcare to become future-oriented, truly personalized and predictive, eliminating much of the guesswork.”
Virtual patients could usher in a new era of personalized healthcare, where treatments are specific to the individual and overall more effective.
Perhaps less consoling is the idea that your twin could be used to predict when you die, with a fairly high degree of accuracy.
Let’s move on.
So when will I have a virtual me?
Before you get too excited (or petrified), let’s do a quick checkup.
Oxford University professor Denis Noble developed the first model of a beating heart cell in 1959. A few years later his work was extended to the level of cell patches, and by the models of the years 1990s of the whole core, powered by the first supercomputers, began to take shape. Today, programs like Alya Red allow simulations of almost every part of the human body.
This is where we are right now. To date, a digital twin of an entire human has never been created.
There are still “massive technical hurdles” to overcome, Conveney said. Simulations of this complexity will require access to incredibly powerful computers, such as Frontier, the first and fastest in the world exascale supercomputer. These computers are still rare and require large amounts of energy run.
Another “huge challenge”, he says, is putting together all the codes for each part of the virtual body. Each part of the digital human, like a cell or a heart, is technically a separate simulation. There are also several scales for simulations: one model for a cell and another for the whole organ require different codes and run at different speeds. Getting all those codes to load at the same time and at the same speed is no mean feat.
There are also ethical considerations. The ability to predict almost anything about your health is a powerful tool for medical professionals, but potentially dangerous in the wrong hands.
Within the limits of current technology, creating your own virtual twin right now is 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 all molecular detail. You, my friend, are too complicated for even the smartest computer.
But Coveney and Highfield convincingly demonstrate that incomplete digital representations will remain an extremely useful tool for advancing medical science and the health of individuals. As the late British statistician George Box said: “All models are wrong. Some are useful.
The authors also hope that the computing needs of these twins can be reduced by using, you guessed it, artificial intelligence.
“AI and machine learning can replicate some of the code and allow the whole digital twin to load at the kind of speed needed for effective medical decision-making,” Highfield said. AI could allow virtual humans to run on much smaller machines.
While there are many hurdles to overcome, and certainly some ethical issues to address, fully functioning virtual patients, which offer healthcare professionals information they can actually act on, are not as far off as one would expect. might think so.
Conveney, one of the world’s leading experts on the subject, believes virtual patients could be available for practical medical uses. in about five years.