.jpeg)
ten years. As part of its Living Heart project, Dassault Systemes built and created a "virtual twin" of the human heart in that amount of time. This "virtual heart" is now saving lives thanks to advances in AI and machine learning models, as the company demonstrated at the recent CES in Las Vegas.
The French company has been producing multiple "virtual twin" versions of intricate machines like automobiles, aircraft, and so on for decades. However, the challenge of creating a virtual replica of the human heart was distinct and complicated.
“The process by which treatments are developed lacks the equivalent of a patient virtual twin to allow for testing on the virtual twin. As a result, we accepted the difficult task of developing human-like virtual twins. We decided to start with the human heart for a number of reasons, not the least of which is the fact that heart disease is still the leading cause of death worldwide.
In order to assist in the development of this three-dimensional "virtual twin," Dassault's project brought together specialists, researchers, and medical professionals in the field. Over 150 distinct organizations from 49 nations collaborate on the project now. The human heart's 3D model is "physics-based" and "operates in the same way as a real human heart." The "virtual twin" can even be given a heart disease and run simulations to see how it reacts to complications. Researchers can even experience this heart inside and look for any defects because virtual reality is now catching up and getting stronger. Dr. Levine emphasized that the researchers have "complete flexibility to introduce anything that might happen in the heart."
Companies like Sahajanand Medicals in India are utilizing Dassault's technology to assist in the production of individualized stents for less than half the cost. Manufacturers of medical devices and pharmaceuticals are also utilizing the "virtual twin" heart to assess the heart's response to their products.
He gave an illustration of how the Boston Children's Hospital uses a 3D "virtual twin" to treat complex cases and how the model has correctly predicted the kinds of surgeries that doctors need to perform. In one such instance, doctors weren't sure what to do with a toddler who was dying because all the oxygen in his blood was going to one lung and they didn't know what to do.
“An exact virtual twin of that patient was created by Dr. David Hoginson at the hospital. In fact, they designed a successful experiment or procedure with the twin. Dr. Levine explained, "The model found the best surgery, and when they did it, it worked perfectly, exactly as predicted."
"The real challenge is to measure the right data and be systematic." The heart is essentially a pump made of electricity. Dr. Levine stated, "We understand the electrical and mechanical system, the pumping, but the very precise mechanics of how nature constructed it must be replicated otherwise the behavior will not be the same."
More specifically, each patient's "virtual heart" can be customized to deliver the best possible outcomes. Dr. Levine stated, "The AI algorithms now have the ability to know about what is happening to the patient as well as what is happening to the clinical measurements that they get." Additionally, these cloud-based platforms are able to communicate and function from any location. Therefore, technically, doctors in any nation can benefit from the procedures and data created by this system.
In addition, Dassault is collaborating with the US Food and Drug Administration (FDA) to set up complete clinical trials on virtual humans. This could make it possible to test treatments on a virtual body and see how they work in the early stages. However, Dassault isn't just limiting the creation of the "virtual twin" to the human heart. According to Dr. Levine, it is also attempting the same thing with the human liver and brain.
However, there are difficulties. While some parts of other organs, like the brain, are well-understood, others remain a complete mystery. Because we will never know if we get it right, it is very difficult for us to model something that we do not comprehend,” he stated.
Another organ that the company wants to create a virtual twin for is the liver. This is especially important because it would help pharmaceutical companies understand how a drug might affect the liver, which is a major obstacle. They are also utilizing AI-based new tools to "make sense of very complex datasets."
We do not require a million patients to comprehend how something works. Therefore, we only require a few that are representative. However, before we can test them against a million patients, we must first locate the right patients and gather data. That is crucial," he stated.
Although Dr. Levine is confident that they will have a functioning "virtual liver" within a year, he anticipates that it could take a decade to perform all functions.
Naturally, developing such systems also entails significant expenditures. The "business challenge" for Dassault also includes persuading insurance companies and hospitals that such technology can reduce healthcare costs in the long run.
To demonstrate that you will save money, you must first spend the money. That point is where we are now. They now have sufficient data in Boston because they have been doing that for three years. "The outcomes are generally better, the teams are more prepared, and the number of repeat surgeries has gone down dramatically," he said.