The field of Medicine is undergoing a radical transformation thanks to the tremendous progress in artificial intelligence technologies. The digital Twin technology is emerging as a promising tool to revolutionize medical research and treatments. this technology provides accurate virtual copies of human organs, allowing researchers and developers to test medical devices and treatments in a safe and effective environment, reducing the risks and costs associated with traditional clinical trials.
Adsilico, a startup specializing in the development of AI-powered digital twins for healthcare applications, aims to revolutionize the development of medical devices and drug testing by creating accurate virtual models of the human body.
This company has developed an advanced digital model of the heart, or what is known as the digital twin, to simulate in its movement and functions a living human organ.This digital twin is used in testing implantable cardiovascular devices, such as stents and artificial valves, before using them on real patients. these tests aim to ensure the safety and effectiveness of these devices, paving the way for their clinical applications.
These digital hearts are characterized by their ability to simulate various biological features, such as: weight, age, gender, blood pressure, as well as diverse health conditions and ethnic backgrounds, and since clinical data often lack adequate representation of these differences, these digital heart twins present a golden opportunity for medical device manufacturers to conduct experiments on more diverse populations, enhancing the accuracy and comprehensiveness of test results.
AI-powered digital twins enable experiments that cannot be performed on humans, and even on traditional digital models that lack the diversity provided by artificial intelligence, and this diversity ensures that medical devices and treatments will be safe and effective for all patients, regardless of their ethnic backgrounds or health conditions.
Sheena McPherson, CEO of adsilico, emphasizes the importance of this technology, saying: “digital twin technology allows us to represent the full diversity of patients 'Anatomy and physiological responses, which cannot be achieved using traditional methods, and the use of artificial intelligence in testing medical devices leads to the development of more comprehensive and safer devices. by creating realistic virtual models of patients' bodies, researchers can test devices in an environment that accurately simulates the human body, allowing them to identify potential problems and modify designs before using them on patients.
What benefits does digital twin technology offer in the development of medical devices ?
In light of the challenges facing the medical device sector, digital twin technology is emerging as a promising solution to reduce deaths and injuries caused by these devices.
McPherson hopes that AI-powered digital twins will help reduce these shocking numbers, explaining the matter:” to make medical devices safer, accurate and comprehensive tests must be carried out, which is impractical in a clinical trial environment due to high costs, therefore, we seek to use computer-generated digital models, to ensure that the devices are tested as accurately as possible before testing them on humans.
“A large part of the deaths and lawsuits related to medical devices could have been avoided by conducting more comprehensive tests, and digital models provide more detailed and in-depth results, as we can use the digital model of the heart and perform tests under various conditions, such as low or high blood pressure, or under various pathological developments, to assess the impact of these conditions on the performance of the device,” she added.
McPherson emphasizes that this technology provides medical device manufacturers with more comprehensive and detailed insights, and it also makes it possible to conduct tests on diverse subgroups of patients, and not just on white men on whom clinical trials have traditionally relied, which represents an important step towards the development of safer and more effective medical devices.
The benefits of digital twins:
Reducing risks to patients: digital twins make it possible to test devices in a virtual environment that simulates the human body, reducing the risks associated with their experience on patients directly.
More detailed results: various tests can be performed on the digital twin, such as testing the effect of high or low blood pressure, or various pathological developments, on the functioning of the device.
More comprehensive tests: the devices can be tested on different subgroups of patients, including women and minorities, who are often excluded from traditional clinical trials.
Reduce lawsuits: a large part of the lawsuits associated with deaths and injuries caused by medical devices can be avoided by conducting more thorough tests.
How to develop these digital hearts?
In developing its innovative digital heart models, AdSilico relies on training its artificial intelligence systems on a unique combination of data, including cardiovascular data, magnetic resonance images, and real CT scans, obtained from volunteer patients after obtaining their consent.
These data are intended to provide models with detailed information about the structures of cardiac anatomy, enabling them to create accurate digital representations of how medical devices interact with the anatomy of different patients.The testing process followed by AdSilico involves creating a (digital twin) of the medical device to be tested, and then inserting this digital twin into the virtual heart model, within an advanced simulation environment generated by artificial intelligence.
These tests are carried out entirely within an advanced computer environment, allowing the tests to be repeated on thousands of other digital heart models, all of which are artificial intelligence-simulated versions of real human hearts, representing a significant shift from traditional human and animal experiments, which are usually limited to only hundreds of participants.
Reducing risks and costs:
How does the "digital twin" technology contribute to accelerating the process of drug development
The biggest incentive for pharmaceutical and medical device companies to adopt AI-powered digital twin models, as a complementary alternative to traditional clinical trials, is the ability of these models to reduce the time required to conduct trials, which translates into significant cost savings.
For example, Sanofi pharmaceutical expects to be able to reduce the duration of testing by up to 20% while also achieving an increase in the success rate, and Sanofi is applying digital twin technology in its specialty areas, which include immunology, oncology, and rare diseases.
Sanofi relies on biological data from real people to create digital models to simulate patients, which are not replicas of specific individuals, but digital representations that can be distributed to control groups and a placebo within the experiment.
In addition, Sanofi's artificial intelligence systems create computer-generated models of the drugs to be tested, synthesize their characteristics, such as: how the drug is absorbed by the body, which makes it possible to test them on digital patient models, and the program also predicts the reactions of these models, simulating the process of a real clinical trial.
Matt Trubo, global head of computer R&D platforms at Sanofi, pointed out the big challenges facing the pharmaceutical industry, as the failure rate of new drugs during clinical development stages is 90% industry-wide, meaning that companies spend huge amounts on clinical trials, which often end in negative results.
Matt Trobo believes that technologies such as digital twins can revolutionize this sector, and explained that achieving an increase of only 10% in the success rate of drugs using these technologies can lead to saving 100 million dollars, given the high costs incurred by companies in conducting clinical trials in the late stages.
Trubo stressed that the initial results of the use of digital twins at Sanofi look very promising; however, he stressed that there is still a lot of work to be done, especially in the field of complex diseases.
Tropo believes that artificial intelligence will have a vital role in the development of the next generation of digital twins, as he stressed that providing the next generation of digital twins with accurate artificial intelligence models of complex human biology represents the next frontier in this field.
The digital twin technology between great opportunities and challenges:
Charlie Patterson, managing partner at PA Consulting and former director at the National Health Service (NHS), warns that digital twins may carry weaknesses, noting that their quality depends largely on the quality of the data on which they are trained. It is feared that the use of outdated data collection methods and low representation of marginalized populations may lead to the continued introduction of biases into hypothetical models of individuals.
Sanofi is aware of this challenge of relying on outdated and limited data in training its artificial intelligence systems, and is striving to overcome it. To expand the scope of its internal datasets, which include millions of data points from thousands of patients participating in its trials every year, the company uses data from external sources, such as electronic health records and biobanks.
Returning to ad silico, Sheena McPherson hopes that digital twin technology, powered by artificial intelligence, will help eliminate the need to use animals in clinical trials, which is still an essential part of the drug and medical device testing process.
She emphasizes that virtual models of human hearts are closer to the real human heart than the hearts of animals such as dogs, cows, sheep, and pigs, which are often used in implantable device studies.
A promising future:
As the amazing progress in artificial intelligence technologies continues, eyes are turning towards a promising future for digital twins, as experts expect a remarkable development in the accuracy and complexity of these virtual models, it is expected that digital twins will become able to simulate the functions of more complex human organs, such as: brain, liver and kidneys, which opens new horizons in understanding and treating diseases, and contributes significantly to improving human health and well-being.
Through the use of these advanced technologies, scientists and doctors will be able to develop more effective treatments and customize them to meet the needs of each individual patient, leading to better patient outcomes and improving their quality of life.