IImagine having a digital twin who gets sick and can be experimented on to identify the best possible treatment, without having to reach for a pill or a surgeon’s knife. Scientists estimate that within five to ten years, “in silico” trials – in which hundreds of virtual organs are used to assess the safety and effectiveness of drugs – could become commonplace, while models organs specific to each patient could be used to personalize treatment and avoid medical complications.
Digital twins are computer models of physical objects or processes, updated using data from their real-world counterparts. In medicine, this means combining large amounts of data about the functioning of genes, proteins, cells and whole-body systems with patients’ personal data to create virtual models of their organs – and eventually their entire body .
“If you practice medicine today, a lot of your practice is not very scientific,” said Professor Peter Coveney, director of the Center for Computational Science at University College London and co-author of You virtual. “Often it’s like driving a car and figuring out where to go next by looking in the rearview mirror: you’re trying to figure out how to treat the patient in front of you based on people you’ve seen in the past. which had similar conditions.
“What a digital twin does is use your data in a model that represents how your physiology and pathology work. This is not about making decisions about you based on a population that may be completely unrepresentative. It’s truly personalized.
The current cutting-edge model is found in cardiology. Companies are already using patient-specific heart models to design medical devices, while the Barcelona start-up ELEM BioTech offers companies the ability to test drugs and devices on simulated models of human hearts.
“We have already conducted a number of virtual human trials on several compounds and are about to enter a new phase, with our product ready and deployed in the cloud for external access by pharmaceutical customers” , said the co-founder and director of ELEM. director, Chris Morton.
Speaking at Digital Twins Conference At the Royal Society of Medicine in London on Friday, Dr. Caroline Roney of Queen Mary University of London described efforts to develop personalized cardiac models that would help surgeons plan surgery for patients with irregular, chaotic heartbeat (atrial fibrillation).
“Often, surgeons use an approach that works on average, but it’s very difficult to make patient-specific predictions and predict long-term outcomes,” Roney said. “I think there are many applications in cardiovascular disease where we will see this type of approach come to fruition, such as deciding what type of valve to use or where to insert it when replacing a heart valve.”
Cancer patients should also benefit. Artificial intelligence experts at pharmaceutical company GSK are working with cancer researchers at King’s College London to create digital replicas of patients’ tumors using images and genetic and molecular data, as well as culturing the cancer cells of the patients in 3D and testing their reaction. drugs.
By applying machine learning to this data, scientists can predict how individual patients are likely to respond to different drugs, drug combinations, and dosing regimens.
“You can’t do this repetitively with the real patient with multiple drugs and drug combinations, because every time you try a new treatment, it’s a clinical trial,” said Professor Tony Ng, from King’s.
“We try to find a solution while the patient is still alive, so if he comes back with a recurrence (of his cancer), we will know how to treat him, or which clinical trial to submit him to.”
Proof-of-concept testing is expected to begin next year.
Researchers are even developing digital twins for pregnancy, which could help develop drugs for conditions such as placental insufficiency or pre-eclampsia, as well as a better understanding of the physiological processes that underlie pregnancy and the work.
“In many cases it is impossible to do experiments on pregnant women, nor are there good animal models for human pregnancy,” said Professor Michelle Oyen, director of the Center for Engineering at women’s health at Washington University in St. Louis.
Oyen builds models of the placenta from ultrasound scans taken during pregnancy and high-resolution images after birth in women with healthy and complicated pregnancies, and trains an algorithm to recognize and build a digital replica of the different tissues.
“Our goal is to try to understand the things we could measure in a living person to predict who is likely to have problems with placental function during pregnancy, and to intervene to prevent things like stillbirth,” said Oyen said.
His collaborator, Professor Kristin Myers, of Columbia University in New York, is building models of the cervix, the uterus and the membranes that surround the fetus. Their long-term goal is to combine them all into a single model of an individual capable of predicting the course of pregnancy.
Myers said, “I’m hoping we can do a simplistic ultrasound of the maternal anatomy and be able to assess how this uterus is going to grow and stretch, as well as a best time for labor.” » It could even predict a long or complicated labor and help women make a more informed decision about whether to have a C-section, she said.
Other researchers are building digital twins of hospitals to try to improve the efficiency with which individual patients move through the health care system.
“By tracking the digital signatures created every time something happens to a patient – from the time an X-ray is ordered, performed and reported, to the time that patient is booked for an outpatient appointment and there assists – we can create a very detailed analysis, a real-time picture of how patients with similar conditions are progressing through the system,” said Dr. Jacob Koris, trauma and orthopedic surgeon and digital lead at Succeed the first timea national program designed to improve the treatment and care of patients.
“This could identify areas we need to improve, but also best practices that improve patient care, which we can use to rethink how we care for patients.” »