Digital twins could potentially facilitate individualized healthcare options.
Imagine having a digital replica of yourself that becomes sick and can be used for experiments to determine the most effective treatment, without the need for any pills or surgeries. Experts predict that in the next five to 10 years, “in silico” trials – where virtual organs are employed to test the safety and effectiveness of medications – could become a regular practice. Additionally, personalized organ models based on individual patients could be utilized to customize treatment and prevent medical complications.
Digital twins are computational models of physical objects or processes, updated using data from their real-world counterparts. Within medicine, this means combining vast amounts of data about the workings of genes, proteins, cells and whole-body systems with patients’ personal data to create virtual models of their organs – and eventually, potentially their entire body.
According to Professor Peter Coveney, who co-wrote Virtual You and is the director of the Centre for Computational Science at University College London, modern medicine often lacks scientific evidence. It can be compared to driving a car and using the rear-view mirror to determine the next steps – doctors often rely on past experiences with patients who had similar conditions to treat the current patient.
A digital twin utilizes your data in a model that reflects how your body functions and any potential health issues. It does not rely on general population data that may not accurately represent you. This technology is truly personalized.
The current state of the art model can be found in cardiology. Already, companies are using patient-specific heart models to help design medical devices, while the Barcelona-based start-up ELEM BioTech is offering companies the ability to test drugs and devices on simulated models of human hearts.
According to Chris Morton, co-founder and CEO of ELEM, we have conducted various virtual trials on multiple compounds and are now preparing to move into the next phase. Our product is fully developed and will soon be accessible in the cloud for pharmaceutical clients to use externally.
Dr. Caroline Roney from Queen Mary University of London spoke at the Digital Twins conference at the Royal Society of Medicine in London on Friday. She discussed the progress being made in creating individualized heart models to aid surgeons in planning surgeries for patients with atrial fibrillation, a condition characterized by irregular and erratic heart rhythms.
“According to Roney, surgeons tend to use a general approach, but accurately predicting individual patient outcomes and long-term results is a difficult task. This approach is expected to be applied in various cases of cardiovascular disease, such as determining the appropriate valve and placement for heart valve replacement.”
Cancer patients are also expected to benefit. Artificial intelligence experts at the drug company GSK are working with cancer researchers at King’s College London to build digital replicas of patients’ tumours by using images and genetic and molecular data, as well as growing patients’ cancer cells in 3D and testing how they respond to drugs.
Using machine learning on this information, researchers can forecast the potential reactions of individual patients to various medications, combinations of medications, and dosages.
According to Professor Tony Ng from King’s, it is not possible to repeatedly test multiple drugs and drug combinations on real patients as each new treatment would be considered a clinical trial.
“We are actively seeking a solution while the patient is alive. This way, if they experience a recurrence of their cancer, we will be prepared with the appropriate treatment or clinical trial.”
Next year, we anticipate commencing proof of concept trials.
Scientists are currently working on creating digital duplicates for pregnancy. This could potentially aid in the development of medications for conditions like placental insufficiency and pre-eclampsia, as well as improve our comprehension of the physiological processes involved in pregnancy and childbirth.
Prof Michelle Oyen, director of the Center for Women’s Health Engineering at Washington University in St Louis, stated that conducting experiments on pregnant women is often not possible and there are inadequate animal models to represent human pregnancy.
Oyen is creating digital representations of placenta tissues by using ultrasound scans and high-resolution images from women who had both healthy and complicated pregnancies. They are also teaching an algorithm to identify and reconstruct these tissues.
“We aim to identify measurable factors in live individuals that can predict the likelihood of placental dysfunction during pregnancy, and take preventive measures, such as avoiding stillbirth,” stated Oyen.
Kristin Myers, a professor at Columbia University in New York, is working with her colleague to develop models of the cervix, uterus, and fetal membranes. Their ultimate objective is to integrate these models into one cohesive representation of an individual to forecast the progression of a pregnancy.
According to Myers, her goal is to use a basic ultrasound scan of the mother’s anatomy to determine how the uterus will develop and expand, which could assist in predicting the timing of labor. This information could also potentially identify potential complications or a lengthy labor, allowing women to make a more informed choice about whether to undergo a caesarean section.
Some scientists are creating virtual replicas of hospitals in an effort to enhance the speed at which patients navigate through the healthcare process.
Dr. Jacob Koris, a trauma and orthopaedic surgeon and digital lead at the national programme Getting It Right First Time, states that by monitoring digital signatures created during all interactions with a patient, such as ordering and performing X-rays, scheduling outpatient appointments, and receiving reports, a comprehensive and up-to-date understanding can be developed on how patients with similar conditions progress through the healthcare system.
This could help us identify areas for improvement and also highlight effective practices that enhance patient care. We can then use this information to revamp our approach to patient care.