Feature Story | 8-Jan-2025

Building digital twins and hearts

NIH/National Heart, Lung and Blood Institute

Imagine having a digital carbon copy of yourself that physicians could use to predict long-term risks for disease, assess how your body may respond to treatment, and simulate surgeries in advance. A virtual twin may sound as far-fetched as robotic surgery and self-driving cars once did, but researchers are studying how to turn this vision into a reality.

“I hope I see it in my lifetime,” said Colleen E. Clancy, Ph.D., the director of precision medicine and data sciences at the University of California, Davis Health and School of Medicine. “I think we’re on the cusp of real, personalized medicine.”

Creating a digital twin starts with building a prototype, customizing it, and identifying how to synchronize or regularly update it with feedback from a person’s body and their environment.

This includes mapping a person’s organs and systems, tissues, cells, genes, and molecules among other things, and incorporating input from external stimuli. This might include exposure to viruses, temperature swings, and social factors, such as living near green spaces or pharmacies. “All these pieces live in different parts of a hospital, so to speak,” said Clancy. “Suddenly we can start to bring all those things together.”

This long-term goal will require collaboration from nearly every sector — the government, regulatory bodies, researchers, engineers, physicians, patients, and medical and biotech industries. It’s also fraught with nuance. How can experts build models that will add the most value to care? How can computer systems power a digital replica of a human being and at scale? What safeguards are needed to protect the privacy and safety of patients?

As researchers discuss the best ways to navigate these issues and build digital twins, they are also studying how virtual organs, like hearts, and digital snapshots, including 3D images of arteries, could improve care.

Here is what they hope to achieve:

Make surgeries more precise

At the Trayanova Lab at Johns Hopkins University, researchers take images of a patient’s heart the week before they have an ablation, a medical procedure for atrial fibrillation, an irregular heart rhythm. Based on these images, they create a computer simulation of a patient’s heart to practice the procedure. This creates a blueprint to identify areas of the heart that they will ablate, or target, by destroying affected tissues where the irregular heart rhythm occurs. Then, they save it and have a customized plan for the operating room.

Currently, ablation works for about 50-70% of people. Through a trial ending later this year, the researchers are studying if using these personalized plans could improve success rates and reduce complications.

“There’s a saying that goes, ‘all models are wrong, but some are useful,’” said Roozbeh Jafari, Ph.D., a principal staff member at MIT Lincoln Laboratory and an adjunct professor at Texas A&M University. He explained the goal is to find models that work so physicians and patients can take action. “That’s the whole key,” he said. “If it’s not actionable there is nothing we can do about it. I can’t take your model and apply it to my body and vice versa.”

Jafari notes that by finding the right models, virtual twins could potentially serve as a randomized trial for each person.

Other researchers are studying how these concepts — using digital scans of a patient’s heart, cardiopulmonary system, or coronary arteries — could help doctors practice surgeries in advance and predict if and when they may need certain procedures.

Identify the right treatments for patients

In addition to using a person’s virtual organs to inform decisions about treatment, researchers are discussing ways digital twins could participate in studies.

Nidhi Gera, Ph.D., a health sciences administrator at NHLBI, likes this concept because it could accelerate different phases of research. “We can predict, ‘How will this person respond to treatment? What should be the drug dose?’” she explained. “How can we bring this information together to do clinical trials quickly and effectively?”

The benefits of virtual trials could be vast, added Ehsan Abadi, Ph.D., an associate professor in radiology at Duke University. In addition to possibly saving years and billions of dollars by expediting research, they could reduce patient exposure to extra tests and imaging, including higher doses of radiation. They could also help identify therapies worth studying in real-world clinical trials, which may mean patients get access to new treatments sooner. This applies to chronic conditions like heart and lung disease, as well as understudied and rare conditions.

Abadi added that virtual trials could also help diversify research. People who don’t have time to enroll in studies or who don’t live near trial sites could lend their virtual selves to research — and still contribute to and benefit from the findings.

Personalize prevention

As researchers create the groundwork for building digital twins, they are also investigating other ways to support earlier risk predictions.

At Stanford University, researchers are studying how medical images of the chest and abdomen could complement information in electronic health records to enhance risk predictions for cardiovascular disease. This includes studying how early signs of calcium deposits in coronary arteries and the aorta, excess fat in the liver, and reduced bone mineral density may improve predictions.

“It’s taking very high-dimensional data, but making it useful,” said Akshay Chaudhari, Ph.D., an assistant professor of radiology and biomedical data science at Stanford University. Building a digital twin follows the same premise, he explained. “From a holistic perspective, can we simulate potential interventions, such as weight loss or starting a new treatment, to understand what will be best for a patient at a given time?”

Chaudhari and the researchers note that while digital twin technology is in its infancy, the concepts studied are designed to help patients and physicians work together to personalize care and improve health outcomes.

“The concept of personalized or precision medicine has been around for a long time,” said Clancy. “Now it feels as though we are on the horizon to realize it. To do it in a way that we haven’t done before.”

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.