Digital Twin Tech Is Set to Reshape Healthcare Dx

Health systems are just beginning to develop digital models of everything from organs to people to whole neighborhoods to improve and personalize patient outcomes.

A technology first used by NASA to map out space travel is now giving healthcare providers a better look at how to treat patients.

Digital twin technology creates a digital model of a person, object, system, or process, which can be used to simulate the real thing for testing, monitoring, and other processes. Healthcare has only recently caught on to the potential for digital twins, which can be used to map out complex surgeries, test the efficacy of a treatment, and anticipate the progress (including possible side-effects and setbacks) or a care plan.

“We know the technology is capable of great things,” says Steve Levine, senior director of virtual human modeling for San Diego–based Dassault Systèmes, which drew large crowds with an exhibition at the CES 2023 show in Las Vegas last January. “Many medical centers are only recently becoming digitized, so the adoption curve is going to be long.”

[See also: Consortium Unveils Guidelines for Using Digital Twin Technology.]

Digital twin technology was first used by the American space program in the 1960s to model spacecraft development and simulate the moon landing. Since then, it has been used to design buildings and other structures such as dams, roadways, theme parks, automobiles, planes, planned communities, and a wide range of manufactured products.

The concept first entered the healthcare lexicon roughly 10 years ago with the launch of the Living Heart Project, a collaboration between Dassault Systèmes and the U.S. Food and Drug Administration (FDA) to gather cardiovascular researchers, medical device developers, cardiologists, educators and others to “develop and validate highly accurate personalized digital human heart models.”

Levine, who founded the project and serves as its chief strategy officer, says the goal is to create a 3D model that replaces animal testing, reduces the cost and complexity of clinical trials, helps guide medical device makers in designing cardiac technology, and can be used to plan out surgeries, treatments, and other procedures.

“Simulations are extremely expensive, limited, and not personal,” Levine says. “This will give us a much better model of the human heart.”

Levine says several organizations are using lessons learned from the Living Heart Project to develop digital twin models for other parts of the body, including the brain, liver, kidneys, lungs, and musculoskeletal system. In addition, Boston Children’s Hospital is partnering with Dassault Systèmes on applications of the technology for pediatric care, and Johns Hopkins is exploring the potential for digital twins in remote surgery and treatment.

“Ten years ago, no one had heard of digital twins,” he says. “Now [healthcare organizations] are interested in it and are looking at how they can use it. The pandemic raised a lot of awareness around the need for working virtually, so the focus on this technology has accelerated phenomenally over the past few years.”

Several health systems are testing the technology, including the University of Miami Miller School of Medicine, which is using funding from the National Institutes of Health (NIH) to create a digital twin, or MILBox, of a patient through data gathered from wearables and sensors.

[Listen to the HealthLeaders podcast: Examining the Potential for Digital Twins in Healthcare.]

“We want to demonstrate that this kind of individualized data capture can spur a new line of research and personalization in healthcare,” Azizi Seixas, PhD, founding director of the Media and Innovation Lab (TheMIL), and associate director for the Translational Sleep and Circadian Sciences Program at the Miller School of Medicine, said in a press release. “With the capacity to discover everything we can about the individual, we can change the relationship between people and their health.”

“Eventually, such digital twins could comprise sufficient detail about an individual so that a computer could test different treatment or wellness options against that model to predict which are most likely to produce the best outcomes for that person,” school officials said. “Instead of prescribing treatments based on a statistical model of outcomes across a large population, this new approach would provide each patient with a personalized recommendation calculated to produce the best outcome for them.”

This past January, the NIH awarded a $3.14 million grant to the Cleveland Clinic and MetroHealth to design entire “digital twin neighborhoods” based on the electronic health record data of 250,000 patients, to analyze how environmental, economic, and social factors create healthcare disparities.

“Where a person lives or works can shape their health outcomes, including life expectancy and risk of developing diseases like cancer or diabetes,” Jarrod Dalton, PhD, director of the Center for Populations Health Research at the Cleveland Clinic, said in a press release. “Americans from socioeconomically disadvantaged communities are more likely to have heart attacks and stroke, and are expected to live 10 fewer years than wealthier Americans. Our goal is to design an approach to help health systems, governments and organizations collaborate and strategize ways to address clear disparities.”

“This project aims to chart a new course for understanding place-based population health strategies and improving health outcomes,” added Adam Perzynski, PhD, of MetroHealth’s Population Health Research Institute (PHRI). “Evaluating technology like digital twins in the research space can make it easier for organizations to take a data-backed approach to public health interventions. Instead of building these models from scratch, other health systems and organizations can adapt the framework for their own needs.”

Levine, who is now working to develop a playbook on digital twin technology in healthcare, says the evolution of digital twin technology will move from designing models to using AI and predictive analytics to map out outcomes, both good and bad.

“We’ll move on from what does it look like to how does it perform to what it can and will do,” he says.

The biggest obstacle at present, he says, is unfamiliarity with the technology, alongside the reluctance among health system decision-makers to invest in something new.

“We need the pioneers to take on the work,” he says. “Once we start getting the qualitative assessments and the data … you’ll see a lot more interest [and engagement]. It’s going to happen.”