Researchers at the University of Miami School of Medicine have launched an NIH-funded study to create a 'digital twin,' which would stand in for the patient on any tests or new treatments to determine whether they're effective.
Researchers at the University of Miami Miller School of Medicine are creating a “digital twin” that would replace the patient during tests and treatments.
Called the MLBox, it would use digital health wearables and smart devices in the home to collect biological, clinical, behavioral and environmental data on a patient, then create a model that could be used to test out new treatments before they’re tried on the actual patient.
The project is being spearheaded by the Miller School’s Media and Innovation Lab (TheMIL), along with Amazon Web Services and the Open Health Network, and will initially focus on treatments for sleep issues, such as sleep apnea, and their link to serious health concerns like dementia and heart disease.
“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 TheMI, an associate director for the Translational Sleep and Circadian Sciences Program at the Miller School of Medicine, and one of the nation’s leading experts on sleep health, 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.”
Seixas will be working on the project, which is funded by the National Institutes of Health, with Girardin Jean-Louis, PhD, director of the Translational Sleep and Circadian Sciences Program and professor of psychiatry and behavioral sciences.
Through the use of sensors and digital health devices, the MILBox will develop and analyze a patient’s sleep patterns, weight, environmental pressures and stress levels. The data will be gathered over seven consecutive days to create a biological health algorithm, which would act as a patient’s digital twin.
The idea is to create a model that will stand in for the patient, allowing care providers to study how a certain drug or treatment works without putting the patient through any stress or danger. For example, it would allow doctors to identify and design a treatment for a specific type of allergy without needing to run the patient through a battery of tests to identify to what the patient is allergic.
“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,” the press release stated. “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.”
Much of the work will be done on the PatientSphere 2.0 platform developed by the Mountain View, CA-based Open Health Network. Officials say the platform will be device-agnostic and scalable, so that more sensors and devices can be added and more data collected to address other health concerns.
“You will be able to add and subtract different devices based on the use case,” Seixas said in the press release. “We’ve designed this to be future-proof and support our larger mission of creating a new kind of personalized health care.”
The program enrolled its first participants in late 2021, and officials hope to have as many as 1,500 participants this year.
Eric Wicklund is the associate content manager and senior editor for Innovation at HealthLeaders.