Researchers from MIT and Massachusetts General Hospital have developed an exercise and muscle engagement monitoring system for unsupervised physical rehabilitation that could help with injuries and better mobility for the elderly and athletes, they say.
WHY IT MATTERS
People with disabilities benefit from physical rehabilitation, but there are not enough physical therapists.
To better enable data-driven, unattended rehabilitation for athletes recovering from injuries, patients currently undergoing physical therapy, or patients with disabling conditions, researchers from the MIT Computer Science and Artificial Intelligence Laboratory and MGH have developed a sensor-based wearable device and developing a virtual reality platform, MuscleRehab.
The system calculates muscle use and visualizes it on a virtual musculoskeletal avatar. It uses an imaging technique called electrical impedance tomography, which measures how muscles interact with a VR headset and tracking suit that allow patients to observe themselves alongside a physical therapist.
The researchers, who are preparing to present their work for the first time, say studies of the system show that monitoring and visualizing muscle engagement during unsupervised physical rehabilitation improves therapeutic accuracy and post-rehab evaluation and potential re-injury can prevent.
“By actively measuring deep muscle engagement, we can observe whether the data is abnormal compared to a patient’s baseline value to provide insight into the potential muscle pathway,” said Junyi Zhu, a graduate student at MIT CSAIL and lead author of an article on MuscleRehab in Today notice.
The system includes a training program with pre-recorded baseline standards for the program and streams the avatar with real-time muscle use.
Patients wear the tracking suit and VR to capture their 3D motion data and then perform various exercises such as z and adductor activity.
The EIT sensor board is accompanied by two electrode-filled bands that slide onto a user’s thigh to collect 3D volumetric data. Using a motion capture system, EIT capture data shows actively triggered muscles on the display, where muscles darken with more engagement.
The team compared exercise accuracy with and without the wearable EIT. In both cases, her avatar appears alongside a physical therapist.
A professional PT explained which muscle groups to engage in each of the exercises. They compared the two results – with just the motion tracking data overlaid on their patient avatar and added the EIT sensor straps that provide information and visualization of the movement and muscle engagement.
By visualizing both muscle activity and movement data during these unsupervised exercises, rather than just the movement alone, subjects’ overall exercise accuracy improved by 15%.
Researchers also compared how long during exercise the right muscle group was triggered with and without the wearable.
By monitoring and recording most of the engagement data, the PTs reported a much better understanding of the quality of the patient’s exercise and that this helped better assess their current regime and exercise based on these statistics.
Interested in finding a better way than electromyography, which is used by some wearable devices, to detect the engagement (blood flow, stretch, and contraction) of different muscle layers, Zhu was inspired by EIT, which normally measures the electrical conductivity of muscles measures to monitor lung function, detect breast tumors and diagnose pulmonary embolism.
Currently, MuscleRehab focuses on the hamstrings and inner major muscle groups, but could expand to the glutes.
The publication’s co-authors include research scientist Hamid Ghaednia, instructor in the Department of Orthopedic Surgery at Harvard Medical School and co-director of the Center for Physical Artificial Intelligence at Mass General Hospital, and Dr. Joseph Schwab, director of the Orthopedic Spine Center, director of spine oncology and co-director of the Stephan L. Harris Chordoma Center and associate professor of orthopedic surgery at Harvard Medical School.
THE BIGGER TREND
There is a growing trend to use technology such as remote patient monitoring to care for patients and relieve hospitals and providers.
Innovation is in its early stages with physicians and patients open and willing to adopt new solutions, said Dr. Waqaas Al-Siddiq, Chairman, CEO and Founder of Biotricity IT news in healthcare March.
“We can advance RPM by looking at diagnostic devices that currently exist for each condition, figuring out what sensors can be integrated into wireless devices, and creating clinically relevant, continuous solutions,” he said.
Just as RPM can significantly reduce hospital readmissions and emergency room visits, new sensor-based technologies can advance approaches to home healthcare and have the potential to improve outcomes and reduce in-person visits.
ON THE RECORD
“This work advances EIT, a sensing approach traditionally used in clinical settings, with an ingenious and unique combination with virtual reality,” said Yang Zhang, assistant professor of electrical and computer engineering at UCLA’s Samueli School of Engineering, in the announcement.
“Enabled application facilitating rehabilitation may have a major impact on society at large to assist patients to carry out physical rehabilitation safely and effectively at home.
Andrea Fox is Editor-in-Chief of Healthcare IT News.
Email: [email protected]
Healthcare IT News is a HIMSS publication.
