Sunghoon Lee
University of Massachusetts, MA·Biomedical Engineering
After a stroke, most survivors have weakness in one arm or hand, a condition called upper-limb paresis. What matters most for recovery is how much people actually use that arm at home and in the community, not only what they can manage during a test in the clinic.
- Fields
Biomedical Engineering
Computer Science
Medicine & Clinical Research
- Topics
stroke rehabilitation
upper-limb paresis
hemiparesis
- Grants
- 2 known grants, through May 2027
What they work on
- Develop a Body Channel Identification (BCID) sensing platform, with batteryless object tags read by a wrist-worn device through the body during touch, that records object identity, contact timing, grip pressure and wrist motion.
- Build machine learning algorithms that use BCID and wrist motion-sensor data from 50 stroke survivors and ten healthy subjects to classify rehabilitation-relevant arm movements and rate their amount and quality.
- Examine how stroke survivors' motor capacity measured in the clinic relates to their arm and hand performance in daily life outside the clinic, using the multi-modal BCID platform.
- Develop an mHealth platform that combines a finger-worn ring accelerometer with cloud-based systems, plus machine learning algorithms, to measure arm and fine hand use during daily activities in chronic stroke survivors.
- Use human-centered design with patients and clinicians to find the best goal tailoring, feedback content, delivery medium and timing, and data sharing for an app that encourages use of the stroke-affected arm.
- Test in an 8-week field deployment whether the ring-sensor mHealth system with tailored feedback increases use of the affected upper limb in chronic stroke survivors.
More about the research
Clinicians have few tools to measure real-world arm use. They also have few ways to keep patients practicing after the first weeks, when recovery levels off and function can slip. Both projects build wearable sensors and machine learning tools that track arm and hand use in daily life. One of them also tests whether a mobile app that gives feedback can encourage people to use the affected arm more.
Why it matters
The grants estimate that nearly 800,000 Americans go through stroke rehabilitation each year. Measuring real-world arm use could let clinicians build personalized rehabilitation programs that target what patients actually do in daily life. Feedback tools could help chronic stroke survivors keep practicing so they hold on to the function they regained. The sensing approach could also help people with one-sided weakness from traumatic brain injury or multiple sclerosis.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Zhaozheng Yin
Stony Brook University, NY·Computer Science
Develop motion capture from wearable inertial measurement unit (IMU) sensors alone to reconstruct and predict daily-life gait, using knowledge distillation from a multi-sensor teacher network to a simpler student network.
Zhishan Guo
North Carolina State University, NC·Engineering
Develop a gait capture method using only wearable inertial motion unit (IMU) sensors, using knowledge distillation so a multi-sensor teacher network trains a simpler IMU-only student network to predict walking in daily life.
Sudha Srinivasan
University of Connecticut, CT·Medicine & Clinical Research
Assess whether a home program using modified joystick-operated ride-on toys is feasible, enjoyable, and acceptable for children aged 3–8 with hemiplegia and their caregivers, using child and caregiver questionnaires.
The school
University of Massachusetts: 28 labs on PI Pages, $282M a year on research, 337 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.