
NSF Org: |
IIS Division of Information & Intelligent Systems |
Recipient: |
|
Initial Amendment Date: | August 16, 2019 |
Latest Amendment Date: | May 12, 2020 |
Award Number: | 1722619 |
Award Instrument: | Standard Grant |
Program Manager: |
Wendy Nilsen
wnilsen@nsf.gov (703)292-2568 IIS Division of Information & Intelligent Systems CSE Directorate for Computer and Information Science and Engineering |
Start Date: | August 15, 2019 |
End Date: | July 31, 2022 (Estimated) |
Total Intended Award Amount: | $150,293.00 |
Total Awarded Amount to Date: | $158,293.00 |
Funds Obligated to Date: |
FY 2020 = $8,000.00 |
History of Investigator: |
|
Recipient Sponsored Research Office: |
1109 GEDDES AVE STE 3300 ANN ARBOR MI US 48109-1015 (734)763-6438 |
Sponsor Congressional District: |
|
Primary Place of Performance: |
4901 Evergreen Road Dearborn MI US 48128-2406 |
Primary Place of
Performance Congressional District: |
|
Unique Entity Identifier (UEI): |
|
Parent UEI: |
|
NSF Program(s): | Smart and Connected Health |
Primary Program Source: |
01002021DB NSF RESEARCH & RELATED ACTIVIT |
Program Reference Code(s): |
|
Program Element Code(s): |
|
Award Agency Code: | 4900 |
Fund Agency Code: | 4900 |
Assistance Listing Number(s): | 47.070 |
ABSTRACT
Musculoskeletal conditions, often requiring rehabilitation, affects one-third of the American population annually. RehabBuddy is a rehabilitation assistance system that extends the reach of a physical rehabilitation specialist beyond the clinic to address two significant problems in the current standard of care; poor adherence to prescribed exercises and the lack of objective tracking. Both will be addressed by developing a system that uses body-worn motion sensors and a mobile application (e.g. tablet or phone) that provides the patient with assistance to ensure that home exercises are performed with the same precision as under clinical supervision. Assisted by a specialist in the clinic, the wearable sensors and user interface developed will allow the capture of individualized exercises unique to the patient's physical abilities. The system will assist patients by providing real-time corrective feedback to repeat these exercises through a correct and complete arc of motion for the prescribed number of repetitions. The planned work will develop the sensing system to measure the body's motion, the motion processing algorithms that provide measurements of the joint angles, and a real-time corrective feedback approach. The system will be objectively evaluated by three-dimensional motion analysis and assessed by patients with a musculoskeletal injury. The final system will be capable of documenting exercise performance and enhancing the patient's confidence by providing a portable rehabilitation assistant.
RehabBuddy is a multidisciplinary project that spans several domains. The planned approach goes beyond passive exercise monitoring to a patient-in-the-loop approach with real-time corrective feedback. The core scientific challenge is to develop a general framework using inertial sensors capable of exercise motion capture and later assisted repetition for any joint and any exercise through real-time feedback, enabling patient-centered health care. Effective signal processing methods using inertial measurement units to achieve this are not known. The research will include inertial measurement unit signal processing, identifying parameters that unambiguously define custom exercises, and providing useful feedback to assist the patient in repeating exercises correctly while minimizing compensation at other body regions. The system will be evaluated for shoulder exercises, a multi-joint structure that requires a more comprehensive and general solution and has had little attention in prior literature. Critical questions on the human-computer interaction aspect will also be addressed. The effectiveness of the feedback and the system as a whole will be evaluated on how patient motivation and their empowerment to manage their injury are affected by the increased confidence and self-reliance aided by the feedback. It is unknown if providing real-time feedback will improve patients' self-efficacy when performing exercises. Also, it is unknown if upper extremity exercise performance can be enhanced with real-time feedback without supervision. Through the development and evaluation of RehabBuddy with patients, the project aims to begin addressing these questions.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
PUBLICATIONS PRODUCED AS A RESULT OF THIS RESEARCH
Note:
When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external
site maintained by the publisher. Some full text articles may not yet be available without a
charge during the embargo (administrative interval).
Some links on this page may take you to non-federal websites. Their policies may differ from
this site.
PROJECT OUTCOMES REPORT
Disclaimer
This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.
Musculoskeletal injury rehabilitation requires individualized intervention to address the patient's unique needs. Current practice is for patients to seek care from a licensed healthcare professional for treatment. Often these interventions require patients to perform exercises at home without supervision. It is established in the medical literature that even with detailed instructions and images, patients fail to perform the exercises or fail to perform them adequately to recover from their injury. A significant barrier to home exercises is to have similar feedback as the patient has in the clinical environment to ensure they are performing their exercises correctly. Therefore, this study proposed to examine the effectiveness of three levels of feedback: with direct supervision, with no supervision, and with wearing a sensor that tracked the exercise prescribed and provided real-time feedback on performance. The goal of the study was to determine if feedback with the sensor and feedback system was equal to supervised exercise instruction and better than no feedback. Patients undergoing outpatient physical or occupational therapy at the clinic were recruited to be in the study. All patients had upper extremity injuries ranging from fractures to tendonitis. Patients performed a resistive exercise under each of the three conditions for several repetitions not exceeding 10 repetitions. Patients moved through various arcs of motion specific to their needs and were asked to hold at the end range for 2- 5 seconds to fatigue their muscle just like they would during normal rehabilitation. A small sensor was attached to their upper extremity after they agreed to participate in the study and signed a consent form. The sensor communicates with a portable tablet computer via Bluetooth to track all the motions during the study. The patients start and end positions for an exercise were identified and the patient performed three sets of the exercise under each of three conditions; supervised by the treating therapist, unsupervised to simulate what they would do at home, and with feedback from our "RehabBuddy" system. Several variables were measured, such as the full arc of motion performed, the amount of error moving from start to end, and the hold time that patients sustained at their end position. We determined that the two conditions, with feedback from the therapist and with feedback from RehabBuddy were comparable. However, without feedback, patients tended to exceed their prescribed arc of motion, sustain their hold time for shorter durations, and make more movement error as they went from the start to end position. This research supports our idea that by providing patients with a single sensor on their arm and feedback during their exercise, they can perform exercises with the same accuracy as if they were under the supervision of the therapist in the clinic. This study does not replace the role of the therapist as they must prescribe the exercise, define the start, and stop point and determine the appropriate volume of exercise to benefit the patient. This study supports the concept that a system with a single sensor attached to your arm can help a patient perform their exercise through the correct amount of motion, with less chance of moving outside of the correct plane of motion, and facilitate proper training intensity to benefit muscular strengthening. Further research in the home environment and with cell phones are the next logical steps to continue this research to make it feasible to put into clinical practice.
Last Modified: 02/02/2023
Modified by: Samir Rawashdeh
Please report errors in award information by writing to: awardsearch@nsf.gov.