SCH: INT: Collaborative Research: "RehabBuddy" Extending Individualized Physical Rehabilitation Beyond the Clinic Using Wearable Technology to Empower Patients

Regents Of The University Of Michigan - Ann Arbor, Ann Arbor MI

Investigators

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.