Kendra Cherry-Allen


Title: Tracking post-stroke gait improvements from the clinic to the home


  • Ryan Roemmich, PhD (Kennedy Krieger Institute & The Johns Hopkins University School of Medicine)


The purpose of this proposal is to use novel video-based movement tracking technology to measure gait quality after stroke – in the home. Current rehabilitation practice assesses walking in the highly controlled ‘ideal’ clinical environment. The implicit assumption by clinicians and researchers is that the way people walk in the clinic (their best capacity) reflects the way they walk in the real-world (true performance). With advances in computer vision and development of pose estimation algorithms, we are now able to directly measure how people are walking in their homes. It is critical that we apply this technology to examine the basic assumptions that underly current rehabilitation practice. Here, we will use a video-based pose estimation workflow that has been previously developed by our lab to 1) contrast the gait patterns of persons post-stroke as observed in-clinical vs. in-home settings, and 2) map the rate of deterioration of clinically derived walking improvements, in the home. Our methodology has been used to accurately measure gait kinematics in people with stroke as they walk in laboratory, however we now seek to use these methods to record people with stroke as they walk in their natural home environments. The ultimate outcome of this project will not only be freely available video-based workflow modified for home-based gait assessments, but also preliminary data revealing how people with stroke walk in the real world.

R. James Cotton


Title: Longitudinal Mobile Gait Analysis of Individuals with Knee Osteoarthritis


  • Prakash Jayabalan, MD, PhD


In this project, we will perform longitudinal gait analysis for individuals with knee osteoarthritis seen in musculoskeletal clinic for intra-articular joint injections with collection of patient-reported outcome measures to identify biomechanical features associated with symptoms, changes in symptoms, and predictive of response to injections. Data will be acquired using a mobile gait analysis tool we have developed that combines video and wearable sensor data collected via a mobile app, which can easily and quickly integrate into a clinical workflow. The video analysis benefits from novel algorithms we have developed using a large gait lab dataset that allows accurate characterization of several spatiotemporal gait parameters on a cycle-by-cycle basis. This enables longitudinal monitoring for changes in gait following interventions using videos that subjects collect at home. We will develop models that predict the Knee Injury and Osteoarthritis Outcome Score during the clinic visit and at 4 and 8-week follow-up to identify biomechanical features associated with symptoms and responsive to injections.

Meghan Huber


Title: Mobile robot system to measure human kinematics in real world environments


  • Donghyun Kim, PhD (University of Massachusetts at Amherst)


Advancing the accessibility and efficacy of neuromotor rehabilitation requires new technology that enables robust and accurate measurements of human behavior during everyday activities in real-world conditions. Equipped with such data, clinicians can make more informed decisions on treatment based on factors such as the observance of undesirable compensatory strategies, changes in behavior due disease progression or injury recovery, level of active engagement, and the use and efficacy of an assistive device. To meet this need, the overall goal of our project is to enable a Mini-Cheetah quadruped robot to autonomously measure whole body human kinematics during walking in real-world environments with high accuracy and reliability. To this end, the proposed project aims to complete the following: (1) advance a Mini-Cheetah robot to be a mobile sensing system that can autonomously follow and measure the kinematics of a human during their daily activities; and (2) quantify the accuracy and reliability of human kinematic measurements from the mobile sensing system during walking experiments conducted in real-world (outdoor and indoor) environments. Successful completion of the aims will result novel and validated tool to measure human kinematics in real-world conditions that will have broad relevance in rehabilitation practice and research.

Ryan McGinnis


Title: Wearables-only Characterization of Real-world Joint and Muscle Loading in Patients Recovering from Orthopedic Surgery


  • Michael Toth, PhD (University of Vermont)
  • Nathaniel Nelms, PhD (University of Vermont Medical Center)


The purpose of this project is to advance a novel hybrid modeling approach for characterizing clinically relevant measures of skeletal muscle dysfunction and joint loading under free-living conditions using data from a minimal set of multi-modal wearable sensors. We will develop new methods for online calibration of neuromusculoskeletal models and synergy functions and complete a study to assess the feasibility for using this approach in the early post-operative period following total knee arthroplasty. This technology could provide an objective and continuous measure of functional recovery in this population. Currently, physical rehabilitation is meant to prevent or resolve muscle impairments and restore pre-morbid function immediately falling surgery, but most rehabilitation programs fall short of this goal. This is likely because most rehabilitation is performed at home, where the types of activities patients can perform are limited and adherence is low. Practical and financial constraints curtail outpatient visits, limiting the ability of providers to monitor functional recovery and intercede to personalize rehabilitative care to patient needs. If successful, this project has the potential to provide continuous and objective measures of functional recovery that could be used to inform personalized rehabilitation and may lead to a paradigm shift in rehabilitation practice.