Journal Article in Journal of Biomechanics
Quantifying individualized rehabilitation responses and optimizing therapy for each person is challenging. For interventions like treadmill training, there are multiple parameters, such as speed or incline, that can be adjusted throughout sessions.
Aim: This study evaluates if causal modeling and Bayesian Additive Regression Trees (BART) can be used to accurately track the direct effects of treadmill training on gait.
Methods: We developed a Directed Acyclic Graph (DAG) to specify the assumed relationship between training input parameters and spatiotemporal outcomes during Short Burst Locomotor Treadmill Training (SBLTT), a therapy designed specifically for children with cerebral palsy (CP). We evaluated outcomes after 24 sessions of SBLTT for simulated datasets of 150 virtual participants and experimental data from four children with CP, ages 4–13 years old. Individual BART models were created from treadmill data of each step.
Results: Simulated datasets demonstrated that BART could accurately identify specified responses to training, including strong correlations for step length progression (R2 = 0.73) and plateaus (R2 = 0.87). Model fit was stronger for participants with less step-to-step variability but did not impact model accuracy. For experimental data, participants’ step lengths increased by 26 ± 13 % after 24 sessions. Using BART to control for speed or incline, we found that step length increased for three participants (direct effect: 13.5 ± 4.5 %), while one participant decreased step length (−11.6 %). SBLTT had minimal effects on step length asymmetry and step width.
Interpretation: Tools such as BART can leverage step-by-step data collected during training for researchers and clinicians to monitor progression, optimize rehabilitation protocols, and inform the causal mechanisms driving individual responses.
ASB 2024 Recap
Steele Lab members, Charlotte Caskey, Victoria (Tori) Landrum, and Megan Ebers, attended the American Society of Biomechanics Annual Meeting (ASB) in Madison, WI from August 5-8, 2024.
Charlotte gave a poster presentation on the “Effect of spinal stimulation and interval treadmill training on gait mechanics in children with cerebral palsy”
Tori also gave a poster presentation on the “Impact of a Resistive Exoskeleton on Fatigue in Children with Cerebral Palsy”
Megan co-hosted a Symposia Session titled, “Can machine learning reveal the next generation of neural and biomechanical processes governing human movement?” with Steele Lab Alumni, Michael Rosenberg. In Megan’s talk, “A machine learning approach to quantify individual gait responses to ankle exoskeletons,” she discussed how neural network-based discrepancy modeling can be used to isolate the dynamics governing changes in gait with ankle exoskeletons.
CMBBE 2024 Recap
Members of the Steele Lab traveled to Vancouver, BC for the 19th International Symposium on Computer Methods in Biomechanics and Biomedical Engineering (CMBBE) hosted by the University of British Columbia.
PhD candidate, Mackenzie Pitts, gave a poster presentation on “Inferring Unmeasured Inertial Data from Sparse Sensing for Treadmill Running”. Steele Lab Alumni and Post-Doctoral Research Fellow at Emory University, Michael Rosenberg, gave a podium presentation titled “Recurrent Neural Network Gait Signatures Encode Speed-Induced Changes in Post-Stroke Gait Quality.”
In addition to sharing their research at the conference, the Steele Lab enjoyed connecting with fellow biomechanics and biomedical engineering researchers as well as exploring the beautiful campus at UBC.
MR Ebers, JP Williams, KM Steele, JN Kutz (2024) “Leveraging arbitrary mobile sensor trajectories with shallow recurrent decoder networks for full-state reconstruction,”
Journal Article in IEEE Access
Sensing is a fundamental task for the monitoring, forecasting, and control of complex systems. In many applications, a limited number of sensors are available and must move with the dynamics. Currently, optimal path planning, like Kalman filter estimation, is required to enable sparse mobile sensing for state estimation. However, we show that arbitrary mobile sensor trajectories can be used. By adapting the Shallow REcurrent Decoder (SHRED) network with mobile sensors, their time-history can be used to encode global information of the measured high-dimensional state space.
Aim: We leverage sparse mobile sensor trajectories for full-state estimation, agnostic to sensor path.
Methods: Using modern deep learning architectures, we show that a sequence-to-vector model, such as an LSTM (long, short-term memory) network, with a decoder network, dynamic trajectory information can be mapped to full state-space estimates.
Results: We demonstrate that by leveraging mobile sensor trajectories with shallow recurrent decoder networks, we can train the network (i) to accurately reconstruct the full state space using arbitrary dynamical trajectories of the sensors, (ii) the architecture reduces the variance of the mean-squared error of the reconstruction error in comparison with immobile sensors, and (iii) the architecture also allows for rapid generalization (parameterization of dynamics) for data outside the training set. Moreover, the path of the sensor can be chosen arbitrarily, provided training data for the spatial trajectory of the sensor is available.
Interpretation: The time-history of mobile sensors can be used to encode global information of the measured high-dimensional state space.
Megan Ebers Presents at 2024 WiDS Puget Sound Conference
On May 14, 2024, Steele Lab members Dr. Megan Ebers, Mackenzie Pitts, and Dr. Kat Steele attended the Women in Data Science (WiDS) Puget Sound conference hosted at Seattle University. WiDS aims to inspire and educate data scientists worldwide, regardless of gender, and to support women in the field.
Among the speakers at the conference, postdoctoral scholar Dr. Megan Ebers gave a presentation titled “Data Expansion to Improve Accuracy and Availability of Digital Biomarkers for Human Health and Performance.”
