PK Gill, JM Donelan, KM Steele, MH Schwartz, AJ Ries (2025) Quantifying altered oxygen kinetics and reducing metabolic test times for children with cerebral palsy: a dual-exponential Bayesian modeling approach

Journal Article in Journal of Applied Physiology

Prior research using indirect calorimetry has shown that children with cerebral palsy (CP) exhibit significantly increased energetic costs during walking. However, metabolic testing to obtain oxygen cost is challenging. As a result, differences in oxygen uptake kinetics (V̇o2) in CP compared with their typically developing peers remain unexplored. Step changes in work rate have been shown to result in an exponential V̇o2 response with three distinct phases 1) cardiodynamic, 2) primary, and 3) steady-state.

Infographic titled “Slower oxygen kinetics and reduced metabolic testing times for children with cerebral palsy.” The conclusion states "“Conclusion: Time constants are longer in CP; only 3 minutes of data are needed for reliable steady- state walking estimates.Aim: This study aimed to apply a dual-exponential Bayesian model to assess the time constant of the primary phase V̇o2 response from resting to walking in children with CP. In addition, evaluate the model’s ability to estimate steady-state V̇o2 using shorter test durations.

Methods: A dual-exponential Bayesian model was applied to metabolic data from a sample of 263 children with CP. The model estimated the time constant of the primary phase V̇o₂ response and tested the accuracy of steady-state V̇o₂ estimation using only the first 3 minutes of data, compared to the standard 6-minute duration.

Results: The median V̇o2 time constant was 33.1 s (5th–95th percentile range: 14.5–69.8 s), significantly longer than reported values for typically developing children (range of means: 10.2–31.6 s). Furthermore, the model accurately estimated steady-state V̇o2 using only the first 3 min of metabolic data compared with the typical 6 min used in current clinical practice. The 3-min estimate explained >95% of the 6-min estimate variance, with <5% mean absolute error.

Interpretation: Slower oxygen kinetics in children with CP suggest impairments in metabolic control, potentially contributing to their higher energy demands. Although the exact mechanisms remain unclear, this study provides valuable insights into the walking energetics of children with CP and presents a more efficient method for analyzing V̇o2 for this population.

MN Pitts, MR Ebers, CE Agresta, KM Steele (2025) Evaluating Sparse Inertial Measurement Unit Configurations for Inferring Treadmill Running Motion

Journal Article in Sensors

 Inertial measurement units (IMUs) are used to analyze running performance. While leveraging one sensor to estimate kinematic and kinetic variables is common, sparsity limits the number of digital biomarkers that can be evaluated.

An illustration demonstrating experimental factors influencing the accuracy of motion inference when using Shallow recurrent decoder networks (SHRED) can reconstruct a dense set of time-series signals from a single input sensor. Running speed and sampling rate were most influential, while sensor location, and sensor type were neutral.Aim: Shallow recurrent decoder networks (SHRED) can reconstruct a dense set of time-series signals from a single input sensor and have been successful in human mobility applications, highlighting the potential for this algorithm to monitor running.

Methods: We trained and tested subject-specific SHRED models of nine subjects running on a treadmill to map from one input sensor to the remaining three IMUs. We varied the type of input to reflect experimental parameters that are important in running studies—sensor location, sensor type, sampling rate, and running speed—and compared the error of inferred signals from each input type.

Results: Sensor location and type did not impact SHRED inference accuracy, while decreasing the sampling rate affected the accuracy of ankle measurements. All ankle acceleration inferences from these models remained below the minimal detectable change threshold of 12.0 m/s2. SHRED models trained and tested at multiple speeds did not accurately infer IMU measurements below this threshold.

Interpretation: SHRED may broaden the scope of motion analysis by expanding access to data with fewer sensors. The data from this study and an instructional Jupyter notebook for training and testing individualized SHRED models are available at [link to GitHub].

CR DeVol, SR Shrivastav, AM Spomer, KF Bjornson, D Roge, CT Moritz, KM Steele (2024) “Effects of interval treadmill training on spatiotemporal parameters in children with cerebral palsy: A machine learning approach”

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.

A) Pre-post effect of SBLTT on step length for the more affected side. B) BART results quantify direct effects of SBLTT on step length. Accumulated Local Effects (ALE) plots for each input variable show the effect of that variable on step length including session number, treadmill speed (Froude number), time within session, side, and treadmill incline. The size of the data point on each ALE plot depicts the relative number of data points in each bin. C) BART model fit (R2) for each participant. D) Direct effects of each input variable on the response variable, step length, calculated from the change in the ALE plots in B).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.