Nicole Zaino wins the ESMAC Best Paper award

Congratulations to Nicole Zaino for being awarded the ESMAC (European Society of Movement Analysis for Adults and Children) Best Paper Award. Nicole received this award at the 2019 ESMAC conference in Amsterdam, September 23-28, 2019 where she gave her talk: “Spasticity reduction in children with cerebral palsy is not associated with reduced energy during walking.” For more information, visit ESMAC.

Woman in formal attire standing behind a black and purple podium in front of a large presentation screen

ESMAC 2019: Award Finalists

Congratulations to Nicole Zaino and our colleague Mike Schwartz at Gillette Children’s Specialty Healthcare for both being nominated as finalists for the Best Presentation Award at the upcoming ESMAC Conference in Amsterdam. Their abstracts are among the top 16 submissions to the conference and the final award will be determined based upon their presentations.

Logo for the 2019 ESMAC meeting overlaid on a classic Amsterdam scene, bikes lined up on a bridge over a canal with historic buildings in the background.

Nicole will be presenting her research:

Spasticity reduction in children with cerebral palsy is not associated with reduced energy during walking 

Selective dorsal rhizotomy reduces spasticity, but does it also reduce energy consumption during walking? In an analysis of over 300 children with cerebral palsy, Nicole demonstrated that although rhiztomy does reduce spasticity, it does not reduce energy consumption. These results provide further evidence that spasticity is not a main contributor to elevated energy among people with cerebral palsy. You can also learn more about this study from our recent submitted manuscript, available on bioRxiv.

Mike will be presenting his research:

The effects of walking speed and age on energy consumption in children with cerebral palsy and their typically developing peers

We know that walking energy is high among people with cerebral palsy, and that energy varies with speed and age. Using retrospective data of over 300 kids with cerebral palsy and 150 typically-developing peers, Mike used a statistical model to evaluate these speed and age effects. He found that energy decreases until 8-10 years of age for kids with CP, while it remains stable beyond age 5 for typically-developing peers. Kids with CP also have a greater elevation in energy with greater walking speeds. These results are important to help quantify and understand impacts of interventions, like surgery or assistive devices, which are often done during this time period when kids are still growing and developing.

They will both be presenting in the Optimizing Energy Cost session from 11:40-12:30 on Thursday, September 26th.

Best of luck to Nicole & Mike!

A Rozumalski, KM Steele, MH Schwartz (2017) “Muscle synergies are similar when typically developing children walk on a treadmill at different speeds and slopes.” Journal of Biomechanics

There were minimal changes in EMG signals with walking speed and slope.

Journal article in Journal of Biomechanics:

In collaboration with Gillette Children’s Specialty Healthcare, we evaluated whether muscle synergies change when unimpaired individuals walk at different speeds and slopes.

There were minimal changes in EMG signals with walking speed and slope.Background: The aim of this study was to determine whether changes in synergies relate to changes in gait while walking on a treadmill at multiple speeds and slopes. The hypothesis was that significant changes in movement pattern would not be accompanied by significant changes in synergies, suggesting that synergies are not dependent on the mechanical constraints but are instead neurological in origin.

Methods: Sixteen typically developing children walked on a treadmill for nine combinations (stages) of different speeds and slopes while simultaneously collecting kinematics, kinetics, and surface electromyography (EMG) data. The kinematics for each stride were summarized using a modified version of the Gait Deviation Index that only includes the sagittal plane. The kinetics for each stride were summarized using a modified version of the Gait Deviation Index – Kinetic which includes sagittal plane moments and powers. Within each synergy group, the correlations of the synergies were calculated between the treadmill stages.

Results: While kinematics and kinetics were significantly altered at the highest slope compared to level ground when walking on a treadmill, synergies were similar across stages.

Conclusions: The high correlations between synergies across stages indicate that neuromuscular control strategies do not change as children walk at different speeds and slopes on a treadmill. However, the multiple significant differences in kinematics and kinetics between stages indicate real differences in movement pattern. This supports the theory that synergies are neurological in origin and not simply a response to the biomechanical task constraints.

Jessica Zistatsis awarded CoMotion Innovation Fund grant

We are proud to announce that our very own Jessica Zistatsis has been awarded the CoMotion Innovation Fund grant. Jessica’s application process included market research, customer surveys, a lean canvas, and a 10 min pitch to a panel of investors. The CoMotion Innovation Fund will provide $40,000 to support research along with $10,000 for business development assistance through UW CoMotion.

jessicazThis award will support clinical trials with 10 kids with CP trying PlayGaitTM in Spring and Summer 2017 along with two quarters of Research Assistant support.

Jessica also just filed for a provisional patent.
Congratulations, Jessica!

B Soran, L Lowes, KM Steele (2016) “Evaluation of infants with spinal muscular atrophy using convolutional neural networks.” European Conference on Computer Vision

Experimental set-up with infant positioned below Kinect depth camera.

Peer-reviewed paper at European Conference on Computer Vision:

30-second videos from a depth camera can be used in the evaluation of infants with spinal muscular atrophy.

Experimental set-up with infant positioned below Kinect depth camera.Abstract: Spinal Muscular Atrophy is the most common genetic cause of infant death. Due to its severity, there is a need for methods for automated estimation of disease progression. In this paper we propose a Convolutional-Neural-Network (CNN) model to estimate disease progression during infants’ natural behavior. With the proposed methodology, we were able to predict each child’s score on current behavior-based clinical exams with an average per-subject error of 6.96 out of 72 points (<10 % difference), using 30-second videos in leave-one-subject-out-cross-validation setting. When simple statistics were used over 30-second video-segments to estimate a score for longer videos, we obtained an average error of 5.95 (8 % error rate). By showing promising results on a small dataset (N = 70, 2-minute samples, which were handled as 1487, 30-second video segments), our methodology demonstrates that it is possible to benefit from CNNs on small datasets by proper design and data handling choices.