Quantitative Pose-Based Analysis of Movement Disorders in Pediatric NGLY1 and SLC13A5 Patients

Chengliang Dai, Phil Scordis, Prathyusha Teeyagura, Rayann M. Solidum, Jeff Broderick, Julia Broderick, Jane Broderick, Brenda E. Porter
Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, PMLR 315:670-684, 2026.

Abstract

Movement disorders have long relied on subjective clinical observation for diagnosis and monitoring. By contrast, computer vision tools such as OpenPose can turn video recordings into precise, time-resolved measurements of a patient’s posture and movement. In this work, we apply a fully markerless, pose-based pipeline to classify abnormal movements in children with NGLY1 or SLC13A5 mutations. Our primary focus is on simple, physician-informed pose features that can be interpreted in clinical terms and used with conventional classifiers (Random Forest, SVM, etc.) on a very small dataset. We show that these handcrafted features capture clinically meaningful differences between movement-disorder phenotypes and can achieve useful classification performance. In addition, we include an exploratory comparison with a transformer model that is pre-trained on large-scale action-recognition data and then fine-tuned on our pose data. This experiment illustrates the potential performance ceiling of deep learning with extensive pretraining, but we emphasize that such models are less transparent and more data-hungry than the traditional approaches that form the core contribution of this study.

Cite this Paper

BibTeX
@InProceedings{pmlr-v315-dai26a, title = {Quantitative Pose-Based Analysis of Movement Disorders in Pediatric NGLY1 and SLC13A5 Patients}, author = {Dai, Chengliang and Scordis, Phil and Teeyagura, Prathyusha and Solidum, Rayann M. and Broderick, Jeff and Broderick, Julia and Broderick, Jane and Porter, Brenda E.}, booktitle = {Proceedings of The 9th International Conference on Medical Imaging with Deep Learning}, pages = {670--684}, year = {2026}, editor = {Huo, Yuankai and Gao, Mingchen and Kuo, Chang-Fu and Jin, Yueming and Deng, Ruining}, volume = {315}, series = {Proceedings of Machine Learning Research}, month = {08--10 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v315/main/assets/dai26a/dai26a.pdf}, url = {https://proceedings.mlr.press/v315/dai26a.html}, abstract = {Movement disorders have long relied on subjective clinical observation for diagnosis and monitoring. By contrast, computer vision tools such as OpenPose can turn video recordings into precise, time-resolved measurements of a patient’s posture and movement. In this work, we apply a fully markerless, pose-based pipeline to classify abnormal movements in children with NGLY1 or SLC13A5 mutations. Our primary focus is on simple, physician-informed pose features that can be interpreted in clinical terms and used with conventional classifiers (Random Forest, SVM, etc.) on a very small dataset. We show that these handcrafted features capture clinically meaningful differences between movement-disorder phenotypes and can achieve useful classification performance. In addition, we include an exploratory comparison with a transformer model that is pre-trained on large-scale action-recognition data and then fine-tuned on our pose data. This experiment illustrates the potential performance ceiling of deep learning with extensive pretraining, but we emphasize that such models are less transparent and more data-hungry than the traditional approaches that form the core contribution of this study.} }
Endnote
%0 Conference Paper %T Quantitative Pose-Based Analysis of Movement Disorders in Pediatric NGLY1 and SLC13A5 Patients %A Chengliang Dai %A Phil Scordis %A Prathyusha Teeyagura %A Rayann M. Solidum %A Jeff Broderick %A Julia Broderick %A Jane Broderick %A Brenda E. Porter %B Proceedings of The 9th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Yuankai Huo %E Mingchen Gao %E Chang-Fu Kuo %E Yueming Jin %E Ruining Deng %F pmlr-v315-dai26a %I PMLR %P 670--684 %U https://proceedings.mlr.press/v315/dai26a.html %V 315 %X Movement disorders have long relied on subjective clinical observation for diagnosis and monitoring. By contrast, computer vision tools such as OpenPose can turn video recordings into precise, time-resolved measurements of a patient’s posture and movement. In this work, we apply a fully markerless, pose-based pipeline to classify abnormal movements in children with NGLY1 or SLC13A5 mutations. Our primary focus is on simple, physician-informed pose features that can be interpreted in clinical terms and used with conventional classifiers (Random Forest, SVM, etc.) on a very small dataset. We show that these handcrafted features capture clinically meaningful differences between movement-disorder phenotypes and can achieve useful classification performance. In addition, we include an exploratory comparison with a transformer model that is pre-trained on large-scale action-recognition data and then fine-tuned on our pose data. This experiment illustrates the potential performance ceiling of deep learning with extensive pretraining, but we emphasize that such models are less transparent and more data-hungry than the traditional approaches that form the core contribution of this study.
APA
Dai, C., Scordis, P., Teeyagura, P., Solidum, R.M., Broderick, J., Broderick, J., Broderick, J. & Porter, B.E.. (2026). Quantitative Pose-Based Analysis of Movement Disorders in Pediatric NGLY1 and SLC13A5 Patients. Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 315:670-684 Available from https://proceedings.mlr.press/v315/dai26a.html.

Related Material