Saved in:
Bibliographic Details
Main Authors: Schwartz, Dafna, Quinn, Lori, Fritz, Nora E., Muratori, Lisa M., Hausdorff, Jeffery M., Bachrach, Ran Gilad
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.11286
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915065336168448
author Schwartz, Dafna
Quinn, Lori
Fritz, Nora E.
Muratori, Lisa M.
Hausdorff, Jeffery M.
Bachrach, Ran Gilad
author_facet Schwartz, Dafna
Quinn, Lori
Fritz, Nora E.
Muratori, Lisa M.
Hausdorff, Jeffery M.
Bachrach, Ran Gilad
contents Wearable sensors offer a non-invasive way to collect physical activity (PA) data, with walking as a key component. Existing models often struggle to detect gait bouts in individuals with neurodegenerative diseases (NDDs) involving involuntary movements. We developed J-Net, a deep learning model inspired by U-Net, which uses a pre-trained self-supervised foundation model fine-tuned with Huntington`s disease (HD) in-lab data and paired with a segmentation head for gait detection. J-Net processes wrist-worn accelerometer data to detect gait during daily living. We evaluated J-Net on in-lab and daily-living data from HD, Parkinson`s disease (PD), and controls. J-Net achieved a 10-percentage point improvement in ROC-AUC for HD over existing methods, reaching 0.97 for in-lab data. In daily-living environments, J-Net estimates showed no significant differences in median daily walking time between HD and controls (p = 0.23), in contrast to other models, which indicated counterintuitive results (p < 0.005). Walking time measured by J-Net correlated with the UHDRS-TMS clinical severity score (r=-0.52; p=0.02), confirming its clinical relevance. Fine-tuning J-Net on PD data also improved gait detection over current methods. J-Net`s architecture effectively addresses the challenges of gait detection in severe chorea and offers robust performance in daily living. The dataset and J-Net model are publicly available, providing a resource for further research into NDD-related gait impairments.
format Preprint
id arxiv_https___arxiv_org_abs_2412_11286
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Detecting Daily Living Gait Amid Huntington's Disease Chorea using a Foundation Deep Learning Model
Schwartz, Dafna
Quinn, Lori
Fritz, Nora E.
Muratori, Lisa M.
Hausdorff, Jeffery M.
Bachrach, Ran Gilad
Computer Vision and Pattern Recognition
Artificial Intelligence
Wearable sensors offer a non-invasive way to collect physical activity (PA) data, with walking as a key component. Existing models often struggle to detect gait bouts in individuals with neurodegenerative diseases (NDDs) involving involuntary movements. We developed J-Net, a deep learning model inspired by U-Net, which uses a pre-trained self-supervised foundation model fine-tuned with Huntington`s disease (HD) in-lab data and paired with a segmentation head for gait detection. J-Net processes wrist-worn accelerometer data to detect gait during daily living. We evaluated J-Net on in-lab and daily-living data from HD, Parkinson`s disease (PD), and controls. J-Net achieved a 10-percentage point improvement in ROC-AUC for HD over existing methods, reaching 0.97 for in-lab data. In daily-living environments, J-Net estimates showed no significant differences in median daily walking time between HD and controls (p = 0.23), in contrast to other models, which indicated counterintuitive results (p < 0.005). Walking time measured by J-Net correlated with the UHDRS-TMS clinical severity score (r=-0.52; p=0.02), confirming its clinical relevance. Fine-tuning J-Net on PD data also improved gait detection over current methods. J-Net`s architecture effectively addresses the challenges of gait detection in severe chorea and offers robust performance in daily living. The dataset and J-Net model are publicly available, providing a resource for further research into NDD-related gait impairments.
title Detecting Daily Living Gait Amid Huntington's Disease Chorea using a Foundation Deep Learning Model
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2412.11286