Saved in:
| Main Authors: | , , , , , |
|---|---|
| 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 |