Care-PD: A Multi-Site Anonymized Clinical Dataset for Parkinson’s Disease Gait Assessment
University of Toronto Vector Institute · University Health Network · University of Toronto (UofT) · Delft University of Technology · University of Toronto · Université de Strasbourg · University of Illinois at Urbana-Champaign · University of Illinois · CNRS-Univ. Strasbourg · Hôpitaux Universitaires de Strasbourg · Universidade Federal do ABC · KU Leuven · Hasselt University · Emory University · University of Bristol · Toronto Rehab / University of Toronto
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
摘要
Objective gait assessment in Parkinson’s Disease (PD) is limited by the absence of large, diverse, and clinically annotated motion datasets. We introduce Care-PD, the largest publicly available archive of 3D mesh gait data for PD, and the first multi-site collection spanning 9 cohorts from 8 clinical centers. All recordings (RGB video or motion capture) are converted into anonymized SMPL meshes via a harmonized preprocessing pipeline. Care-PD supports two key benchmarks: supervised clinical score prediction (estimating Unified Parkinson’s Disease Rating Scale, UPDRS, gait scores) and unsupervised motion pretext tasks (2D-to-3D keypoint lifting and full-body 3D reconstruction). Clinical prediction is evaluated under four generalization protocols: within-dataset, cross-dataset, leave-one-dataset-out, and multi-dataset in-domain adaptation.To assess clinical relevance, we compare state-of-the-art motion encoders with a traditional gait-feature baseline, finding that encoders consistently outperform handcrafted features. Pretraining on Care-PD reduces MPJPE (from 60.8mm to 7.5mm) and boosts PD severity macro-F1 by 17\%, underscoring the value of clinically curated, diverse training data. Care-PD and all benchmark code are released for non-commercial research (Code, Data).